fix: dataset file upload not dataser editor

fix: package error

.github/workflows/build-push.yml

@@ -5,6 +5,7 @@ on:
     branches:
       - "main"
       - "deploy/dev"
+      - "fix/0.8.3-upload-auth"
   release:
     types: [published]
 

.github/workflows/web-tests.yml

@@ -1,46 +0,0 @@
-name: Web Tests
-
-on:
-  pull_request:
-    branches:
-      - main
-    paths:
-      - web/**
-
-concurrency:
-  group: web-tests-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  test:
-    name: Web Tests
-    runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: ./web
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Check changed files
-        id: changed-files
-        uses: tj-actions/changed-files@v45
-        with:
-          files: web/**
-
-      - name: Setup Node.js
-        uses: actions/setup-node@v4
-        if: steps.changed-files.outputs.any_changed == 'true'
-        with:
-          node-version: 20
-          cache: yarn
-          cache-dependency-path: ./web/package.json
-
-      - name: Install dependencies
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn install --frozen-lockfile
-
-      - name: Run tests
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: yarn test

api/.env.example

@@ -162,8 +162,6 @@ PGVECTOR_PORT=5433
 PGVECTOR_USER=postgres
 PGVECTOR_PASSWORD=postgres
 PGVECTOR_DATABASE=postgres
-PGVECTOR_MIN_CONNECTION=1
-PGVECTOR_MAX_CONNECTION=5
 
 # Tidb Vector configuration
 TIDB_VECTOR_HOST=xxx.eu-central-1.xxx.aws.tidbcloud.com

api/Dockerfile

@@ -55,7 +55,7 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends zlib1g=1:1.3.dfsg+really1.3.1-1 expat=2.6.3-1 libldap-2.5-0=2.5.18+dfsg-3 perl=5.38.2-5 libsqlite3-0=3.46.0-1 \
+    && apt-get install -y --no-install-recommends expat=2.6.4-1 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-8 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
     && apt-get autoremove -y \
     && rm -rf /var/lib/apt/lists/*
 

api/README.md

@@ -65,12 +65,14 @@
 
 8. Start Dify [web](../web) service.
 9. Setup your application by visiting `http://localhost:3000`...
-10. If you need to handle and debug the async tasks (e.g. dataset importing and documents indexing), please start the worker service.
+10. If you need to debug local async processing, please start the worker service.
 
    ```bash
    poetry run python -m celery -A app.celery worker -P gevent -c 1 --loglevel INFO -Q dataset,generation,mail,ops_trace,app_deletion
    ```
 
+   The started celery app handles the async tasks, e.g. dataset importing and documents indexing.
+
 ## Testing
 
 1. Install dependencies for both the backend and the test environment

api/app.py

@@ -53,9 +53,11 @@ from services.account_service import AccountService
 
 warnings.simplefilter("ignore", ResourceWarning)
 
-os.environ["TZ"] = "UTC"
-# windows platform not support tzset
-if hasattr(time, "tzset"):
+# fix windows platform
+if os.name == "nt":
+    os.system('tzutil /s "UTC"')
+else:
+    os.environ["TZ"] = "UTC"
     time.tzset()
 
 

api/commands.py

@@ -28,28 +28,28 @@ from services.account_service import RegisterService, TenantService
 
 
 @click.command("reset-password", help="Reset the account password.")
-@click.option("--email", prompt=True, help="Account email to reset password for")
-@click.option("--new-password", prompt=True, help="New password")
-@click.option("--password-confirm", prompt=True, help="Confirm new password")
+@click.option("--email", prompt=True, help="The email address of the account whose password you need to reset")
+@click.option("--new-password", prompt=True, help="the new password.")
+@click.option("--password-confirm", prompt=True, help="the new password confirm.")
 def reset_password(email, new_password, password_confirm):
     """
     Reset password of owner account
     Only available in SELF_HOSTED mode
     """
     if str(new_password).strip() != str(password_confirm).strip():
-        click.echo(click.style("Passwords do not match.", fg="red"))
+        click.echo(click.style("sorry. The two passwords do not match.", fg="red"))
         return
 
     account = db.session.query(Account).filter(Account.email == email).one_or_none()
 
     if not account:
-        click.echo(click.style("Account not found for email: {}".format(email), fg="red"))
+        click.echo(click.style("sorry. the account: [{}] not exist .".format(email), fg="red"))
         return
 
     try:
         valid_password(new_password)
     except:
-        click.echo(click.style("Invalid password. Must match {}".format(password_pattern), fg="red"))
+        click.echo(click.style("sorry. The passwords must match {} ".format(password_pattern), fg="red"))
         return
 
     # generate password salt
@@ -62,37 +62,37 @@ def reset_password(email, new_password, password_confirm):
     account.password = base64_password_hashed
     account.password_salt = base64_salt
     db.session.commit()
-    click.echo(click.style("Password reset successfully.", fg="green"))
+    click.echo(click.style("Congratulations! Password has been reset.", fg="green"))
 
 
 @click.command("reset-email", help="Reset the account email.")
-@click.option("--email", prompt=True, help="Current account email")
-@click.option("--new-email", prompt=True, help="New email")
-@click.option("--email-confirm", prompt=True, help="Confirm new email")
+@click.option("--email", prompt=True, help="The old email address of the account whose email you need to reset")
+@click.option("--new-email", prompt=True, help="the new email.")
+@click.option("--email-confirm", prompt=True, help="the new email confirm.")
 def reset_email(email, new_email, email_confirm):
     """
     Replace account email
     :return:
     """
     if str(new_email).strip() != str(email_confirm).strip():
-        click.echo(click.style("New emails do not match.", fg="red"))
+        click.echo(click.style("Sorry, new email and confirm email do not match.", fg="red"))
         return
 
     account = db.session.query(Account).filter(Account.email == email).one_or_none()
 
     if not account:
-        click.echo(click.style("Account not found for email: {}".format(email), fg="red"))
+        click.echo(click.style("sorry. the account: [{}] not exist .".format(email), fg="red"))
         return
 
     try:
         email_validate(new_email)
     except:
-        click.echo(click.style("Invalid email: {}".format(new_email), fg="red"))
+        click.echo(click.style("sorry. {} is not a valid email. ".format(email), fg="red"))
         return
 
     account.email = new_email
     db.session.commit()
-    click.echo(click.style("Email updated successfully.", fg="green"))
+    click.echo(click.style("Congratulations!, email has been reset.", fg="green"))
 
 
 @click.command(
@@ -104,7 +104,7 @@ def reset_email(email, new_email, email_confirm):
 )
 @click.confirmation_option(
     prompt=click.style(
-        "Are you sure you want to reset encrypt key pair? This operation cannot be rolled back!", fg="red"
+        "Are you sure you want to reset encrypt key pair? this operation cannot be rolled back!", fg="red"
     )
 )
 def reset_encrypt_key_pair():
@@ -114,13 +114,13 @@ def reset_encrypt_key_pair():
     Only support SELF_HOSTED mode.
     """
     if dify_config.EDITION != "SELF_HOSTED":
-        click.echo(click.style("This command is only for SELF_HOSTED installations.", fg="red"))
+        click.echo(click.style("Sorry, only support SELF_HOSTED mode.", fg="red"))
         return
 
     tenants = db.session.query(Tenant).all()
     for tenant in tenants:
         if not tenant:
-            click.echo(click.style("No workspaces found. Run /install first.", fg="red"))
+            click.echo(click.style("Sorry, no workspace found. Please enter /install to initialize.", fg="red"))
             return
 
         tenant.encrypt_public_key = generate_key_pair(tenant.id)
@@ -137,7 +137,7 @@ def reset_encrypt_key_pair():
         )
 
 
-@click.command("vdb-migrate", help="Migrate vector db.")
+@click.command("vdb-migrate", help="migrate vector db.")
 @click.option("--scope", default="all", prompt=False, help="The scope of vector database to migrate, Default is All.")
 def vdb_migrate(scope: str):
     if scope in {"knowledge", "all"}:
@@ -150,7 +150,7 @@ def migrate_annotation_vector_database():
     """
     Migrate annotation datas to target vector database .
     """
-    click.echo(click.style("Starting annotation data migration.", fg="green"))
+    click.echo(click.style("Start migrate annotation data.", fg="green"))
     create_count = 0
     skipped_count = 0
     total_count = 0
@@ -174,14 +174,14 @@ def migrate_annotation_vector_database():
                 f"Processing the {total_count} app {app.id}. " + f"{create_count} created, {skipped_count} skipped."
             )
             try:
-                click.echo("Creating app annotation index: {}".format(app.id))
+                click.echo("Create app annotation index: {}".format(app.id))
                 app_annotation_setting = (
                     db.session.query(AppAnnotationSetting).filter(AppAnnotationSetting.app_id == app.id).first()
                 )
 
                 if not app_annotation_setting:
                     skipped_count = skipped_count + 1
-                    click.echo("App annotation setting disabled: {}".format(app.id))
+                    click.echo("App annotation setting is disabled: {}".format(app.id))
                     continue
                 # get dataset_collection_binding info
                 dataset_collection_binding = (
@@ -190,7 +190,7 @@ def migrate_annotation_vector_database():
                     .first()
                 )
                 if not dataset_collection_binding:
-                    click.echo("App annotation collection binding not found: {}".format(app.id))
+                    click.echo("App annotation collection binding is not exist: {}".format(app.id))
                     continue
                 annotations = db.session.query(MessageAnnotation).filter(MessageAnnotation.app_id == app.id).all()
                 dataset = Dataset(
@@ -211,11 +211,11 @@ def migrate_annotation_vector_database():
                         documents.append(document)
 
                 vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
-                click.echo(f"Migrating annotations for app: {app.id}.")
+                click.echo(f"Start to migrate annotation, app_id: {app.id}.")
 
                 try:
                     vector.delete()
-                    click.echo(click.style(f"Deleted vector index for app {app.id}.", fg="green"))
+                    click.echo(click.style(f"Successfully delete vector index for app: {app.id}.", fg="green"))
                 except Exception as e:
                     click.echo(click.style(f"Failed to delete vector index for app {app.id}.", fg="red"))
                     raise e
@@ -223,12 +223,12 @@ def migrate_annotation_vector_database():
                     try:
                         click.echo(
                             click.style(
-                                f"Creating vector index with {len(documents)} annotations for app {app.id}.",
+                                f"Start to created vector index with {len(documents)} annotations for app {app.id}.",
                                 fg="green",
                             )
                         )
                         vector.create(documents)
-                        click.echo(click.style(f"Created vector index for app {app.id}.", fg="green"))
+                        click.echo(click.style(f"Successfully created vector index for app {app.id}.", fg="green"))
                     except Exception as e:
                         click.echo(click.style(f"Failed to created vector index for app {app.id}.", fg="red"))
                         raise e
@@ -237,14 +237,14 @@ def migrate_annotation_vector_database():
             except Exception as e:
                 click.echo(
                     click.style(
-                        "Error creating app annotation index: {} {}".format(e.__class__.__name__, str(e)), fg="red"
+                        "Create app annotation index error: {} {}".format(e.__class__.__name__, str(e)), fg="red"
                     )
                 )
                 continue
 
     click.echo(
         click.style(
-            f"Migration complete. Created {create_count} app annotation indexes. Skipped {skipped_count} apps.",
+            f"Congratulations! Create {create_count} app annotation indexes, and skipped {skipped_count} apps.",
             fg="green",
         )
     )
@@ -254,7 +254,7 @@ def migrate_knowledge_vector_database():
     """
     Migrate vector database datas to target vector database .
     """
-    click.echo(click.style("Starting vector database migration.", fg="green"))
+    click.echo(click.style("Start migrate vector db.", fg="green"))
     create_count = 0
     skipped_count = 0
     total_count = 0
@@ -278,7 +278,7 @@ def migrate_knowledge_vector_database():
                 f"Processing the {total_count} dataset {dataset.id}. {create_count} created, {skipped_count} skipped."
             )
             try:
-                click.echo("Creating dataset vector database index: {}".format(dataset.id))
+                click.echo("Create dataset vdb index: {}".format(dataset.id))
                 if dataset.index_struct_dict:
                     if dataset.index_struct_dict["type"] == vector_type:
                         skipped_count = skipped_count + 1
@@ -299,7 +299,7 @@ def migrate_knowledge_vector_database():
                         if dataset_collection_binding:
                             collection_name = dataset_collection_binding.collection_name
                         else:
-                            raise ValueError("Dataset Collection Binding not found")
+                            raise ValueError("Dataset Collection Bindings is not exist!")
                     else:
                         dataset_id = dataset.id
                         collection_name = Dataset.gen_collection_name_by_id(dataset_id)
@@ -351,12 +351,14 @@ def migrate_knowledge_vector_database():
                     raise ValueError(f"Vector store {vector_type} is not supported.")
 
                 vector = Vector(dataset)
-                click.echo(f"Migrating dataset {dataset.id}.")
+                click.echo(f"Start to migrate dataset {dataset.id}.")
 
                 try:
                     vector.delete()
                     click.echo(
-                        click.style(f"Deleted vector index {collection_name} for dataset {dataset.id}.", fg="green")
+                        click.style(
+                            f"Successfully delete vector index {collection_name} for dataset {dataset.id}.", fg="green"
+                        )
                     )
                 except Exception as e:
                     click.echo(
@@ -408,13 +410,15 @@ def migrate_knowledge_vector_database():
                     try:
                         click.echo(
                             click.style(
-                                f"Creating vector index with {len(documents)} documents of {segments_count}"
+                                f"Start to created vector index with {len(documents)} documents of {segments_count}"
                                 f" segments for dataset {dataset.id}.",
                                 fg="green",
                             )
                         )
                         vector.create(documents)
-                        click.echo(click.style(f"Created vector index for dataset {dataset.id}.", fg="green"))
+                        click.echo(
+                            click.style(f"Successfully created vector index for dataset {dataset.id}.", fg="green")
+                        )
                     except Exception as e:
                         click.echo(click.style(f"Failed to created vector index for dataset {dataset.id}.", fg="red"))
                         raise e
@@ -425,13 +429,13 @@ def migrate_knowledge_vector_database():
             except Exception as e:
                 db.session.rollback()
                 click.echo(
-                    click.style("Error creating dataset index: {} {}".format(e.__class__.__name__, str(e)), fg="red")
+                    click.style("Create dataset index error: {} {}".format(e.__class__.__name__, str(e)), fg="red")
                 )
                 continue
 
     click.echo(
         click.style(
-            f"Migration complete. Created {create_count} dataset indexes. Skipped {skipped_count} datasets.", fg="green"
+            f"Congratulations! Create {create_count} dataset indexes, and skipped {skipped_count} datasets.", fg="green"
         )
     )
 
@@ -441,7 +445,7 @@ def convert_to_agent_apps():
     """
     Convert Agent Assistant to Agent App.
     """
-    click.echo(click.style("Starting convert to agent apps.", fg="green"))
+    click.echo(click.style("Start convert to agent apps.", fg="green"))
 
     proceeded_app_ids = []
 
@@ -492,23 +496,23 @@ def convert_to_agent_apps():
             except Exception as e:
                 click.echo(click.style("Convert app error: {} {}".format(e.__class__.__name__, str(e)), fg="red"))
 
-    click.echo(click.style("Conversion complete. Converted {} agent apps.".format(len(proceeded_app_ids)), fg="green"))
+    click.echo(click.style("Congratulations! Converted {} agent apps.".format(len(proceeded_app_ids)), fg="green"))
 
 
-@click.command("add-qdrant-doc-id-index", help="Add Qdrant doc_id index.")
-@click.option("--field", default="metadata.doc_id", prompt=False, help="Index field , default is metadata.doc_id.")
+@click.command("add-qdrant-doc-id-index", help="add qdrant doc_id index.")
+@click.option("--field", default="metadata.doc_id", prompt=False, help="index field , default is metadata.doc_id.")
 def add_qdrant_doc_id_index(field: str):
-    click.echo(click.style("Starting Qdrant doc_id index creation.", fg="green"))
+    click.echo(click.style("Start add qdrant doc_id index.", fg="green"))
     vector_type = dify_config.VECTOR_STORE
     if vector_type != "qdrant":
-        click.echo(click.style("This command only supports Qdrant vector store.", fg="red"))
+        click.echo(click.style("Sorry, only support qdrant vector store.", fg="red"))
         return
     create_count = 0
 
     try:
         bindings = db.session.query(DatasetCollectionBinding).all()
         if not bindings:
-            click.echo(click.style("No dataset collection bindings found.", fg="red"))
+            click.echo(click.style("Sorry, no dataset collection bindings found.", fg="red"))
             return
         import qdrant_client
         from qdrant_client.http.exceptions import UnexpectedResponse
@@ -518,7 +522,7 @@ def add_qdrant_doc_id_index(field: str):
 
         for binding in bindings:
             if dify_config.QDRANT_URL is None:
-                raise ValueError("Qdrant URL is required.")
+                raise ValueError("Qdrant url is required.")
             qdrant_config = QdrantConfig(
                 endpoint=dify_config.QDRANT_URL,
                 api_key=dify_config.QDRANT_API_KEY,
@@ -535,39 +539,41 @@ def add_qdrant_doc_id_index(field: str):
             except UnexpectedResponse as e:
                 # Collection does not exist, so return
                 if e.status_code == 404:
-                    click.echo(click.style(f"Collection not found: {binding.collection_name}.", fg="red"))
+                    click.echo(
+                        click.style(f"Collection not found, collection_name:{binding.collection_name}.", fg="red")
+                    )
                     continue
                 # Some other error occurred, so re-raise the exception
                 else:
                     click.echo(
                         click.style(
-                            f"Failed to create Qdrant index for collection: {binding.collection_name}.", fg="red"
+                            f"Failed to create qdrant index, collection_name:{binding.collection_name}.", fg="red"
                         )
                     )
 
     except Exception as e:
-        click.echo(click.style("Failed to create Qdrant client.", fg="red"))
+        click.echo(click.style("Failed to create qdrant client.", fg="red"))
 
-    click.echo(click.style(f"Index creation complete. Created {create_count} collection indexes.", fg="green"))
+    click.echo(click.style(f"Congratulations! Create {create_count} collection indexes.", fg="green"))
 
 
 @click.command("create-tenant", help="Create account and tenant.")
-@click.option("--email", prompt=True, help="Tenant account email.")
-@click.option("--name", prompt=True, help="Workspace name.")
+@click.option("--email", prompt=True, help="The email address of the tenant account.")
+@click.option("--name", prompt=True, help="The workspace name of the tenant account.")
 @click.option("--language", prompt=True, help="Account language, default: en-US.")
 def create_tenant(email: str, language: Optional[str] = None, name: Optional[str] = None):
     """
     Create tenant account
     """
     if not email:
-        click.echo(click.style("Email is required.", fg="red"))
+        click.echo(click.style("Sorry, email is required.", fg="red"))
         return
 
     # Create account
     email = email.strip()
 
     if "@" not in email:
-        click.echo(click.style("Invalid email address.", fg="red"))
+        click.echo(click.style("Sorry, invalid email address.", fg="red"))
         return
 
     account_name = email.split("@")[0]
@@ -587,19 +593,19 @@ def create_tenant(email: str, language: Optional[str] = None, name: Optional[str
 
     click.echo(
         click.style(
-            "Account and tenant created.\nAccount: {}\nPassword: {}".format(email, new_password),
+            "Congratulations! Account and tenant created.\nAccount: {}\nPassword: {}".format(email, new_password),
             fg="green",
         )
     )
 
 
-@click.command("upgrade-db", help="Upgrade the database")
+@click.command("upgrade-db", help="upgrade the database")
 def upgrade_db():
     click.echo("Preparing database migration...")
     lock = redis_client.lock(name="db_upgrade_lock", timeout=60)
     if lock.acquire(blocking=False):
         try:
-            click.echo(click.style("Starting database migration.", fg="green"))
+            click.echo(click.style("Start database migration.", fg="green"))
 
             # run db migration
             import flask_migrate
@@ -609,7 +615,7 @@ def upgrade_db():
             click.echo(click.style("Database migration successful!", fg="green"))
 
         except Exception as e:
-            logging.exception(f"Database migration failed: {e}")
+            logging.exception(f"Database migration failed, error: {e}")
         finally:
             lock.release()
     else:
@@ -621,7 +627,7 @@ def fix_app_site_missing():
     """
     Fix app related site missing issue.
     """
-    click.echo(click.style("Starting fix for missing app-related sites.", fg="green"))
+    click.echo(click.style("Start fix app related site missing issue.", fg="green"))
 
     failed_app_ids = []
     while True:
@@ -644,22 +650,22 @@ where sites.id is null limit 1000"""
                     if tenant:
                         accounts = tenant.get_accounts()
                         if not accounts:
-                            print("Fix failed for app {}".format(app.id))
+                            print("Fix app {} failed.".format(app.id))
                             continue
 
                         account = accounts[0]
-                        print("Fixing missing site for app {}".format(app.id))
+                        print("Fix app {} related site missing issue.".format(app.id))
                         app_was_created.send(app, account=account)
                 except Exception as e:
                     failed_app_ids.append(app_id)
-                    click.echo(click.style("Failed to fix missing site for app {}".format(app_id), fg="red"))
+                    click.echo(click.style("Fix app {} related site missing issue failed!".format(app_id), fg="red"))
                     logging.exception(f"Fix app related site missing issue failed, error: {e}")
                     continue
 
             if not processed_count:
                 break
 
-    click.echo(click.style("Fix for missing app-related sites completed successfully!", fg="green"))
+    click.echo(click.style("Congratulations! Fix app related site missing issue successful!", fg="green"))
 
 
 def register_commands(app):

api/configs/deploy/__init__.py

@@ -4,30 +4,30 @@ from pydantic_settings import BaseSettings
 
 class DeploymentConfig(BaseSettings):
     """
-    Configuration settings for application deployment
+    Deployment configs
     """
 
     APPLICATION_NAME: str = Field(
-        description="Name of the application, used for identification and logging purposes",
+        description="application name",
         default="langgenius/dify",
     )
 
     DEBUG: bool = Field(
-        description="Enable debug mode for additional logging and development features",
+        description="whether to enable debug mode.",
         default=False,
     )
 
     TESTING: bool = Field(
-        description="Enable testing mode for running automated tests",
+        description="",
         default=False,
     )
 
     EDITION: str = Field(
-        description="Deployment edition of the application (e.g., 'SELF_HOSTED', 'CLOUD')",
+        description="deployment edition",
         default="SELF_HOSTED",
     )
 
     DEPLOY_ENV: str = Field(
-        description="Deployment environment (e.g., 'PRODUCTION', 'DEVELOPMENT'), default to PRODUCTION",
+        description="deployment environment, default to PRODUCTION.",
         default="PRODUCTION",
     )

api/configs/enterprise/__init__.py

@@ -4,17 +4,17 @@ from pydantic_settings import BaseSettings
 
 class EnterpriseFeatureConfig(BaseSettings):
     """
-    Configuration for enterprise-level features.
+    Enterprise feature configs.
     **Before using, please contact business@dify.ai by email to inquire about licensing matters.**
     """
 
     ENTERPRISE_ENABLED: bool = Field(
-        description="Enable or disable enterprise-level features."
+        description="whether to enable enterprise features."
         "Before using, please contact business@dify.ai by email to inquire about licensing matters.",
         default=False,
     )
 
     CAN_REPLACE_LOGO: bool = Field(
-        description="Allow customization of the enterprise logo.",
+        description="whether to allow replacing enterprise logo.",
         default=False,
     )

api/configs/extra/notion_config.py

@@ -6,31 +6,30 @@ from pydantic_settings import BaseSettings
 
 class NotionConfig(BaseSettings):
     """
-    Configuration settings for Notion integration
+    Notion integration configs
     """
 
     NOTION_CLIENT_ID: Optional[str] = Field(
-        description="Client ID for Notion API authentication. Required for OAuth 2.0 flow.",
+        description="Notion client ID",
         default=None,
     )
 
     NOTION_CLIENT_SECRET: Optional[str] = Field(
-        description="Client secret for Notion API authentication. Required for OAuth 2.0 flow.",
+        description="Notion client secret key",
         default=None,
     )
 
     NOTION_INTEGRATION_TYPE: Optional[str] = Field(
-        description="Type of Notion integration."
-        " Set to 'internal' for internal integrations, or None for public integrations.",
+        description="Notion integration type, default to None, available values: internal.",
         default=None,
     )
 
     NOTION_INTERNAL_SECRET: Optional[str] = Field(
-        description="Secret key for internal Notion integrations. Required when NOTION_INTEGRATION_TYPE is 'internal'.",
+        description="Notion internal secret key",
         default=None,
     )
 
     NOTION_INTEGRATION_TOKEN: Optional[str] = Field(
-        description="Integration token for Notion API access. Used for direct API calls without OAuth flow.",
+        description="Notion integration token",
         default=None,
     )

api/configs/extra/sentry_config.py

@@ -6,23 +6,20 @@ from pydantic_settings import BaseSettings
 
 class SentryConfig(BaseSettings):
     """
-    Configuration settings for Sentry error tracking and performance monitoring
+    Sentry configs
     """
 
     SENTRY_DSN: Optional[str] = Field(
-        description="Sentry Data Source Name (DSN)."
-        " This is the unique identifier of your Sentry project, used to send events to the correct project.",
+        description="Sentry DSN",
         default=None,
     )
 
     SENTRY_TRACES_SAMPLE_RATE: NonNegativeFloat = Field(
-        description="Sample rate for Sentry performance monitoring traces."
-        " Value between 0.0 and 1.0, where 1.0 means 100% of traces are sent to Sentry.",
+        description="Sentry trace sample rate",
         default=1.0,
     )
 
     SENTRY_PROFILES_SAMPLE_RATE: NonNegativeFloat = Field(
-        description="Sample rate for Sentry profiling."
-        " Value between 0.0 and 1.0, where 1.0 means 100% of profiles are sent to Sentry.",
+        description="Sentry profiles sample rate",
         default=1.0,
     )

api/configs/feature/__init__.py

@@ -8,143 +8,145 @@ from configs.feature.hosted_service import HostedServiceConfig
 
 class SecurityConfig(BaseSettings):
     """
-    Security-related configurations for the application
+    Secret Key configs
     """
 
     SECRET_KEY: Optional[str] = Field(
-        description="Secret key for secure session cookie signing."
+        description="Your App secret key will be used for securely signing the session cookie"
         "Make sure you are changing this key for your deployment with a strong key."
-        "Generate a strong key using `openssl rand -base64 42` or set via the `SECRET_KEY` environment variable.",
+        "You can generate a strong key using `openssl rand -base64 42`."
+        "Alternatively you can set it with `SECRET_KEY` environment variable.",
         default=None,
     )
 
     RESET_PASSWORD_TOKEN_EXPIRY_HOURS: PositiveInt = Field(
-        description="Duration in hours for which a password reset token remains valid",
+        description="Expiry time in hours for reset token",
         default=24,
     )
 
 
 class AppExecutionConfig(BaseSettings):
     """
-    Configuration parameters for application execution
+    App Execution configs
     """
 
     APP_MAX_EXECUTION_TIME: PositiveInt = Field(
-        description="Maximum allowed execution time for the application in seconds",
+        description="execution timeout in seconds for app execution",
         default=1200,
     )
     APP_MAX_ACTIVE_REQUESTS: NonNegativeInt = Field(
-        description="Maximum number of concurrent active requests per app (0 for unlimited)",
+        description="max active request per app, 0 means unlimited",
         default=0,
     )
 
 
 class CodeExecutionSandboxConfig(BaseSettings):
     """
-    Configuration for the code execution sandbox environment
+    Code Execution Sandbox configs
     """
 
     CODE_EXECUTION_ENDPOINT: HttpUrl = Field(
-        description="URL endpoint for the code execution service",
+        description="endpoint URL of code execution service",
         default="http://sandbox:8194",
     )
 
     CODE_EXECUTION_API_KEY: str = Field(
-        description="API key for accessing the code execution service",
+        description="API key for code execution service",
         default="dify-sandbox",
     )
 
     CODE_EXECUTION_CONNECT_TIMEOUT: Optional[float] = Field(
-        description="Connection timeout in seconds for code execution requests",
+        description="connect timeout in seconds for code execution request",
         default=10.0,
     )
 
     CODE_EXECUTION_READ_TIMEOUT: Optional[float] = Field(
-        description="Read timeout in seconds for code execution requests",
+        description="read timeout in seconds for code execution request",
         default=60.0,
     )
 
     CODE_EXECUTION_WRITE_TIMEOUT: Optional[float] = Field(
-        description="Write timeout in seconds for code execution request",
+        description="write timeout in seconds for code execution request",
         default=10.0,
     )
 
     CODE_MAX_NUMBER: PositiveInt = Field(
-        description="Maximum allowed numeric value in code execution",
+        description="max depth for code execution",
         default=9223372036854775807,
     )
 
     CODE_MIN_NUMBER: NegativeInt = Field(
-        description="Minimum allowed numeric value in code execution",
+        description="",
         default=-9223372036854775807,
     )
 
     CODE_MAX_DEPTH: PositiveInt = Field(
-        description="Maximum allowed depth for nested structures in code execution",
+        description="max depth for code execution",
         default=5,
     )
 
     CODE_MAX_PRECISION: PositiveInt = Field(
-        description="mMaximum number of decimal places for floating-point numbers in code execution",
+        description="max precision digits for float type in code execution",
         default=20,
     )
 
     CODE_MAX_STRING_LENGTH: PositiveInt = Field(
-        description="Maximum allowed length for strings in code execution",
+        description="max string length for code execution",
         default=80000,
     )
 
     CODE_MAX_STRING_ARRAY_LENGTH: PositiveInt = Field(
-        description="Maximum allowed length for string arrays in code execution",
+        description="",
         default=30,
     )
 
     CODE_MAX_OBJECT_ARRAY_LENGTH: PositiveInt = Field(
-        description="Maximum allowed length for object arrays in code execution",
+        description="",
         default=30,
     )
 
     CODE_MAX_NUMBER_ARRAY_LENGTH: PositiveInt = Field(
-        description="Maximum allowed length for numeric arrays in code execution",
+        description="",
         default=1000,
     )
 
 
 class EndpointConfig(BaseSettings):
     """
-    Configuration for various application endpoints and URLs
+    Module URL configs
     """
 
     CONSOLE_API_URL: str = Field(
-        description="Base URL for the console API,"
-        "used for login authentication callback or notion integration callbacks",
+        description="The backend URL prefix of the console API."
+        "used to concatenate the login authorization callback or notion integration callback.",
         default="",
     )
 
     CONSOLE_WEB_URL: str = Field(
-        description="Base URL for the console web interface," "used for frontend references and CORS configuration",
+        description="The front-end URL prefix of the console web."
+        "used to concatenate some front-end addresses and for CORS configuration use.",
         default="",
     )
 
     SERVICE_API_URL: str = Field(
-        description="Base URL for the service API, displayed to users for API access",
+        description="Service API Url prefix. used to display Service API Base Url to the front-end.",
         default="",
     )
 
     APP_WEB_URL: str = Field(
-        description="Base URL for the web application, used for frontend references",
+        description="WebApp Url prefix. used to display WebAPP API Base Url to the front-end.",
         default="",
     )
 
 
 class FileAccessConfig(BaseSettings):
     """
-    Configuration for file access and handling
+    File Access configs
     """
 
     FILES_URL: str = Field(
-        description="Base URL for file preview or download,"
-        " used for frontend display and multi-model inputs"
+        description="File preview or download Url prefix."
+        " used to display File preview or download Url to the front-end or as Multi-model inputs;"
         "Url is signed and has expiration time.",
         validation_alias=AliasChoices("FILES_URL", "CONSOLE_API_URL"),
         alias_priority=1,
@@ -152,49 +154,49 @@ class FileAccessConfig(BaseSettings):
     )
 
     FILES_ACCESS_TIMEOUT: int = Field(
-        description="Expiration time in seconds for file access URLs",
+        description="timeout in seconds for file accessing",
         default=300,
     )
 
 
 class FileUploadConfig(BaseSettings):
     """
-    Configuration for file upload limitations
+    File Uploading configs
     """
 
     UPLOAD_FILE_SIZE_LIMIT: NonNegativeInt = Field(
-        description="Maximum allowed file size for uploads in megabytes",
+        description="size limit in Megabytes for uploading files",
         default=15,
     )
 
     UPLOAD_FILE_BATCH_LIMIT: NonNegativeInt = Field(
-        description="Maximum number of files allowed in a single upload batch",
+        description="batch size limit for uploading files",
         default=5,
     )
 
     UPLOAD_IMAGE_FILE_SIZE_LIMIT: NonNegativeInt = Field(
-        description="Maximum allowed image file size for uploads in megabytes",
+        description="image file size limit in Megabytes for uploading files",
         default=10,
     )
 
     BATCH_UPLOAD_LIMIT: NonNegativeInt = Field(
-        description="Maximum number of files allowed in a batch upload operation",
+        description="",  # todo: to be clarified
         default=20,
     )
 
 
 class HttpConfig(BaseSettings):
     """
-    HTTP-related configurations for the application
+    HTTP configs
     """
 
     API_COMPRESSION_ENABLED: bool = Field(
-        description="Enable or disable gzip compression for HTTP responses",
+        description="whether to enable HTTP response compression of gzip",
         default=False,
     )
 
     inner_CONSOLE_CORS_ALLOW_ORIGINS: str = Field(
-        description="Comma-separated list of allowed origins for CORS in the console",
+        description="",
         validation_alias=AliasChoices("CONSOLE_CORS_ALLOW_ORIGINS", "CONSOLE_WEB_URL"),
         default="",
     )
@@ -216,360 +218,359 @@ class HttpConfig(BaseSettings):
         return self.inner_WEB_API_CORS_ALLOW_ORIGINS.split(",")
 
     HTTP_REQUEST_MAX_CONNECT_TIMEOUT: Annotated[
-        PositiveInt, Field(ge=10, description="Maximum connection timeout in seconds for HTTP requests")
+        PositiveInt, Field(ge=10, description="connect timeout in seconds for HTTP request")
     ] = 10
 
     HTTP_REQUEST_MAX_READ_TIMEOUT: Annotated[
-        PositiveInt, Field(ge=60, description="Maximum read timeout in seconds for HTTP requests")
+        PositiveInt, Field(ge=60, description="read timeout in seconds for HTTP request")
     ] = 60
 
     HTTP_REQUEST_MAX_WRITE_TIMEOUT: Annotated[
-        PositiveInt, Field(ge=10, description="Maximum write timeout in seconds for HTTP requests")
+        PositiveInt, Field(ge=10, description="read timeout in seconds for HTTP request")
     ] = 20
 
     HTTP_REQUEST_NODE_MAX_BINARY_SIZE: PositiveInt = Field(
-        description="Maximum allowed size in bytes for binary data in HTTP requests",
+        description="",
         default=10 * 1024 * 1024,
     )
 
     HTTP_REQUEST_NODE_MAX_TEXT_SIZE: PositiveInt = Field(
-        description="Maximum allowed size in bytes for text data in HTTP requests",
+        description="",
         default=1 * 1024 * 1024,
     )
 
     SSRF_PROXY_HTTP_URL: Optional[str] = Field(
-        description="Proxy URL for HTTP requests to prevent Server-Side Request Forgery (SSRF)",
+        description="HTTP URL for SSRF proxy",
         default=None,
     )
 
     SSRF_PROXY_HTTPS_URL: Optional[str] = Field(
-        description="Proxy URL for HTTPS requests to prevent Server-Side Request Forgery (SSRF)",
+        description="HTTPS URL for SSRF proxy",
         default=None,
     )
 
 
 class InnerAPIConfig(BaseSettings):
     """
-    Configuration for internal API functionality
+    Inner API configs
     """
 
     INNER_API: bool = Field(
-        description="Enable or disable the internal API",
+        description="whether to enable the inner API",
         default=False,
     )
 
     INNER_API_KEY: Optional[str] = Field(
-        description="API key for accessing the internal API",
+        description="The inner API key is used to authenticate the inner API",
         default=None,
     )
 
 
 class LoggingConfig(BaseSettings):
     """
-    Configuration for application logging
+    Logging configs
     """
 
     LOG_LEVEL: str = Field(
-        description="Logging level, default to INFO. Set to ERROR for production environments.",
+        description="Log output level, default to INFO. It is recommended to set it to ERROR for production.",
         default="INFO",
     )
 
     LOG_FILE: Optional[str] = Field(
-        description="File path for log output.",
+        description="logging output file path",
         default=None,
     )
 
     LOG_FORMAT: str = Field(
-        description="Format string for log messages",
+        description="log format",
         default="%(asctime)s.%(msecs)03d %(levelname)s [%(threadName)s] [%(filename)s:%(lineno)d] - %(message)s",
     )
 
     LOG_DATEFORMAT: Optional[str] = Field(
-        description="Date format string for log timestamps",
+        description="log date format",
         default=None,
     )
 
     LOG_TZ: Optional[str] = Field(
-        description="Timezone for log timestamps (e.g., 'America/New_York')",
+        description="specify log timezone, eg: America/New_York",
         default=None,
     )
 
 
 class ModelLoadBalanceConfig(BaseSettings):
     """
-    Configuration for model load balancing
+    Model load balance configs
     """
 
     MODEL_LB_ENABLED: bool = Field(
-        description="Enable or disable load balancing for models",
+        description="whether to enable model load balancing",
         default=False,
     )
 
 
 class BillingConfig(BaseSettings):
     """
-    Configuration for platform billing features
+    Platform Billing Configurations
     """
 
     BILLING_ENABLED: bool = Field(
-        description="Enable or disable billing functionality",
+        description="whether to enable billing",
         default=False,
     )
 
 
 class UpdateConfig(BaseSettings):
     """
-    Configuration for application update checks
+    Update configs
     """
 
     CHECK_UPDATE_URL: str = Field(
-        description="URL to check for application updates",
+        description="url for checking updates",
         default="https://updates.dify.ai",
     )
 
 
 class WorkflowConfig(BaseSettings):
     """
-    Configuration for workflow execution
+    Workflow feature configs
     """
 
     WORKFLOW_MAX_EXECUTION_STEPS: PositiveInt = Field(
-        description="Maximum number of steps allowed in a single workflow execution",
+        description="max execution steps in single workflow execution",
         default=500,
     )
 
     WORKFLOW_MAX_EXECUTION_TIME: PositiveInt = Field(
-        description="Maximum execution time in seconds for a single workflow",
+        description="max execution time in seconds in single workflow execution",
         default=1200,
     )
 
     WORKFLOW_CALL_MAX_DEPTH: PositiveInt = Field(
-        description="Maximum allowed depth for nested workflow calls",
+        description="max depth of calling in single workflow execution",
         default=5,
     )
 
     MAX_VARIABLE_SIZE: PositiveInt = Field(
-        description="Maximum size in bytes for a single variable in workflows. Default to 5KB.",
+        description="The maximum size in bytes of a variable. default to 5KB.",
         default=5 * 1024,
     )
 
 
 class OAuthConfig(BaseSettings):
     """
-    Configuration for OAuth authentication
+    oauth configs
     """
 
     OAUTH_REDIRECT_PATH: str = Field(
-        description="Redirect path for OAuth authentication callbacks",
+        description="redirect path for OAuth",
         default="/console/api/oauth/authorize",
     )
 
     GITHUB_CLIENT_ID: Optional[str] = Field(
-        description="GitHub OAuth client secret",
+        description="GitHub client id for OAuth",
         default=None,
     )
 
     GITHUB_CLIENT_SECRET: Optional[str] = Field(
-        description="GitHub OAuth client secret",
+        description="GitHub client secret key for OAuth",
         default=None,
     )
 
     GOOGLE_CLIENT_ID: Optional[str] = Field(
-        description="Google OAuth client ID",
+        description="Google client id for OAuth",
         default=None,
     )
 
     GOOGLE_CLIENT_SECRET: Optional[str] = Field(
-        description="Google OAuth client secret",
+        description="Google client secret key for OAuth",
         default=None,
     )
 
 
 class ModerationConfig(BaseSettings):
     """
-    Configuration for content moderation
+    Moderation in app configs.
     """
 
     MODERATION_BUFFER_SIZE: PositiveInt = Field(
-        description="Size of the buffer for content moderation processing",
+        description="buffer size for moderation",
         default=300,
     )
 
 
 class ToolConfig(BaseSettings):
     """
-    Configuration for tool management
+    Tool configs
     """
 
     TOOL_ICON_CACHE_MAX_AGE: PositiveInt = Field(
-        description="Maximum age in seconds for caching tool icons",
+        description="max age in seconds for tool icon caching",
         default=3600,
     )
 
 
 class MailConfig(BaseSettings):
     """
-    Configuration for email services
+    Mail Configurations
     """
 
     MAIL_TYPE: Optional[str] = Field(
-        description="Email service provider type ('smtp' or 'resend'), default to None.",
+        description="Mail provider type name, default to None, available values are `smtp` and `resend`.",
         default=None,
     )
 
     MAIL_DEFAULT_SEND_FROM: Optional[str] = Field(
-        description="Default email address to use as the sender",
+        description="default email address for sending from ",
         default=None,
     )
 
     RESEND_API_KEY: Optional[str] = Field(
-        description="API key for Resend email service",
+        description="API key for Resend",
         default=None,
     )
 
     RESEND_API_URL: Optional[str] = Field(
-        description="API URL for Resend email service",
+        description="API URL for Resend",
         default=None,
     )
 
     SMTP_SERVER: Optional[str] = Field(
-        description="SMTP server hostname",
+        description="smtp server host",
         default=None,
     )
 
     SMTP_PORT: Optional[int] = Field(
-        description="SMTP server port number",
+        description="smtp server port",
         default=465,
     )
 
     SMTP_USERNAME: Optional[str] = Field(
-        description="Username for SMTP authentication",
+        description="smtp server username",
         default=None,
     )
 
     SMTP_PASSWORD: Optional[str] = Field(
-        description="Password for SMTP authentication",
+        description="smtp server password",
         default=None,
     )
 
     SMTP_USE_TLS: bool = Field(
-        description="Enable TLS encryption for SMTP connections",
+        description="whether to use TLS connection to smtp server",
         default=False,
     )
 
     SMTP_OPPORTUNISTIC_TLS: bool = Field(
-        description="Enable opportunistic TLS for SMTP connections",
+        description="whether to use opportunistic TLS connection to smtp server",
         default=False,
     )
 
 
 class RagEtlConfig(BaseSettings):
     """
-    Configuration for RAG ETL processes
+    RAG ETL Configurations.
     """
 
     ETL_TYPE: str = Field(
-        description="RAG ETL type ('dify' or 'Unstructured'), default to 'dify'",
+        description="RAG ETL type name, default to `dify`, available values are `dify` and `Unstructured`. ",
         default="dify",
     )
 
     KEYWORD_DATA_SOURCE_TYPE: str = Field(
-        description="Data source type for keyword extraction"
-        " ('database' or other supported types), default to 'database'",
+        description="source type for keyword data, default to `database`, available values are `database` .",
         default="database",
     )
 
     UNSTRUCTURED_API_URL: Optional[str] = Field(
-        description="API URL for Unstructured.io service",
+        description="API URL for Unstructured",
         default=None,
     )
 
     UNSTRUCTURED_API_KEY: Optional[str] = Field(
-        description="API key for Unstructured.io service",
+        description="API key for Unstructured",
         default=None,
     )
 
 
 class DataSetConfig(BaseSettings):
     """
-    Configuration for dataset management
+    Dataset configs
     """
 
     CLEAN_DAY_SETTING: PositiveInt = Field(
-        description="Interval in days for dataset cleanup operations",
+        description="interval in days for cleaning up dataset",
         default=30,
     )
 
     DATASET_OPERATOR_ENABLED: bool = Field(
-        description="Enable or disable dataset operator functionality",
+        description="whether to enable dataset operator",
         default=False,
     )
 
 
 class WorkspaceConfig(BaseSettings):
     """
-    Configuration for workspace management
+    Workspace configs
     """
 
     INVITE_EXPIRY_HOURS: PositiveInt = Field(
-        description="Expiration time in hours for workspace invitation links",
+        description="workspaces invitation expiration in hours",
         default=72,
     )
 
 
 class IndexingConfig(BaseSettings):
     """
-    Configuration for indexing operations
+    Indexing configs.
     """
 
     INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH: PositiveInt = Field(
-        description="Maximum token length for text segmentation during indexing",
+        description="max segmentation token length for indexing",
         default=1000,
     )
 
 
 class ImageFormatConfig(BaseSettings):
     MULTIMODAL_SEND_IMAGE_FORMAT: str = Field(
-        description="Format for sending images in multimodal contexts ('base64' or 'url'), default is base64",
+        description="multi model send image format, support base64, url, default is base64",
         default="base64",
     )
 
 
 class CeleryBeatConfig(BaseSettings):
     CELERY_BEAT_SCHEDULER_TIME: int = Field(
-        description="Interval in days for Celery Beat scheduler execution, default to 1 day",
+        description="the time of the celery scheduler, default to 1 day",
         default=1,
     )
 
 
 class PositionConfig(BaseSettings):
     POSITION_PROVIDER_PINS: str = Field(
-        description="Comma-separated list of pinned model providers",
+        description="The heads of model providers",
         default="",
     )
 
     POSITION_PROVIDER_INCLUDES: str = Field(
-        description="Comma-separated list of included model providers",
+        description="The included model providers",
         default="",
     )
 
     POSITION_PROVIDER_EXCLUDES: str = Field(
-        description="Comma-separated list of excluded model providers",
+        description="The excluded model providers",
         default="",
     )
 
     POSITION_TOOL_PINS: str = Field(
-        description="Comma-separated list of pinned tools",
+        description="The heads of tools",
         default="",
     )
 
     POSITION_TOOL_INCLUDES: str = Field(
-        description="Comma-separated list of included tools",
+        description="The included tools",
         default="",
     )
 
     POSITION_TOOL_EXCLUDES: str = Field(
-        description="Comma-separated list of excluded tools",
+        description="The excluded tools",
         default="",
     )
 

api/configs/feature/hosted_service/__init__.py

@@ -6,31 +6,31 @@ from pydantic_settings import BaseSettings
 
 class HostedOpenAiConfig(BaseSettings):
     """
-    Configuration for hosted OpenAI service
+    Hosted OpenAI service config
     """
 
     HOSTED_OPENAI_API_KEY: Optional[str] = Field(
-        description="API key for hosted OpenAI service",
+        description="",
         default=None,
     )
 
     HOSTED_OPENAI_API_BASE: Optional[str] = Field(
-        description="Base URL for hosted OpenAI API",
+        description="",
         default=None,
     )
 
     HOSTED_OPENAI_API_ORGANIZATION: Optional[str] = Field(
-        description="Organization ID for hosted OpenAI service",
+        description="",
         default=None,
     )
 
     HOSTED_OPENAI_TRIAL_ENABLED: bool = Field(
-        description="Enable trial access to hosted OpenAI service",
+        description="",
         default=False,
     )
 
     HOSTED_OPENAI_TRIAL_MODELS: str = Field(
-        description="Comma-separated list of available models for trial access",
+        description="",
         default="gpt-3.5-turbo,"
         "gpt-3.5-turbo-1106,"
         "gpt-3.5-turbo-instruct,"
@@ -42,17 +42,17 @@ class HostedOpenAiConfig(BaseSettings):
     )
 
     HOSTED_OPENAI_QUOTA_LIMIT: NonNegativeInt = Field(
-        description="Quota limit for hosted OpenAI service usage",
+        description="",
         default=200,
     )
 
     HOSTED_OPENAI_PAID_ENABLED: bool = Field(
-        description="Enable paid access to hosted OpenAI service",
+        description="",
         default=False,
     )
 
     HOSTED_OPENAI_PAID_MODELS: str = Field(
-        description="Comma-separated list of available models for paid access",
+        description="",
         default="gpt-4,"
         "gpt-4-turbo-preview,"
         "gpt-4-turbo-2024-04-09,"
@@ -71,122 +71,124 @@ class HostedOpenAiConfig(BaseSettings):
 
 class HostedAzureOpenAiConfig(BaseSettings):
     """
-    Configuration for hosted Azure OpenAI service
+    Hosted OpenAI service config
     """
 
     HOSTED_AZURE_OPENAI_ENABLED: bool = Field(
-        description="Enable hosted Azure OpenAI service",
+        description="",
         default=False,
     )
 
     HOSTED_AZURE_OPENAI_API_KEY: Optional[str] = Field(
-        description="API key for hosted Azure OpenAI service",
+        description="",
         default=None,
     )
 
     HOSTED_AZURE_OPENAI_API_BASE: Optional[str] = Field(
-        description="Base URL for hosted Azure OpenAI API",
+        description="",
         default=None,
     )
 
     HOSTED_AZURE_OPENAI_QUOTA_LIMIT: NonNegativeInt = Field(
-        description="Quota limit for hosted Azure OpenAI service usage",
+        description="",
         default=200,
     )
 
 
 class HostedAnthropicConfig(BaseSettings):
     """
-    Configuration for hosted Anthropic service
+    Hosted Azure OpenAI service config
     """
 
     HOSTED_ANTHROPIC_API_BASE: Optional[str] = Field(
-        description="Base URL for hosted Anthropic API",
+        description="",
         default=None,
     )
 
     HOSTED_ANTHROPIC_API_KEY: Optional[str] = Field(
-        description="API key for hosted Anthropic service",
+        description="",
         default=None,
     )
 
     HOSTED_ANTHROPIC_TRIAL_ENABLED: bool = Field(
-        description="Enable trial access to hosted Anthropic service",
+        description="",
         default=False,
     )
 
     HOSTED_ANTHROPIC_QUOTA_LIMIT: NonNegativeInt = Field(
-        description="Quota limit for hosted Anthropic service usage",
+        description="",
         default=600000,
     )
 
     HOSTED_ANTHROPIC_PAID_ENABLED: bool = Field(
-        description="Enable paid access to hosted Anthropic service",
+        description="",
         default=False,
     )
 
 
 class HostedMinmaxConfig(BaseSettings):
     """
-    Configuration for hosted Minmax service
+    Hosted Minmax service config
     """
 
     HOSTED_MINIMAX_ENABLED: bool = Field(
-        description="Enable hosted Minmax service",
+        description="",
         default=False,
     )
 
 
 class HostedSparkConfig(BaseSettings):
     """
-    Configuration for hosted Spark service
+    Hosted Spark service config
     """
 
     HOSTED_SPARK_ENABLED: bool = Field(
-        description="Enable hosted Spark service",
+        description="",
         default=False,
     )
 
 
 class HostedZhipuAIConfig(BaseSettings):
     """
-    Configuration for hosted ZhipuAI service
+    Hosted Minmax service config
     """
 
     HOSTED_ZHIPUAI_ENABLED: bool = Field(
-        description="Enable hosted ZhipuAI service",
+        description="",
         default=False,
     )
 
 
 class HostedModerationConfig(BaseSettings):
     """
-    Configuration for hosted Moderation service
+    Hosted Moderation service config
     """
 
     HOSTED_MODERATION_ENABLED: bool = Field(
-        description="Enable hosted Moderation service",
+        description="",
         default=False,
     )
 
     HOSTED_MODERATION_PROVIDERS: str = Field(
-        description="Comma-separated list of moderation providers",
+        description="",
         default="",
     )
 
 
 class HostedFetchAppTemplateConfig(BaseSettings):
     """
-    Configuration for fetching app templates
+    Hosted Moderation service config
     """
 
     HOSTED_FETCH_APP_TEMPLATES_MODE: str = Field(
-        description="Mode for fetching app templates: remote, db, or builtin" " default to remote,",
+        description="the mode for fetching app templates,"
+        " default to remote,"
+        " available values: remote, db, builtin",
         default="remote",
     )
 
     HOSTED_FETCH_APP_TEMPLATES_REMOTE_DOMAIN: str = Field(
-        description="Domain for fetching remote app templates",
+        description="the domain for fetching remote app templates",
         default="https://tmpl.dify.ai",
     )
 

api/configs/middleware/__init__.py

@@ -5,7 +5,6 @@ from pydantic import Field, NonNegativeInt, PositiveFloat, PositiveInt, computed
 from pydantic_settings import BaseSettings
 
 from configs.middleware.cache.redis_config import RedisConfig
-from configs.middleware.external.bedrock_config import BedrockConfig
 from configs.middleware.storage.aliyun_oss_storage_config import AliyunOSSStorageConfig
 from configs.middleware.storage.amazon_s3_storage_config import S3StorageConfig
 from configs.middleware.storage.azure_blob_storage_config import AzureBlobStorageConfig
@@ -32,71 +31,70 @@ from configs.middleware.vdb.weaviate_config import WeaviateConfig
 
 class StorageConfig(BaseSettings):
     STORAGE_TYPE: str = Field(
-        description="Type of storage to use."
-        " Options: 'local', 's3', 'azure-blob', 'aliyun-oss', 'google-storage'. Default is 'local'.",
+        description="storage type,"
+        " default to `local`,"
+        " available values are `local`, `s3`, `azure-blob`, `aliyun-oss`, `google-storage`.",
         default="local",
     )
 
     STORAGE_LOCAL_PATH: str = Field(
-        description="Path for local storage when STORAGE_TYPE is set to 'local'.",
+        description="local storage path",
         default="storage",
     )
 
 
 class VectorStoreConfig(BaseSettings):
     VECTOR_STORE: Optional[str] = Field(
-        description="Type of vector store to use for efficient similarity search."
-        " Set to None if not using a vector store.",
+        description="vector store type",
         default=None,
     )
 
 
 class KeywordStoreConfig(BaseSettings):
     KEYWORD_STORE: str = Field(
-        description="Method for keyword extraction and storage."
-        " Default is 'jieba', a Chinese text segmentation library.",
+        description="keyword store type",
         default="jieba",
     )
 
 
 class DatabaseConfig:
     DB_HOST: str = Field(
-        description="Hostname or IP address of the database server.",
+        description="db host",
         default="localhost",
     )
 
     DB_PORT: PositiveInt = Field(
-        description="Port number for database connection.",
+        description="db port",
         default=5432,
     )
 
     DB_USERNAME: str = Field(
-        description="Username for database authentication.",
+        description="db username",
         default="postgres",
     )
 
     DB_PASSWORD: str = Field(
-        description="Password for database authentication.",
+        description="db password",
         default="",
     )
 
     DB_DATABASE: str = Field(
-        description="Name of the database to connect to.",
+        description="db database",
         default="dify",
     )
 
     DB_CHARSET: str = Field(
-        description="Character set for database connection.",
+        description="db charset",
         default="",
     )
 
     DB_EXTRAS: str = Field(
-        description="Additional database connection parameters. Example: 'keepalives_idle=60&keepalives=1'",
+        description="db extras options. Example: keepalives_idle=60&keepalives=1",
         default="",
     )
 
     SQLALCHEMY_DATABASE_URI_SCHEME: str = Field(
-        description="Database URI scheme for SQLAlchemy connection.",
+        description="db uri scheme",
         default="postgresql",
     )
 
@@ -114,27 +112,27 @@ class DatabaseConfig:
         )
 
     SQLALCHEMY_POOL_SIZE: NonNegativeInt = Field(
-        description="Maximum number of database connections in the pool.",
+        description="pool size of SqlAlchemy",
         default=30,
     )
 
     SQLALCHEMY_MAX_OVERFLOW: NonNegativeInt = Field(
-        description="Maximum number of connections that can be created beyond the pool_size.",
+        description="max overflows for SqlAlchemy",
         default=10,
     )
 
     SQLALCHEMY_POOL_RECYCLE: NonNegativeInt = Field(
-        description="Number of seconds after which a connection is automatically recycled.",
+        description="SqlAlchemy pool recycle",
         default=3600,
     )
 
     SQLALCHEMY_POOL_PRE_PING: bool = Field(
-        description="If True, enables connection pool pre-ping feature to check connections.",
+        description="whether to enable pool pre-ping in SqlAlchemy",
         default=False,
     )
 
     SQLALCHEMY_ECHO: bool | str = Field(
-        description="If True, SQLAlchemy will log all SQL statements.",
+        description="whether to enable SqlAlchemy echo",
         default=False,
     )
 
@@ -152,27 +150,27 @@ class DatabaseConfig:
 
 class CeleryConfig(DatabaseConfig):
     CELERY_BACKEND: str = Field(
-        description="Backend for Celery task results. Options: 'database', 'redis'.",
+        description="Celery backend, available values are `database`, `redis`",
         default="database",
     )
 
     CELERY_BROKER_URL: Optional[str] = Field(
-        description="URL of the message broker for Celery tasks.",
+        description="CELERY_BROKER_URL",
         default=None,
     )
 
     CELERY_USE_SENTINEL: Optional[bool] = Field(
-        description="Whether to use Redis Sentinel for high availability.",
+        description="Whether to use Redis Sentinel mode",
         default=False,
     )
 
     CELERY_SENTINEL_MASTER_NAME: Optional[str] = Field(
-        description="Name of the Redis Sentinel master.",
+        description="Redis Sentinel master name",
         default=None,
     )
 
     CELERY_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
-        description="Timeout for Redis Sentinel socket operations in seconds.",
+        description="Redis Sentinel socket timeout",
         default=0.1,
     )
 
@@ -223,6 +221,5 @@ class MiddlewareConfig(
     TiDBVectorConfig,
     WeaviateConfig,
     ElasticsearchConfig,
-    BedrockConfig,
 ):
     pass

api/configs/middleware/cache/redis_config.py

@@ -6,65 +6,65 @@ from pydantic_settings import BaseSettings
 
 class RedisConfig(BaseSettings):
     """
-    Configuration settings for Redis connection
+    Redis configs
     """
 
     REDIS_HOST: str = Field(
-        description="Hostname or IP address of the Redis server",
+        description="Redis host",
         default="localhost",
     )
 
     REDIS_PORT: PositiveInt = Field(
-        description="Port number on which the Redis server is listening",
+        description="Redis port",
         default=6379,
     )
 
     REDIS_USERNAME: Optional[str] = Field(
-        description="Username for Redis authentication (if required)",
+        description="Redis username",
         default=None,
     )
 
     REDIS_PASSWORD: Optional[str] = Field(
-        description="Password for Redis authentication (if required)",
+        description="Redis password",
         default=None,
     )
 
     REDIS_DB: NonNegativeInt = Field(
-        description="Redis database number to use (0-15)",
+        description="Redis database id, default to 0",
         default=0,
     )
 
     REDIS_USE_SSL: bool = Field(
-        description="Enable SSL/TLS for the Redis connection",
+        description="whether to use SSL for Redis connection",
         default=False,
     )
 
     REDIS_USE_SENTINEL: Optional[bool] = Field(
-        description="Enable Redis Sentinel mode for high availability",
+        description="Whether to use Redis Sentinel mode",
         default=False,
     )
 
     REDIS_SENTINELS: Optional[str] = Field(
-        description="Comma-separated list of Redis Sentinel nodes (host:port)",
+        description="Redis Sentinel nodes",
         default=None,
     )
 
     REDIS_SENTINEL_SERVICE_NAME: Optional[str] = Field(
-        description="Name of the Redis Sentinel service to monitor",
+        description="Redis Sentinel service name",
         default=None,
     )
 
     REDIS_SENTINEL_USERNAME: Optional[str] = Field(
-        description="Username for Redis Sentinel authentication (if required)",
+        description="Redis Sentinel username",
         default=None,
     )
 
     REDIS_SENTINEL_PASSWORD: Optional[str] = Field(
-        description="Password for Redis Sentinel authentication (if required)",
+        description="Redis Sentinel password",
         default=None,
     )
 
     REDIS_SENTINEL_SOCKET_TIMEOUT: Optional[PositiveFloat] = Field(
-        description="Socket timeout in seconds for Redis Sentinel connections",
+        description="Redis Sentinel socket timeout",
         default=0.1,
     )

api/configs/middleware/external/bedrock_config.py

@@ -1,20 +0,0 @@
-from typing import Optional
-
-from pydantic import Field
-from pydantic_settings import BaseSettings
-
-
-class BedrockConfig(BaseSettings):
-    """
-    bedrock configs
-    """
-
-    AWS_SECRET_ACCESS_KEY: Optional[str] = Field(
-        description="AWS secret access key",
-        default=None,
-    )
-
-    AWS_ACCESS_KEY_ID: Optional[str] = Field(
-        description="AWS secret access id",
-        default=None,
-    )

api/configs/middleware/storage/aliyun_oss_storage_config.py

@@ -6,40 +6,40 @@ from pydantic_settings import BaseSettings
 
 class AliyunOSSStorageConfig(BaseSettings):
     """
-    Configuration settings for Aliyun Object Storage Service (OSS)
+    Aliyun storage configs
     """
 
     ALIYUN_OSS_BUCKET_NAME: Optional[str] = Field(
-        description="Name of the Aliyun OSS bucket to store and retrieve objects",
+        description="Aliyun OSS bucket name",
         default=None,
     )
 
     ALIYUN_OSS_ACCESS_KEY: Optional[str] = Field(
-        description="Access key ID for authenticating with Aliyun OSS",
+        description="Aliyun OSS access key",
         default=None,
     )
 
     ALIYUN_OSS_SECRET_KEY: Optional[str] = Field(
-        description="Secret access key for authenticating with Aliyun OSS",
+        description="Aliyun OSS secret key",
         default=None,
     )
 
     ALIYUN_OSS_ENDPOINT: Optional[str] = Field(
-        description="URL of the Aliyun OSS endpoint for your chosen region",
+        description="Aliyun OSS endpoint URL",
         default=None,
     )
 
     ALIYUN_OSS_REGION: Optional[str] = Field(
-        description="Aliyun OSS region where your bucket is located (e.g., 'oss-cn-hangzhou')",
+        description="Aliyun OSS region",
         default=None,
     )
 
     ALIYUN_OSS_AUTH_VERSION: Optional[str] = Field(
-        description="Version of the authentication protocol to use with Aliyun OSS (e.g., 'v4')",
+        description="Aliyun OSS authentication version",
         default=None,
     )
 
     ALIYUN_OSS_PATH: Optional[str] = Field(
-        description="Base path within the bucket to store objects (e.g., 'my-app-data/')",
+        description="Aliyun OSS path",
         default=None,
     )

api/configs/middleware/storage/amazon_s3_storage_config.py

@@ -6,40 +6,40 @@ from pydantic_settings import BaseSettings
 
 class S3StorageConfig(BaseSettings):
     """
-    Configuration settings for S3-compatible object storage
+    S3 storage configs
     """
 
     S3_ENDPOINT: Optional[str] = Field(
-        description="URL of the S3-compatible storage endpoint (e.g., 'https://s3.amazonaws.com')",
+        description="S3 storage endpoint",
         default=None,
     )
 
     S3_REGION: Optional[str] = Field(
-        description="Region where the S3 bucket is located (e.g., 'us-east-1')",
+        description="S3 storage region",
         default=None,
     )
 
     S3_BUCKET_NAME: Optional[str] = Field(
-        description="Name of the S3 bucket to store and retrieve objects",
+        description="S3 storage bucket name",
         default=None,
     )
 
     S3_ACCESS_KEY: Optional[str] = Field(
-        description="Access key ID for authenticating with the S3 service",
+        description="S3 storage access key",
         default=None,
     )
 
     S3_SECRET_KEY: Optional[str] = Field(
-        description="Secret access key for authenticating with the S3 service",
+        description="S3 storage secret key",
         default=None,
     )
 
     S3_ADDRESS_STYLE: str = Field(
-        description="S3 addressing style: 'auto', 'path', or 'virtual'",
+        description="S3 storage address style",
         default="auto",
     )
 
     S3_USE_AWS_MANAGED_IAM: bool = Field(
-        description="Use AWS managed IAM roles for authentication instead of access/secret keys",
+        description="whether to use aws managed IAM for S3",
         default=False,
     )

api/configs/middleware/storage/azure_blob_storage_config.py

@@ -6,25 +6,25 @@ from pydantic_settings import BaseSettings
 
 class AzureBlobStorageConfig(BaseSettings):
     """
-    Configuration settings for Azure Blob Storage
+    Azure Blob storage configs
     """
 
     AZURE_BLOB_ACCOUNT_NAME: Optional[str] = Field(
-        description="Name of the Azure Storage account (e.g., 'mystorageaccount')",
+        description="Azure Blob account name",
         default=None,
     )
 
     AZURE_BLOB_ACCOUNT_KEY: Optional[str] = Field(
-        description="Access key for authenticating with the Azure Storage account",
+        description="Azure Blob account key",
         default=None,
     )
 
     AZURE_BLOB_CONTAINER_NAME: Optional[str] = Field(
-        description="Name of the Azure Blob container to store and retrieve objects",
+        description="Azure Blob container name",
         default=None,
     )
 
     AZURE_BLOB_ACCOUNT_URL: Optional[str] = Field(
-        description="URL of the Azure Blob storage endpoint (e.g., 'https://mystorageaccount.blob.core.windows.net')",
+        description="Azure Blob account URL",
         default=None,
     )

api/configs/middleware/storage/google_cloud_storage_config.py

@@ -6,15 +6,15 @@ from pydantic_settings import BaseSettings
 
 class GoogleCloudStorageConfig(BaseSettings):
     """
-    Configuration settings for Google Cloud Storage
+    Google Cloud storage configs
     """
 
     GOOGLE_STORAGE_BUCKET_NAME: Optional[str] = Field(
-        description="Name of the Google Cloud Storage bucket to store and retrieve objects (e.g., 'my-gcs-bucket')",
+        description="Google Cloud storage bucket name",
         default=None,
     )
 
     GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64: Optional[str] = Field(
-        description="Base64-encoded JSON key file for Google Cloud service account authentication",
+        description="Google Cloud storage service account json base64",
         default=None,
     )

api/configs/middleware/storage/huawei_obs_storage_config.py

@@ -5,25 +5,25 @@ from pydantic import BaseModel, Field
 
 class HuaweiCloudOBSStorageConfig(BaseModel):
     """
-    Configuration settings for Huawei Cloud Object Storage Service (OBS)
+    Huawei Cloud OBS storage configs
     """
 
     HUAWEI_OBS_BUCKET_NAME: Optional[str] = Field(
-        description="Name of the Huawei Cloud OBS bucket to store and retrieve objects (e.g., 'my-obs-bucket')",
+        description="Huawei Cloud OBS bucket name",
         default=None,
     )
 
     HUAWEI_OBS_ACCESS_KEY: Optional[str] = Field(
-        description="Access Key ID for authenticating with Huawei Cloud OBS",
+        description="Huawei Cloud OBS Access key",
         default=None,
     )
 
     HUAWEI_OBS_SECRET_KEY: Optional[str] = Field(
-        description="Secret Access Key for authenticating with Huawei Cloud OBS",
+        description="Huawei Cloud OBS Secret key",
         default=None,
     )
 
     HUAWEI_OBS_SERVER: Optional[str] = Field(
-        description="Endpoint URL for Huawei Cloud OBS (e.g., 'https://obs.cn-north-4.myhuaweicloud.com')",
+        description="Huawei Cloud OBS server URL",
         default=None,
     )

api/configs/middleware/storage/oci_storage_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class OCIStorageConfig(BaseSettings):
     """
-    Configuration settings for Oracle Cloud Infrastructure (OCI) Object Storage
+    OCI storage configs
     """
 
     OCI_ENDPOINT: Optional[str] = Field(
-        description="URL of the OCI Object Storage endpoint (e.g., 'https://objectstorage.us-phoenix-1.oraclecloud.com')",
+        description="OCI storage endpoint",
         default=None,
     )
 
     OCI_REGION: Optional[str] = Field(
-        description="OCI region where the bucket is located (e.g., 'us-phoenix-1')",
+        description="OCI storage region",
         default=None,
     )
 
     OCI_BUCKET_NAME: Optional[str] = Field(
-        description="Name of the OCI Object Storage bucket to store and retrieve objects (e.g., 'my-oci-bucket')",
+        description="OCI storage bucket name",
         default=None,
     )
 
     OCI_ACCESS_KEY: Optional[str] = Field(
-        description="Access key (also known as API key) for authenticating with OCI Object Storage",
+        description="OCI storage access key",
         default=None,
     )
 
     OCI_SECRET_KEY: Optional[str] = Field(
-        description="Secret key associated with the access key for authenticating with OCI Object Storage",
+        description="OCI storage secret key",
         default=None,
     )

api/configs/middleware/storage/tencent_cos_storage_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class TencentCloudCOSStorageConfig(BaseSettings):
     """
-    Configuration settings for Tencent Cloud Object Storage (COS)
+    Tencent Cloud COS storage configs
     """
 
     TENCENT_COS_BUCKET_NAME: Optional[str] = Field(
-        description="Name of the Tencent Cloud COS bucket to store and retrieve objects",
+        description="Tencent Cloud COS bucket name",
         default=None,
     )
 
     TENCENT_COS_REGION: Optional[str] = Field(
-        description="Tencent Cloud region where the COS bucket is located (e.g., 'ap-guangzhou')",
+        description="Tencent Cloud COS region",
         default=None,
     )
 
     TENCENT_COS_SECRET_ID: Optional[str] = Field(
-        description="SecretId for authenticating with Tencent Cloud COS (part of API credentials)",
+        description="Tencent Cloud COS secret id",
         default=None,
     )
 
     TENCENT_COS_SECRET_KEY: Optional[str] = Field(
-        description="SecretKey for authenticating with Tencent Cloud COS (part of API credentials)",
+        description="Tencent Cloud COS secret key",
         default=None,
     )
 
     TENCENT_COS_SCHEME: Optional[str] = Field(
-        description="Protocol scheme for COS requests: 'https' (recommended) or 'http'",
+        description="Tencent Cloud COS scheme",
         default=None,
     )

api/configs/middleware/storage/volcengine_tos_storage_config.py

@@ -5,30 +5,30 @@ from pydantic import BaseModel, Field
 
 class VolcengineTOSStorageConfig(BaseModel):
     """
-    Configuration settings for Volcengine Tinder Object Storage (TOS)
+    Volcengine tos storage configs
     """
 
     VOLCENGINE_TOS_BUCKET_NAME: Optional[str] = Field(
-        description="Name of the Volcengine TOS bucket to store and retrieve objects (e.g., 'my-tos-bucket')",
+        description="Volcengine TOS Bucket Name",
         default=None,
     )
 
     VOLCENGINE_TOS_ACCESS_KEY: Optional[str] = Field(
-        description="Access Key ID for authenticating with Volcengine TOS",
+        description="Volcengine TOS Access Key",
         default=None,
     )
 
     VOLCENGINE_TOS_SECRET_KEY: Optional[str] = Field(
-        description="Secret Access Key for authenticating with Volcengine TOS",
+        description="Volcengine TOS Secret Key",
         default=None,
     )
 
     VOLCENGINE_TOS_ENDPOINT: Optional[str] = Field(
-        description="URL of the Volcengine TOS endpoint (e.g., 'https://tos-cn-beijing.volces.com')",
+        description="Volcengine TOS Endpoint URL",
         default=None,
     )
 
     VOLCENGINE_TOS_REGION: Optional[str] = Field(
-        description="Volcengine region where the TOS bucket is located (e.g., 'cn-beijing')",
+        description="Volcengine TOS Region",
         default=None,
     )

api/configs/middleware/vdb/analyticdb_config.py

@@ -5,38 +5,33 @@ from pydantic import BaseModel, Field
 
 class AnalyticdbConfig(BaseModel):
     """
-    Configuration for connecting to Alibaba Cloud AnalyticDB for PostgreSQL.
+    Configuration for connecting to AnalyticDB.
     Refer to the following documentation for details on obtaining credentials:
     https://www.alibabacloud.com/help/en/analyticdb-for-postgresql/getting-started/create-an-instance-instances-with-vector-engine-optimization-enabled
     """
 
     ANALYTICDB_KEY_ID: Optional[str] = Field(
-        default=None, description="The Access Key ID provided by Alibaba Cloud for API authentication."
+        default=None, description="The Access Key ID provided by Alibaba Cloud for authentication."
     )
     ANALYTICDB_KEY_SECRET: Optional[str] = Field(
-        default=None, description="The Secret Access Key corresponding to the Access Key ID for secure API access."
+        default=None, description="The Secret Access Key corresponding to the Access Key ID for secure access."
     )
     ANALYTICDB_REGION_ID: Optional[str] = Field(
-        default=None,
-        description="The region where the AnalyticDB instance is deployed (e.g., 'cn-hangzhou', 'ap-southeast-1').",
+        default=None, description="The region where the AnalyticDB instance is deployed (e.g., 'cn-hangzhou')."
     )
     ANALYTICDB_INSTANCE_ID: Optional[str] = Field(
         default=None,
-        description="The unique identifier of the AnalyticDB instance you want to connect to.",
+        description="The unique identifier of the AnalyticDB instance you want to connect to (e.g., 'gp-ab123456')..",
     )
     ANALYTICDB_ACCOUNT: Optional[str] = Field(
-        default=None,
-        description="The account name used to log in to the AnalyticDB instance"
-        " (usually the initial account created with the instance).",
+        default=None, description="The account name used to log in to the AnalyticDB instance."
     )
     ANALYTICDB_PASSWORD: Optional[str] = Field(
-        default=None, description="The password associated with the AnalyticDB account for database authentication."
+        default=None, description="The password associated with the AnalyticDB account for authentication."
     )
     ANALYTICDB_NAMESPACE: Optional[str] = Field(
-        default=None, description="The namespace within AnalyticDB for schema isolation (if using namespace feature)."
+        default=None, description="The namespace within AnalyticDB for schema isolation."
     )
     ANALYTICDB_NAMESPACE_PASSWORD: Optional[str] = Field(
-        default=None,
-        description="The password for accessing the specified namespace within the AnalyticDB instance"
-        " (if namespace feature is enabled).",
+        default=None, description="The password for accessing the specified namespace within the AnalyticDB instance."
     )

api/configs/middleware/vdb/chroma_config.py

@@ -6,35 +6,35 @@ from pydantic_settings import BaseSettings
 
 class ChromaConfig(BaseSettings):
     """
-    Configuration settings for Chroma vector database
+    Chroma configs
     """
 
     CHROMA_HOST: Optional[str] = Field(
-        description="Hostname or IP address of the Chroma server (e.g., 'localhost' or '192.168.1.100')",
+        description="Chroma host",
         default=None,
     )
 
     CHROMA_PORT: PositiveInt = Field(
-        description="Port number on which the Chroma server is listening (default is 8000)",
+        description="Chroma port",
         default=8000,
     )
 
     CHROMA_TENANT: Optional[str] = Field(
-        description="Tenant identifier for multi-tenancy support in Chroma",
+        description="Chroma database",
         default=None,
     )
 
     CHROMA_DATABASE: Optional[str] = Field(
-        description="Name of the Chroma database to connect to",
+        description="Chroma database",
         default=None,
     )
 
     CHROMA_AUTH_PROVIDER: Optional[str] = Field(
-        description="Authentication provider for Chroma (e.g., 'basic', 'token', or a custom provider)",
+        description="Chroma authentication provider",
         default=None,
     )
 
     CHROMA_AUTH_CREDENTIALS: Optional[str] = Field(
-        description="Authentication credentials for Chroma (format depends on the auth provider)",
+        description="Chroma authentication credentials",
         default=None,
     )

api/configs/middleware/vdb/elasticsearch_config.py

@@ -6,25 +6,25 @@ from pydantic_settings import BaseSettings
 
 class ElasticsearchConfig(BaseSettings):
     """
-    Configuration settings for Elasticsearch
+    Elasticsearch configs
     """
 
     ELASTICSEARCH_HOST: Optional[str] = Field(
-        description="Hostname or IP address of the Elasticsearch server (e.g., 'localhost' or '192.168.1.100')",
+        description="Elasticsearch host",
         default="127.0.0.1",
     )
 
     ELASTICSEARCH_PORT: PositiveInt = Field(
-        description="Port number on which the Elasticsearch server is listening (default is 9200)",
+        description="Elasticsearch port",
         default=9200,
     )
 
     ELASTICSEARCH_USERNAME: Optional[str] = Field(
-        description="Username for authenticating with Elasticsearch (default is 'elastic')",
+        description="Elasticsearch username",
         default="elastic",
     )
 
     ELASTICSEARCH_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with Elasticsearch (default is 'elastic')",
+        description="Elasticsearch password",
         default="elastic",
     )

api/configs/middleware/vdb/milvus_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class MilvusConfig(BaseSettings):
     """
-    Configuration settings for Milvus vector database
+    Milvus configs
     """
 
     MILVUS_URI: Optional[str] = Field(
-        description="URI for connecting to the Milvus server (e.g., 'http://localhost:19530' or 'https://milvus-instance.example.com:19530')",
+        description="Milvus uri",
         default="http://127.0.0.1:19530",
     )
 
     MILVUS_TOKEN: Optional[str] = Field(
-        description="Authentication token for Milvus, if token-based authentication is enabled",
+        description="Milvus token",
         default=None,
     )
 
     MILVUS_USER: Optional[str] = Field(
-        description="Username for authenticating with Milvus, if username/password authentication is enabled",
+        description="Milvus user",
         default=None,
     )
 
     MILVUS_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with Milvus, if username/password authentication is enabled",
+        description="Milvus password",
         default=None,
     )
 
     MILVUS_DATABASE: str = Field(
-        description="Name of the Milvus database to connect to (default is 'default')",
+        description="Milvus database, default to `default`",
         default="default",
     )

api/configs/middleware/vdb/myscale_config.py

@@ -3,35 +3,35 @@ from pydantic import BaseModel, Field, PositiveInt
 
 class MyScaleConfig(BaseModel):
     """
-    Configuration settings for MyScale vector database
+    MyScale configs
     """
 
     MYSCALE_HOST: str = Field(
-        description="Hostname or IP address of the MyScale server (e.g., 'localhost' or 'myscale.example.com')",
+        description="MyScale host",
         default="localhost",
     )
 
     MYSCALE_PORT: PositiveInt = Field(
-        description="Port number on which the MyScale server is listening (default is 8123)",
+        description="MyScale port",
         default=8123,
     )
 
     MYSCALE_USER: str = Field(
-        description="Username for authenticating with MyScale (default is 'default')",
+        description="MyScale user",
         default="default",
     )
 
     MYSCALE_PASSWORD: str = Field(
-        description="Password for authenticating with MyScale (default is an empty string)",
+        description="MyScale password",
         default="",
     )
 
     MYSCALE_DATABASE: str = Field(
-        description="Name of the MyScale database to connect to (default is 'default')",
+        description="MyScale database name",
         default="default",
     )
 
     MYSCALE_FTS_PARAMS: str = Field(
-        description="Additional parameters for MyScale Full Text Search index)",
+        description="MyScale fts index parameters",
         default="",
     )

api/configs/middleware/vdb/opensearch_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class OpenSearchConfig(BaseSettings):
     """
-    Configuration settings for OpenSearch
+    OpenSearch configs
     """
 
     OPENSEARCH_HOST: Optional[str] = Field(
-        description="Hostname or IP address of the OpenSearch server (e.g., 'localhost' or 'opensearch.example.com')",
+        description="OpenSearch host",
         default=None,
     )
 
     OPENSEARCH_PORT: PositiveInt = Field(
-        description="Port number on which the OpenSearch server is listening (default is 9200)",
+        description="OpenSearch port",
         default=9200,
     )
 
     OPENSEARCH_USER: Optional[str] = Field(
-        description="Username for authenticating with OpenSearch",
+        description="OpenSearch user",
         default=None,
     )
 
     OPENSEARCH_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with OpenSearch",
+        description="OpenSearch password",
         default=None,
     )
 
     OPENSEARCH_SECURE: bool = Field(
-        description="Whether to use SSL/TLS encrypted connection for OpenSearch (True for HTTPS, False for HTTP)",
+        description="whether to use SSL connection for OpenSearch",
         default=False,
     )

api/configs/middleware/vdb/oracle_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class OracleConfig(BaseSettings):
     """
-    Configuration settings for Oracle database
+    ORACLE configs
     """
 
     ORACLE_HOST: Optional[str] = Field(
-        description="Hostname or IP address of the Oracle database server (e.g., 'localhost' or 'oracle.example.com')",
+        description="ORACLE host",
         default=None,
     )
 
     ORACLE_PORT: Optional[PositiveInt] = Field(
-        description="Port number on which the Oracle database server is listening (default is 1521)",
+        description="ORACLE port",
         default=1521,
     )
 
     ORACLE_USER: Optional[str] = Field(
-        description="Username for authenticating with the Oracle database",
+        description="ORACLE user",
         default=None,
     )
 
     ORACLE_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with the Oracle database",
+        description="ORACLE password",
         default=None,
     )
 
     ORACLE_DATABASE: Optional[str] = Field(
-        description="Name of the Oracle database or service to connect to (e.g., 'ORCL' or 'pdborcl')",
+        description="ORACLE database",
         default=None,
     )

api/configs/middleware/vdb/pgvector_config.py

@@ -6,40 +6,30 @@ from pydantic_settings import BaseSettings
 
 class PGVectorConfig(BaseSettings):
     """
-    Configuration settings for PGVector (PostgreSQL with vector extension)
+    PGVector configs
     """
 
     PGVECTOR_HOST: Optional[str] = Field(
-        description="Hostname or IP address of the PostgreSQL server with PGVector extension (e.g., 'localhost')",
+        description="PGVector host",
         default=None,
     )
 
     PGVECTOR_PORT: Optional[PositiveInt] = Field(
-        description="Port number on which the PostgreSQL server is listening (default is 5433)",
+        description="PGVector port",
         default=5433,
     )
 
     PGVECTOR_USER: Optional[str] = Field(
-        description="Username for authenticating with the PostgreSQL database",
+        description="PGVector user",
         default=None,
     )
 
     PGVECTOR_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with the PostgreSQL database",
+        description="PGVector password",
         default=None,
     )
 
     PGVECTOR_DATABASE: Optional[str] = Field(
-        description="Name of the PostgreSQL database to connect to",
+        description="PGVector database",
         default=None,
     )
-
-    PGVECTOR_MIN_CONNECTION: PositiveInt = Field(
-        description="Min connection of the PostgreSQL database",
-        default=1,
-    )
-
-    PGVECTOR_MAX_CONNECTION: PositiveInt = Field(
-        description="Max connection of the PostgreSQL database",
-        default=5,
-    )

api/configs/middleware/vdb/pgvectors_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class PGVectoRSConfig(BaseSettings):
     """
-    Configuration settings for PGVecto.RS (Rust-based vector extension for PostgreSQL)
+    PGVectoRS configs
     """
 
     PGVECTO_RS_HOST: Optional[str] = Field(
-        description="Hostname or IP address of the PostgreSQL server with PGVecto.RS extension (e.g., 'localhost')",
+        description="PGVectoRS host",
         default=None,
     )
 
     PGVECTO_RS_PORT: Optional[PositiveInt] = Field(
-        description="Port number on which the PostgreSQL server with PGVecto.RS is listening (default is 5431)",
+        description="PGVectoRS port",
         default=5431,
     )
 
     PGVECTO_RS_USER: Optional[str] = Field(
-        description="Username for authenticating with the PostgreSQL database using PGVecto.RS",
+        description="PGVectoRS user",
         default=None,
     )
 
     PGVECTO_RS_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with the PostgreSQL database using PGVecto.RS",
+        description="PGVectoRS password",
         default=None,
     )
 
     PGVECTO_RS_DATABASE: Optional[str] = Field(
-        description="Name of the PostgreSQL database with PGVecto.RS extension to connect to",
+        description="PGVectoRS database",
         default=None,
     )

api/configs/middleware/vdb/qdrant_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class QdrantConfig(BaseSettings):
     """
-    Configuration settings for Qdrant vector database
+    Qdrant configs
     """
 
     QDRANT_URL: Optional[str] = Field(
-        description="URL of the Qdrant server (e.g., 'http://localhost:6333' or 'https://qdrant.example.com')",
+        description="Qdrant url",
         default=None,
     )
 
     QDRANT_API_KEY: Optional[str] = Field(
-        description="API key for authenticating with the Qdrant server",
+        description="Qdrant api key",
         default=None,
     )
 
     QDRANT_CLIENT_TIMEOUT: NonNegativeInt = Field(
-        description="Timeout in seconds for Qdrant client operations (default is 20 seconds)",
+        description="Qdrant client timeout in seconds",
         default=20,
     )
 
     QDRANT_GRPC_ENABLED: bool = Field(
-        description="Whether to enable gRPC support for Qdrant connection (True for gRPC, False for HTTP)",
+        description="whether enable grpc support for Qdrant connection",
         default=False,
     )
 
     QDRANT_GRPC_PORT: PositiveInt = Field(
-        description="Port number for gRPC connection to Qdrant server (default is 6334)",
+        description="Qdrant grpc port",
         default=6334,
     )

api/configs/middleware/vdb/relyt_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class RelytConfig(BaseSettings):
     """
-    Configuration settings for Relyt database
+    Relyt configs
     """
 
     RELYT_HOST: Optional[str] = Field(
-        description="Hostname or IP address of the Relyt server (e.g., 'localhost' or 'relyt.example.com')",
+        description="Relyt host",
         default=None,
     )
 
     RELYT_PORT: PositiveInt = Field(
-        description="Port number on which the Relyt server is listening (default is 9200)",
+        description="Relyt port",
         default=9200,
     )
 
     RELYT_USER: Optional[str] = Field(
-        description="Username for authenticating with the Relyt database",
+        description="Relyt user",
         default=None,
     )
 
     RELYT_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with the Relyt database",
+        description="Relyt password",
         default=None,
     )
 
     RELYT_DATABASE: Optional[str] = Field(
-        description="Name of the Relyt database to connect to (default is 'default')",
+        description="Relyt database",
         default="default",
     )

api/configs/middleware/vdb/tencent_vector_config.py

@@ -6,45 +6,45 @@ from pydantic_settings import BaseSettings
 
 class TencentVectorDBConfig(BaseSettings):
     """
-    Configuration settings for Tencent Vector Database
+    Tencent Vector configs
     """
 
     TENCENT_VECTOR_DB_URL: Optional[str] = Field(
-        description="URL of the Tencent Vector Database service (e.g., 'https://vectordb.tencentcloudapi.com')",
+        description="Tencent Vector URL",
         default=None,
     )
 
     TENCENT_VECTOR_DB_API_KEY: Optional[str] = Field(
-        description="API key for authenticating with the Tencent Vector Database service",
+        description="Tencent Vector API key",
         default=None,
     )
 
     TENCENT_VECTOR_DB_TIMEOUT: PositiveInt = Field(
-        description="Timeout in seconds for Tencent Vector Database operations (default is 30 seconds)",
+        description="Tencent Vector timeout in seconds",
         default=30,
     )
 
     TENCENT_VECTOR_DB_USERNAME: Optional[str] = Field(
-        description="Username for authenticating with the Tencent Vector Database (if required)",
+        description="Tencent Vector username",
         default=None,
     )
 
     TENCENT_VECTOR_DB_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with the Tencent Vector Database (if required)",
+        description="Tencent Vector password",
         default=None,
     )
 
     TENCENT_VECTOR_DB_SHARD: PositiveInt = Field(
-        description="Number of shards for the Tencent Vector Database (default is 1)",
+        description="Tencent Vector sharding number",
         default=1,
     )
 
     TENCENT_VECTOR_DB_REPLICAS: NonNegativeInt = Field(
-        description="Number of replicas for the Tencent Vector Database (default is 2)",
+        description="Tencent Vector replicas",
         default=2,
     )
 
     TENCENT_VECTOR_DB_DATABASE: Optional[str] = Field(
-        description="Name of the specific Tencent Vector Database to connect to",
+        description="Tencent Vector Database",
         default=None,
     )

api/configs/middleware/vdb/tidb_vector_config.py

@@ -6,30 +6,30 @@ from pydantic_settings import BaseSettings
 
 class TiDBVectorConfig(BaseSettings):
     """
-    Configuration settings for TiDB Vector database
+    TiDB Vector configs
     """
 
     TIDB_VECTOR_HOST: Optional[str] = Field(
-        description="Hostname or IP address of the TiDB Vector server (e.g., 'localhost' or 'tidb.example.com')",
+        description="TiDB Vector host",
         default=None,
     )
 
     TIDB_VECTOR_PORT: Optional[PositiveInt] = Field(
-        description="Port number on which the TiDB Vector server is listening (default is 4000)",
+        description="TiDB Vector port",
         default=4000,
     )
 
     TIDB_VECTOR_USER: Optional[str] = Field(
-        description="Username for authenticating with the TiDB Vector database",
+        description="TiDB Vector user",
         default=None,
     )
 
     TIDB_VECTOR_PASSWORD: Optional[str] = Field(
-        description="Password for authenticating with the TiDB Vector database",
+        description="TiDB Vector password",
         default=None,
     )
 
     TIDB_VECTOR_DATABASE: Optional[str] = Field(
-        description="Name of the TiDB Vector database to connect to",
+        description="TiDB Vector database",
         default=None,
     )

api/configs/middleware/vdb/weaviate_config.py

@@ -6,25 +6,25 @@ from pydantic_settings import BaseSettings
 
 class WeaviateConfig(BaseSettings):
     """
-    Configuration settings for Weaviate vector database
+    Weaviate configs
     """
 
     WEAVIATE_ENDPOINT: Optional[str] = Field(
-        description="URL of the Weaviate server (e.g., 'http://localhost:8080' or 'https://weaviate.example.com')",
+        description="Weaviate endpoint URL",
         default=None,
     )
 
     WEAVIATE_API_KEY: Optional[str] = Field(
-        description="API key for authenticating with the Weaviate server",
+        description="Weaviate API key",
         default=None,
     )
 
     WEAVIATE_GRPC_ENABLED: bool = Field(
-        description="Whether to enable gRPC for Weaviate connection (True for gRPC, False for HTTP)",
+        description="whether to enable gRPC for Weaviate connection",
         default=True,
     )
 
     WEAVIATE_BATCH_SIZE: PositiveInt = Field(
-        description="Number of objects to be processed in a single batch operation (default is 100)",
+        description="Weaviate batch size",
         default=100,
     )

api/constants/__init__.py

@@ -1,2 +1 @@
 HIDDEN_VALUE = "[__HIDDEN__]"
-UUID_NIL = "00000000-0000-0000-0000-000000000000"

api/controllers/console/__init__.py

@@ -37,17 +37,7 @@ from .auth import activate, data_source_bearer_auth, data_source_oauth, forgot_p
 from .billing import billing
 
 # Import datasets controllers
-from .datasets import (
-    data_source,
-    datasets,
-    datasets_document,
-    datasets_segments,
-    external,
-    file,
-    hit_testing,
-    test_external,
-    website,
-)
+from .datasets import data_source, datasets, datasets_document, datasets_segments, file, hit_testing, website
 
 # Import explore controllers
 from .explore import (

api/controllers/console/app/completion.py

@@ -109,7 +109,6 @@ class ChatMessageApi(Resource):
         parser.add_argument("files", type=list, required=False, location="json")
         parser.add_argument("model_config", type=dict, required=True, location="json")
         parser.add_argument("conversation_id", type=uuid_value, location="json")
-        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
         parser.add_argument("response_mode", type=str, choices=["blocking", "streaming"], location="json")
         parser.add_argument("retriever_from", type=str, required=False, default="dev", location="json")
         args = parser.parse_args()

api/controllers/console/app/message.py

@@ -105,6 +105,8 @@ class ChatMessageListApi(Resource):
             if rest_count > 0:
                 has_more = True
 
+        history_messages = list(reversed(history_messages))
+
         return InfiniteScrollPagination(data=history_messages, limit=args["limit"], has_more=has_more)
 
 

api/controllers/console/app/workflow.py

@@ -166,8 +166,6 @@ class AdvancedChatDraftWorkflowRunApi(Resource):
         parser.add_argument("query", type=str, required=True, location="json", default="")
         parser.add_argument("files", type=list, location="json")
         parser.add_argument("conversation_id", type=uuid_value, location="json")
-        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
-
         args = parser.parse_args()
 
         try:

api/controllers/console/datasets/datasets.py

@@ -49,7 +49,7 @@ class DatasetListApi(Resource):
         page = request.args.get("page", default=1, type=int)
         limit = request.args.get("limit", default=20, type=int)
         ids = request.args.getlist("ids")
-        # provider = request.args.get("provider", default="vendor")
+        provider = request.args.get("provider", default="vendor")
         search = request.args.get("keyword", default=None, type=str)
         tag_ids = request.args.getlist("tag_ids")
 
@@ -57,7 +57,7 @@ class DatasetListApi(Resource):
             datasets, total = DatasetService.get_datasets_by_ids(ids, current_user.current_tenant_id)
         else:
             datasets, total = DatasetService.get_datasets(
-                page, limit, current_user.current_tenant_id, current_user, search, tag_ids
+                page, limit, provider, current_user.current_tenant_id, current_user, search, tag_ids
             )
 
         # check embedding setting
@@ -110,26 +110,6 @@ class DatasetListApi(Resource):
             nullable=True,
             help="Invalid indexing technique.",
         )
-        parser.add_argument(
-            "external_knowledge_api_id",
-            type=str,
-            nullable=True,
-            required=False,
-        )
-        parser.add_argument(
-            "provider",
-            type=str,
-            nullable=True,
-            choices=Dataset.PROVIDER_LIST,
-            required=False,
-            default="vendor",
-        )
-        parser.add_argument(
-            "external_knowledge_id",
-            type=str,
-            nullable=True,
-            required=False,
-        )
         args = parser.parse_args()
 
         # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
@@ -143,9 +123,6 @@ class DatasetListApi(Resource):
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
                 permission=DatasetPermissionEnum.ONLY_ME,
-                provider=args["provider"],
-                external_knowledge_api_id=args["external_knowledge_api_id"],
-                external_knowledge_id=args["external_knowledge_id"],
             )
         except services.errors.dataset.DatasetNameDuplicateError:
             raise DatasetNameDuplicateError()
@@ -234,33 +211,6 @@ class DatasetApi(Resource):
         )
         parser.add_argument("retrieval_model", type=dict, location="json", help="Invalid retrieval model.")
         parser.add_argument("partial_member_list", type=list, location="json", help="Invalid parent user list.")
-
-        parser.add_argument(
-            "external_retrieval_model",
-            type=dict,
-            required=False,
-            nullable=True,
-            location="json",
-            help="Invalid external retrieval model.",
-        )
-
-        parser.add_argument(
-            "external_knowledge_id",
-            type=str,
-            required=False,
-            nullable=True,
-            location="json",
-            help="Invalid external knowledge id.",
-        )
-
-        parser.add_argument(
-            "external_knowledge_api_id",
-            type=str,
-            required=False,
-            nullable=True,
-            location="json",
-            help="Invalid external knowledge api id.",
-        )
         args = parser.parse_args()
         data = request.get_json()
 

api/controllers/console/datasets/external.py

@@ -1,282 +0,0 @@
-from flask import request
-from flask_login import current_user
-from flask_restful import Resource, marshal, reqparse
-from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
-
-import services
-from controllers.console import api
-from controllers.console.app.error import ProviderNotInitializeError
-from controllers.console.datasets.error import DatasetNameDuplicateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
-from fields.dataset_fields import dataset_detail_fields
-from libs.login import login_required
-from services.dataset_service import DatasetService
-from services.external_knowledge_service import ExternalDatasetService
-from services.hit_testing_service import HitTestingService
-
-
-def _validate_name(name):
-    if not name or len(name) < 1 or len(name) > 100:
-        raise ValueError("Name must be between 1 to 100 characters.")
-    return name
-
-
-def _validate_description_length(description):
-    if description and len(description) > 400:
-        raise ValueError("Description cannot exceed 400 characters.")
-    return description
-
-
-class ExternalApiTemplateListApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def get(self):
-        page = request.args.get("page", default=1, type=int)
-        limit = request.args.get("limit", default=20, type=int)
-        search = request.args.get("keyword", default=None, type=str)
-
-        external_knowledge_apis, total = ExternalDatasetService.get_external_knowledge_apis(
-            page, limit, current_user.current_tenant_id, search
-        )
-        response = {
-            "data": [item.to_dict() for item in external_knowledge_apis],
-            "has_more": len(external_knowledge_apis) == limit,
-            "limit": limit,
-            "total": total,
-            "page": page,
-        }
-        return response, 200
-
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument(
-            "name",
-            nullable=False,
-            required=True,
-            help="Name is required. Name must be between 1 to 100 characters.",
-            type=_validate_name,
-        )
-        parser.add_argument(
-            "settings",
-            type=dict,
-            location="json",
-            nullable=False,
-            required=True,
-        )
-        args = parser.parse_args()
-
-        ExternalDatasetService.validate_api_list(args["settings"])
-
-        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
-        if not current_user.is_dataset_editor:
-            raise Forbidden()
-
-        try:
-            external_knowledge_api = ExternalDatasetService.create_external_knowledge_api(
-                tenant_id=current_user.current_tenant_id, user_id=current_user.id, args=args
-            )
-        except services.errors.dataset.DatasetNameDuplicateError:
-            raise DatasetNameDuplicateError()
-
-        return external_knowledge_api.to_dict(), 201
-
-
-class ExternalApiTemplateApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def get(self, external_knowledge_api_id):
-        external_knowledge_api_id = str(external_knowledge_api_id)
-        external_knowledge_api = ExternalDatasetService.get_external_knowledge_api(external_knowledge_api_id)
-        if external_knowledge_api is None:
-            raise NotFound("API template not found.")
-
-        return external_knowledge_api.to_dict(), 200
-
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def patch(self, external_knowledge_api_id):
-        external_knowledge_api_id = str(external_knowledge_api_id)
-
-        parser = reqparse.RequestParser()
-        parser.add_argument(
-            "name",
-            nullable=False,
-            required=True,
-            help="type is required. Name must be between 1 to 100 characters.",
-            type=_validate_name,
-        )
-        parser.add_argument(
-            "settings",
-            type=dict,
-            location="json",
-            nullable=False,
-            required=True,
-        )
-        args = parser.parse_args()
-        ExternalDatasetService.validate_api_list(args["settings"])
-
-        external_knowledge_api = ExternalDatasetService.update_external_knowledge_api(
-            tenant_id=current_user.current_tenant_id,
-            user_id=current_user.id,
-            external_knowledge_api_id=external_knowledge_api_id,
-            args=args,
-        )
-
-        return external_knowledge_api.to_dict(), 200
-
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def delete(self, external_knowledge_api_id):
-        external_knowledge_api_id = str(external_knowledge_api_id)
-
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor or current_user.is_dataset_operator:
-            raise Forbidden()
-
-        ExternalDatasetService.delete_external_knowledge_api(current_user.current_tenant_id, external_knowledge_api_id)
-        return {"result": "success"}, 200
-
-
-class ExternalApiUseCheckApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def get(self, external_knowledge_api_id):
-        external_knowledge_api_id = str(external_knowledge_api_id)
-
-        external_knowledge_api_is_using, count = ExternalDatasetService.external_knowledge_api_use_check(
-            external_knowledge_api_id
-        )
-        return {"is_using": external_knowledge_api_is_using, "count": count}, 200
-
-
-class ExternalDatasetInitApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self):
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
-            raise Forbidden()
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("external_knowledge_api_id", type=str, required=True, nullable=True, location="json")
-        # parser.add_argument('name', nullable=False, required=True,
-        #                     help='name is required. Name must be between 1 to 100 characters.',
-        #                     type=_validate_name)
-        # parser.add_argument('description', type=str, required=True, nullable=True, location='json')
-        parser.add_argument("data_source", type=dict, required=True, nullable=True, location="json")
-        parser.add_argument("process_parameter", type=dict, required=True, nullable=True, location="json")
-
-        args = parser.parse_args()
-
-        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
-        if not current_user.is_dataset_editor:
-            raise Forbidden()
-
-        # validate args
-        ExternalDatasetService.document_create_args_validate(
-            current_user.current_tenant_id, args["external_knowledge_api_id"], args["process_parameter"]
-        )
-
-        try:
-            dataset, documents, batch = ExternalDatasetService.init_external_dataset(
-                tenant_id=current_user.current_tenant_id,
-                user_id=current_user.id,
-                args=args,
-            )
-        except Exception as ex:
-            raise ProviderNotInitializeError(ex.description)
-        response = {"dataset": dataset, "documents": documents, "batch": batch}
-
-        return response
-
-
-class ExternalDatasetCreateApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self):
-        # The role of the current user in the ta table must be admin, owner, or editor
-        if not current_user.is_editor:
-            raise Forbidden()
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("external_knowledge_api_id", type=str, required=True, nullable=False, location="json")
-        parser.add_argument("external_knowledge_id", type=str, required=True, nullable=False, location="json")
-        parser.add_argument(
-            "name",
-            nullable=False,
-            required=True,
-            help="name is required. Name must be between 1 to 100 characters.",
-            type=_validate_name,
-        )
-        parser.add_argument("description", type=str, required=False, nullable=True, location="json")
-        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
-
-        args = parser.parse_args()
-
-        # The role of the current user in the ta table must be admin, owner, or editor, or dataset_operator
-        if not current_user.is_dataset_editor:
-            raise Forbidden()
-
-        try:
-            dataset = ExternalDatasetService.create_external_dataset(
-                tenant_id=current_user.current_tenant_id,
-                user_id=current_user.id,
-                args=args,
-            )
-        except services.errors.dataset.DatasetNameDuplicateError:
-            raise DatasetNameDuplicateError()
-
-        return marshal(dataset, dataset_detail_fields), 201
-
-
-class ExternalKnowledgeHitTestingApi(Resource):
-    @setup_required
-    @login_required
-    @account_initialization_required
-    def post(self, dataset_id):
-        dataset_id_str = str(dataset_id)
-        dataset = DatasetService.get_dataset(dataset_id_str)
-        if dataset is None:
-            raise NotFound("Dataset not found.")
-
-        try:
-            DatasetService.check_dataset_permission(dataset, current_user)
-        except services.errors.account.NoPermissionError as e:
-            raise Forbidden(str(e))
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("query", type=str, location="json")
-        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
-        args = parser.parse_args()
-
-        HitTestingService.hit_testing_args_check(args)
-
-        try:
-            response = HitTestingService.external_retrieve(
-                dataset=dataset,
-                query=args["query"],
-                account=current_user,
-                external_retrieval_model=args["external_retrieval_model"],
-            )
-
-            return response
-        except Exception as e:
-            raise InternalServerError(str(e))
-
-
-api.add_resource(ExternalKnowledgeHitTestingApi, "/datasets/<uuid:dataset_id>/external-hit-testing")
-api.add_resource(ExternalDatasetCreateApi, "/datasets/external")
-api.add_resource(ExternalApiTemplateListApi, "/datasets/external-knowledge-api")
-api.add_resource(ExternalApiTemplateApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>")
-api.add_resource(ExternalApiUseCheckApi, "/datasets/external-knowledge-api/<uuid:external_knowledge_api_id>/use-check")

api/controllers/console/datasets/file.py

@@ -1,6 +1,7 @@
 from flask import request
 from flask_login import current_user
 from flask_restful import Resource, marshal_with
+from werkzeug.exceptions import Forbidden
 
 import services
 from configs import dify_config
@@ -41,6 +42,9 @@ class FileApi(Resource):
     @marshal_with(file_fields)
     @cloud_edition_billing_resource_check("documents")
     def post(self):
+        if not current_user.is_dataset_editor:
+            raise Forbidden()
+        
         # get file from request
         file = request.files["file"]
 

api/controllers/console/datasets/hit_testing.py

@@ -47,7 +47,6 @@ class HitTestingApi(Resource):
         parser = reqparse.RequestParser()
         parser.add_argument("query", type=str, location="json")
         parser.add_argument("retrieval_model", type=dict, required=False, location="json")
-        parser.add_argument("external_retrieval_model", type=dict, required=False, location="json")
         args = parser.parse_args()
 
         HitTestingService.hit_testing_args_check(args)
@@ -58,7 +57,6 @@ class HitTestingApi(Resource):
                 query=args["query"],
                 account=current_user,
                 retrieval_model=args["retrieval_model"],
-                external_retrieval_model=args["external_retrieval_model"],
                 limit=10,
             )
 

api/controllers/console/datasets/test_external.py

@@ -1,33 +0,0 @@
-from flask_restful import Resource, reqparse
-
-from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
-from libs.login import login_required
-from services.external_knowledge_service import ExternalDatasetService
-
-
-class TestExternalApi(Resource):
-    def post(self):
-        parser = reqparse.RequestParser()
-        parser.add_argument("retrieval_setting", nullable=False, required=True, type=dict, location="json")
-        parser.add_argument(
-            "query",
-            nullable=False,
-            required=True,
-            type=str,
-        )
-        parser.add_argument(
-            "knowledge_id",
-            nullable=False,
-            required=True,
-            type=str,
-        )
-        args = parser.parse_args()
-        result = ExternalDatasetService.test_external_knowledge_retrieval(
-            args["retrieval_setting"], args["query"], args["knowledge_id"]
-        )
-        return result, 200
-
-
-api.add_resource(TestExternalApi, "/retrieval")

api/controllers/console/explore/completion.py

@@ -100,7 +100,6 @@ class ChatApi(InstalledAppResource):
         parser.add_argument("query", type=str, required=True, location="json")
         parser.add_argument("files", type=list, required=False, location="json")
         parser.add_argument("conversation_id", type=uuid_value, location="json")
-        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
         parser.add_argument("retriever_from", type=str, required=False, default="explore_app", location="json")
         args = parser.parse_args()
 

api/controllers/console/explore/message.py

@@ -51,7 +51,7 @@ class MessageListApi(InstalledAppResource):
 
         try:
             return MessageService.pagination_by_first_id(
-                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
+                app_model, current_user, args["conversation_id"], args["first_id"], args["limit"]
             )
         except services.errors.conversation.ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")

api/controllers/console/files.py

@@ -0,0 +1,99 @@
+from flask import request
+from flask_login import current_user
+from flask_restful import Resource, marshal_with
+from werkzeug.exceptions import Forbidden
+
+import services
+from configs import dify_config
+from constants import DOCUMENT_EXTENSIONS
+from controllers.common.errors import FilenameNotExistsError
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
+from fields.file_fields import file_fields, upload_config_fields
+from libs.login import login_required
+from services.file_service import FileService
+
+from .error import (
+    FileTooLargeError,
+    NoFileUploadedError,
+    TooManyFilesError,
+    UnsupportedFileTypeError,
+)
+
+PREVIEW_WORDS_LIMIT = 3000
+
+
+class FileApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(upload_config_fields)
+    def get(self):
+        return {
+            "file_size_limit": dify_config.UPLOAD_FILE_SIZE_LIMIT,
+            "batch_count_limit": dify_config.UPLOAD_FILE_BATCH_LIMIT,
+            "image_file_size_limit": dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT,
+            "video_file_size_limit": dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT,
+            "audio_file_size_limit": dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT,
+            "workflow_file_upload_limit": dify_config.WORKFLOW_FILE_UPLOAD_LIMIT,
+        }, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(file_fields)
+    @cloud_edition_billing_resource_check("documents")
+    def post(self):
+        file = request.files["file"]
+        source = request.form.get("source")
+
+        if "file" not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        if source == "datasets" and not current_user.is_dataset_editor:
+            raise Forbidden()
+
+        if source not in {"datasets", None}:
+            source = None
+
+        try:
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source=source,
+            )
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        return upload_file, 201
+
+
+class FilePreviewApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, file_id):
+        file_id = str(file_id)
+        text = FileService.get_file_preview(file_id)
+        return {"content": text}
+
+
+class FileSupportTypeApi(Resource):
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self):
+        return {"allowed_extensions": DOCUMENT_EXTENSIONS}

api/controllers/service_api/app/message.py

@@ -54,7 +54,6 @@ class MessageListApi(Resource):
     message_fields = {
         "id": fields.String,
         "conversation_id": fields.String,
-        "parent_message_id": fields.String,
         "inputs": fields.Raw,
         "query": fields.String,
         "answer": fields.String(attribute="re_sign_file_url_answer"),

api/controllers/service_api/dataset/dataset.py

@@ -28,11 +28,11 @@ class DatasetListApi(DatasetApiResource):
 
         page = request.args.get("page", default=1, type=int)
         limit = request.args.get("limit", default=20, type=int)
-        # provider = request.args.get("provider", default="vendor")
+        provider = request.args.get("provider", default="vendor")
         search = request.args.get("keyword", default=None, type=str)
         tag_ids = request.args.getlist("tag_ids")
 
-        datasets, total = DatasetService.get_datasets(page, limit, tenant_id, current_user, search, tag_ids)
+        datasets, total = DatasetService.get_datasets(page, limit, provider, tenant_id, current_user, search, tag_ids)
         # check embedding setting
         provider_manager = ProviderManager()
         configurations = provider_manager.get_configurations(tenant_id=current_user.current_tenant_id)
@@ -82,26 +82,6 @@ class DatasetListApi(DatasetApiResource):
             required=False,
             nullable=False,
         )
-        parser.add_argument(
-            "external_knowledge_api_id",
-            type=str,
-            nullable=True,
-            required=False,
-            default="_validate_name",
-        )
-        parser.add_argument(
-            "provider",
-            type=str,
-            nullable=True,
-            required=False,
-            default="vendor",
-        )
-        parser.add_argument(
-            "external_knowledge_id",
-            type=str,
-            nullable=True,
-            required=False,
-        )
         args = parser.parse_args()
 
         try:
@@ -111,9 +91,6 @@ class DatasetListApi(DatasetApiResource):
                 indexing_technique=args["indexing_technique"],
                 account=current_user,
                 permission=args["permission"],
-                provider=args["provider"],
-                external_knowledge_api_id=args["external_knowledge_api_id"],
-                external_knowledge_id=args["external_knowledge_id"],
             )
         except services.errors.dataset.DatasetNameDuplicateError:
             raise DatasetNameDuplicateError()

api/controllers/web/completion.py

@@ -96,7 +96,6 @@ class ChatApi(WebApiResource):
         parser.add_argument("files", type=list, required=False, location="json")
         parser.add_argument("response_mode", type=str, choices=["blocking", "streaming"], location="json")
         parser.add_argument("conversation_id", type=uuid_value, location="json")
-        parser.add_argument("parent_message_id", type=uuid_value, required=False, location="json")
         parser.add_argument("retriever_from", type=str, required=False, default="web_app", location="json")
 
         args = parser.parse_args()

api/controllers/web/message.py

@@ -57,7 +57,6 @@ class MessageListApi(WebApiResource):
     message_fields = {
         "id": fields.String,
         "conversation_id": fields.String,
-        "parent_message_id": fields.String,
         "inputs": fields.Raw,
         "query": fields.String,
         "answer": fields.String(attribute="re_sign_file_url_answer"),
@@ -90,7 +89,7 @@ class MessageListApi(WebApiResource):
 
         try:
             return MessageService.pagination_by_first_id(
-                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"], "desc"
+                app_model, end_user, args["conversation_id"], args["first_id"], args["limit"]
             )
         except services.errors.conversation.ConversationNotExistsError:
             raise NotFound("Conversation Not Exists.")

api/core/agent/base_agent_runner.py

@@ -32,7 +32,6 @@ from core.model_runtime.entities.message_entities import (
 from core.model_runtime.entities.model_entities import ModelFeature
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.utils.encoders import jsonable_encoder
-from core.prompt.utils.extract_thread_messages import extract_thread_messages
 from core.tools.entities.tool_entities import (
     ToolParameter,
     ToolRuntimeVariablePool,
@@ -442,12 +441,10 @@ class BaseAgentRunner(AppRunner):
             .filter(
                 Message.conversation_id == self.message.conversation_id,
             )
-            .order_by(Message.created_at.desc())
+            .order_by(Message.created_at.asc())
             .all()
         )
 
-        messages = list(reversed(extract_thread_messages(messages)))
-
         for message in messages:
             if message.id == self.message.id:
                 continue

api/core/app/apps/advanced_chat/app_generator.py

@@ -121,7 +121,6 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
             inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,

api/core/app/apps/agent_chat/app_generator.py

@@ -127,7 +127,6 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,

api/core/app/apps/base_app_generate_response_converter.py

@@ -75,10 +75,10 @@ class AppGenerateResponseConverter(ABC):
         :return:
         """
         # show_retrieve_source
-        updated_resources = []
         if "retriever_resources" in metadata:
+            metadata["retriever_resources"] = []
             for resource in metadata["retriever_resources"]:
-                updated_resources.append(
+                metadata["retriever_resources"].append(
                     {
                         "segment_id": resource["segment_id"],
                         "position": resource["position"],
@@ -87,7 +87,6 @@ class AppGenerateResponseConverter(ABC):
                         "content": resource["content"],
                     }
                 )
-            metadata["retriever_resources"] = updated_resources
 
         # show annotation reply
         if "annotation_reply" in metadata:

api/core/app/apps/base_app_runner.py

@@ -309,7 +309,7 @@ class AppRunner:
             if not prompt_messages:
                 prompt_messages = result.prompt_messages
 
-            if result.delta.usage:
+            if not usage and result.delta.usage:
                 usage = result.delta.usage
 
         if not usage:

api/core/app/apps/chat/app_generator.py

@@ -128,7 +128,6 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             inputs=conversation.inputs if conversation else self._get_cleaned_inputs(inputs, app_config),
             query=query,
             files=file_objs,
-            parent_message_id=args.get("parent_message_id"),
             user_id=user.id,
             stream=stream,
             invoke_from=invoke_from,

api/core/app/apps/message_based_app_generator.py

@@ -218,7 +218,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
             answer_tokens=0,
             answer_unit_price=0,
             answer_price_unit=0,
-            parent_message_id=getattr(application_generate_entity, "parent_message_id", None),
             provider_response_latency=0,
             total_price=0,
             currency="USD",

api/core/app/entities/app_invoke_entities.py

@@ -122,7 +122,6 @@ class ChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
     """
 
     conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = None
 
 
 class CompletionAppGenerateEntity(EasyUIBasedAppGenerateEntity):
@@ -139,7 +138,6 @@ class AgentChatAppGenerateEntity(EasyUIBasedAppGenerateEntity):
     """
 
     conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = None
 
 
 class AdvancedChatAppGenerateEntity(AppGenerateEntity):
@@ -151,7 +149,6 @@ class AdvancedChatAppGenerateEntity(AppGenerateEntity):
     app_config: WorkflowUIBasedAppConfig
 
     conversation_id: Optional[str] = None
-    parent_message_id: Optional[str] = None
     query: str
 
     class SingleIterationRunEntity(BaseModel):

api/core/callback_handler/index_tool_callback_handler.py

@@ -59,7 +59,7 @@ class DatasetIndexToolCallbackHandler:
             for item in resource:
                 dataset_retriever_resource = DatasetRetrieverResource(
                     message_id=self._message_id,
-                    position=item.get("position") or 0,
+                    position=item.get("position"),
                     dataset_id=item.get("dataset_id"),
                     dataset_name=item.get("dataset_name"),
                     document_id=item.get("document_id"),

api/core/embedding/cached_embedding.py

@@ -5,7 +5,6 @@ from typing import Optional, cast
 import numpy as np
 from sqlalchemy.exc import IntegrityError
 
-from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_manager import ModelInstance
 from core.model_runtime.entities.model_entities import ModelPropertyKey
 from core.model_runtime.model_providers.__base.text_embedding_model import TextEmbeddingModel
@@ -57,9 +56,7 @@ class CacheEmbedding(Embeddings):
                 for i in range(0, len(embedding_queue_texts), max_chunks):
                     batch_texts = embedding_queue_texts[i : i + max_chunks]
 
-                    embedding_result = self._model_instance.invoke_text_embedding(
-                        texts=batch_texts, user=self._user, input_type=EmbeddingInputType.DOCUMENT
-                    )
+                    embedding_result = self._model_instance.invoke_text_embedding(texts=batch_texts, user=self._user)
 
                     for vector in embedding_result.embeddings:
                         try:
@@ -103,9 +100,7 @@ class CacheEmbedding(Embeddings):
             redis_client.expire(embedding_cache_key, 600)
             return list(np.frombuffer(base64.b64decode(embedding), dtype="float"))
         try:
-            embedding_result = self._model_instance.invoke_text_embedding(
-                texts=[text], user=self._user, input_type=EmbeddingInputType.QUERY
-            )
+            embedding_result = self._model_instance.invoke_text_embedding(texts=[text], user=self._user)
 
             embedding_results = embedding_result.embeddings[0]
             embedding_results = (embedding_results / np.linalg.norm(embedding_results)).tolist()

api/core/embedding/embedding_constant.py

@@ -1,10 +0,0 @@
-from enum import Enum
-
-
-class EmbeddingInputType(Enum):
-    """
-    Enum for embedding input type.
-    """
-
-    DOCUMENT = "document"
-    QUERY = "query"

api/core/llm_generator/llm_generator.py

@@ -47,8 +47,6 @@ class LLMGenerator:
             )
         answer = response.message.content
         cleaned_answer = re.sub(r"^.*(\{.*\}).*$", r"\1", answer, flags=re.DOTALL)
-        if cleaned_answer is None:
-            return ""
         result_dict = json.loads(cleaned_answer)
         answer = result_dict["Your Output"]
         name = answer.strip()

api/core/llm_generator/prompts.py

@@ -65,6 +65,7 @@ SUGGESTED_QUESTIONS_AFTER_ANSWER_INSTRUCTION_PROMPT = (
     "Please help me predict the three most likely questions that human would ask, "
     "and keeping each question under 20 characters.\n"
     "MAKE SURE your output is the SAME language as the Assistant's latest response"
+    "(if the main response is written in Chinese, then the language of your output must be using Chinese.)!\n"
     "The output must be an array in JSON format following the specified schema:\n"
     '["question1","question2","question3"]\n'
 )

api/core/memory/token_buffer_memory.py

@@ -11,7 +11,6 @@ from core.model_runtime.entities.message_entities import (
     TextPromptMessageContent,
     UserPromptMessage,
 )
-from core.prompt.utils.extract_thread_messages import extract_thread_messages
 from extensions.ext_database import db
 from models.model import AppMode, Conversation, Message, MessageFile
 from models.workflow import WorkflowRun
@@ -34,17 +33,8 @@ class TokenBufferMemory:
 
         # fetch limited messages, and return reversed
         query = (
-            db.session.query(
-                Message.id,
-                Message.query,
-                Message.answer,
-                Message.created_at,
-                Message.workflow_run_id,
-                Message.parent_message_id,
-            )
-            .filter(
-                Message.conversation_id == self.conversation.id,
-            )
+            db.session.query(Message.id, Message.query, Message.answer, Message.created_at, Message.workflow_run_id)
+            .filter(Message.conversation_id == self.conversation.id, Message.answer != "")
             .order_by(Message.created_at.desc())
         )
 
@@ -55,12 +45,7 @@ class TokenBufferMemory:
 
         messages = query.limit(message_limit).all()
 
-        # instead of all messages from the conversation, we only need to extract messages
-        # that belong to the thread of last message
-        thread_messages = extract_thread_messages(messages)
-        thread_messages.pop(0)
-        messages = list(reversed(thread_messages))
-
+        messages = list(reversed(messages))
         message_file_parser = MessageFileParser(tenant_id=app_record.tenant_id, app_id=app_record.id)
         prompt_messages = []
         for message in messages:

api/core/model_manager.py

@@ -3,7 +3,6 @@ import os
 from collections.abc import Callable, Generator, Sequence
 from typing import IO, Optional, Union, cast
 
-from core.embedding.embedding_constant import EmbeddingInputType
 from core.entities.provider_configuration import ProviderConfiguration, ProviderModelBundle
 from core.entities.provider_entities import ModelLoadBalancingConfiguration
 from core.errors.error import ProviderTokenNotInitError
@@ -159,15 +158,12 @@ class ModelInstance:
             tools=tools,
         )
 
-    def invoke_text_embedding(
-        self, texts: list[str], user: Optional[str] = None, input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT
-    ) -> TextEmbeddingResult:
+    def invoke_text_embedding(self, texts: list[str], user: Optional[str] = None) -> TextEmbeddingResult:
         """
         Invoke large language model
 
         :param texts: texts to embed
         :param user: unique user id
-        :param input_type: input type
         :return: embeddings result
         """
         if not isinstance(self.model_type_instance, TextEmbeddingModel):
@@ -180,7 +176,6 @@ class ModelInstance:
             credentials=self.credentials,
             texts=texts,
             user=user,
-            input_type=input_type,
         )
 
     def get_text_embedding_num_tokens(self, texts: list[str]) -> int:

api/core/model_runtime/docs/zh_Hans/predefined_model_scale_out.md

@@ -62,7 +62,7 @@ pricing:  # 价格信息
 
 建议将所有模型配置都准备完毕后再开始模型代码的实现。
 
-同样，也可以参考  `model_providers` 目录下其他供应商对应模型类型目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#aimodelentity)。
+同样，也可以参考  `model_providers` 目录下其他供应商对应模型类型目录下的 YAML 配置信息，完整的 YAML 规则见：[Schema](schema.md#AIModel)。
 
 ### 实现模型调用代码
 

api/core/model_runtime/model_providers/__base/text_embedding_model.py

@@ -4,7 +4,6 @@ from typing import Optional
 
 from pydantic import ConfigDict
 
-from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_runtime.entities.model_entities import ModelPropertyKey, ModelType
 from core.model_runtime.entities.text_embedding_entities import TextEmbeddingResult
 from core.model_runtime.model_providers.__base.ai_model import AIModel
@@ -21,47 +20,35 @@ class TextEmbeddingModel(AIModel):
     model_config = ConfigDict(protected_namespaces=())
 
     def invoke(
-        self,
-        model: str,
-        credentials: dict,
-        texts: list[str],
-        user: Optional[str] = None,
-        input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
+        self, model: str, credentials: dict, texts: list[str], user: Optional[str] = None
     ) -> TextEmbeddingResult:
         """
-        Invoke text embedding model
+        Invoke large language model
 
         :param model: model name
         :param credentials: model credentials
         :param texts: texts to embed
         :param user: unique user id
-        :param input_type: input type
         :return: embeddings result
         """
         self.started_at = time.perf_counter()
 
         try:
-            return self._invoke(model, credentials, texts, user, input_type)
+            return self._invoke(model, credentials, texts, user)
         except Exception as e:
             raise self._transform_invoke_error(e)
 
     @abstractmethod
     def _invoke(
-        self,
-        model: str,
-        credentials: dict,
-        texts: list[str],
-        user: Optional[str] = None,
-        input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
+        self, model: str, credentials: dict, texts: list[str], user: Optional[str] = None
     ) -> TextEmbeddingResult:
         """
-        Invoke text embedding model
+        Invoke large language model
 
         :param model: model name
         :param credentials: model credentials
         :param texts: texts to embed
         :param user: unique user id
-        :param input_type: input type
         :return: embeddings result
         """
         raise NotImplementedError

api/core/model_runtime/model_providers/_position.yaml

@@ -37,6 +37,3 @@
 - siliconflow
 - perfxcloud
 - zhinao
-- fireworks
-- mixedbread
-- nomic

api/core/model_runtime/model_providers/azure_openai/text_embedding/text_embedding.py

@@ -7,7 +7,6 @@ import numpy as np
 import tiktoken
 from openai import AzureOpenAI
 
-from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_runtime.entities.model_entities import AIModelEntity, PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
@@ -18,23 +17,8 @@ from core.model_runtime.model_providers.azure_openai._constant import EMBEDDING_
 
 class AzureOpenAITextEmbeddingModel(_CommonAzureOpenAI, TextEmbeddingModel):
     def _invoke(
-        self,
-        model: str,
-        credentials: dict,
-        texts: list[str],
-        user: Optional[str] = None,
-        input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
+        self, model: str, credentials: dict, texts: list[str], user: Optional[str] = None
     ) -> TextEmbeddingResult:
-        """
-        Invoke text embedding model
-
-        :param model: model name
-        :param credentials: model credentials
-        :param texts: texts to embed
-        :param user: unique user id
-        :param input_type: input type
-        :return: embeddings result
-        """
         base_model_name = credentials["base_model_name"]
         credentials_kwargs = self._to_credential_kwargs(credentials)
         client = AzureOpenAI(**credentials_kwargs)

api/core/model_runtime/model_providers/baichuan/text_embedding/text_embedding.py

@@ -4,7 +4,6 @@ from typing import Optional
 
 from requests import post
 
-from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (
@@ -36,12 +35,7 @@ class BaichuanTextEmbeddingModel(TextEmbeddingModel):
     api_base: str = "http://api.baichuan-ai.com/v1/embeddings"
 
     def _invoke(
-        self,
-        model: str,
-        credentials: dict,
-        texts: list[str],
-        user: Optional[str] = None,
-        input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
+        self, model: str, credentials: dict, texts: list[str], user: Optional[str] = None
     ) -> TextEmbeddingResult:
         """
         Invoke text embedding model
@@ -50,7 +44,6 @@ class BaichuanTextEmbeddingModel(TextEmbeddingModel):
         :param credentials: model credentials
         :param texts: texts to embed
         :param user: unique user id
-        :param input_type: input type
         :return: embeddings result
         """
         api_key = credentials["api_key"]

api/core/model_runtime/model_providers/bedrock/text_embedding/text_embedding.py

@@ -13,7 +13,6 @@ from botocore.exceptions import (
     UnknownServiceError,
 )
 
-from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (
@@ -31,12 +30,7 @@ logger = logging.getLogger(__name__)
 
 class BedrockTextEmbeddingModel(TextEmbeddingModel):
     def _invoke(
-        self,
-        model: str,
-        credentials: dict,
-        texts: list[str],
-        user: Optional[str] = None,
-        input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
+        self, model: str, credentials: dict, texts: list[str], user: Optional[str] = None
     ) -> TextEmbeddingResult:
         """
         Invoke text embedding model
@@ -45,7 +39,6 @@ class BedrockTextEmbeddingModel(TextEmbeddingModel):
         :param credentials: model credentials
         :param texts: texts to embed
         :param user: unique user id
-        :param input_type: input type
         :return: embeddings result
         """
         client_config = Config(region_name=credentials["aws_region"])

api/core/model_runtime/model_providers/cohere/text_embedding/text_embedding.py

@@ -5,7 +5,6 @@ import cohere
 import numpy as np
 from cohere.core import RequestOptions
 
-from core.embedding.embedding_constant import EmbeddingInputType
 from core.model_runtime.entities.model_entities import PriceType
 from core.model_runtime.entities.text_embedding_entities import EmbeddingUsage, TextEmbeddingResult
 from core.model_runtime.errors.invoke import (
@@ -26,12 +25,7 @@ class CohereTextEmbeddingModel(TextEmbeddingModel):
     """
 
     def _invoke(
-        self,
-        model: str,
-        credentials: dict,
-        texts: list[str],
-        user: Optional[str] = None,
-        input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
+        self, model: str, credentials: dict, texts: list[str], user: Optional[str] = None
     ) -> TextEmbeddingResult:
         """
         Invoke text embedding model
@@ -40,7 +34,6 @@ class CohereTextEmbeddingModel(TextEmbeddingModel):
         :param credentials: model credentials
         :param texts: texts to embed
         :param user: unique user id
-        :param input_type: input type
         :return: embeddings result
         """
         # get model properties

api/core/model_runtime/model_providers/fireworks/_assets/icon_l_en.svg

@@ -1,3 +0,0 @@
-<svg width="130" role="graphics-symbol" aria-label="Fireworks AI Home" viewBox="0 0 835 130" xmlns="http://www.w3.org/2000/svg">
-<path fill-rule="evenodd" clip-rule="evenodd" d="M112.65 0L91.33 51.09L69.99 0H56.3L79.69 55.85C81.63 60.51 86.18 63.52 91.25 63.52C96.32 63.52 100.86 60.51 102.81 55.87L126.34 0H112.65ZM121.76 77.84L160.76 38.41L155.44 25.86L112.84 69.01C109.28 72.62 108.26 77.94 110.23 82.6C112.19 87.22 116.72 90.21 121.77 90.21L121.79 90.23L182.68 90.08L177.36 77.53L121.77 77.84H121.76ZM21.92 38.38L27.24 25.83L69.84 68.98C73.4 72.58 74.43 77.92 72.45 82.57C70.49 87.2 65.94 90.18 60.91 90.18L0.02 90.04L0 90.06L5.32 77.51L60.91 77.82L21.92 38.38Z" fill="#6720FF"></path>
-<path d="M231.32 85.2198L231.33 85.2298H241.8V49.1698H275.62V39.8198H241.8V16.3598H279V7.00977H231.32V85.2198Z" class="fill-black dark:fill-white"></path><path d="M299.68 28.73H289.86V85.22H299.68V28.73Z" class="fill-black dark:fill-white"></path><path d="M324.58 36.2198H324.59C324.37 36.7598 324.16 37.0898 323.5 37.0898C322.95 37.0898 322.74 36.8798 322.74 36.3398V28.7298H312.92V85.2198H322.72V53.1598C322.72 42.3098 327.75 38.0698 337.24 38.0698H345.1V28.5098H338.77C331.03 28.5098 327.1 30.7898 324.58 36.2198Z" class="fill-black dark:fill-white"></path><path d="M377.76 78.3996C367.23 78.3996 359.37 72.4196 358.71 59.7196H404.6V54.2796C404.6 38.5296 395 27.1196 377.53 27.1196C360.06 27.1196 348.93 38.5296 348.93 56.9896C348.93 75.4496 359.73 86.8596 377.74 86.8596C395.75 86.8596 403.15 75.8996 404.81 67.3196H394.57C392.98 73.7396 388.29 78.3996 377.76 78.3996ZM377.53 35.5696C387.91 35.5696 394.33 41.1196 394.78 51.5496H358.98C360.61 40.8896 368.14 35.5696 377.53 35.5696Z" class="fill-black dark:fill-white"></path><path d="M474.29 74.68C474.05 75.66 473.75 75.99 472.97 75.99C472.19 75.99 471.86 75.66 471.65 74.68L460.73 28.73H443.81L432.89 74.68C432.65 75.66 432.35 75.99 431.57 75.99C430.79 75.99 430.46 75.66 430.25 74.68L419.33 28.73H409.73V30.91H409.79L423.11 85.22H439.97L451.22 37.85C451.43 37.08 451.64 36.87 452.3 36.87C452.84 36.87 453.17 37.1 453.38 37.85L464.63 85.22H481.49L494.81 30.91V28.73H485.21L474.29 74.68Z" class="fill-black dark:fill-white"></path><path d="M529.05 27.1099C512.56 27.1099 499.47 37.4199 499.47 56.9799C499.47 76.5399 512.55 86.8499 529.05 86.8499C545.55 86.8499 558.64 76.5399 558.64 56.9799C558.64 37.4199 545.54 27.1099 529.05 27.1099ZM529.07 78.1599C517.61 78.1599 509.42 70.5699 509.42 56.9799C509.42 43.3899 517.61 35.7999 529.07 35.7999C540.53 35.7999 548.72 43.4099 548.72 56.9799C548.72 70.5499 540.53 78.1599 529.07 78.1599Z" class="fill-black dark:fill-white"></path><path d="M580.68 36.2198C580.47 36.7598 580.26 37.0898 579.6 37.0898C579.05 37.0898 578.841 36.8798 578.841 36.3398V28.7298H569.021V85.2098H578.82V53.1598C578.82 42.3098 583.851 38.0698 593.341 38.0698H601.201V28.5098H594.87C587.13 28.5098 583.2 30.7898 580.68 36.2198Z" class="fill-black dark:fill-white"></path><path d="M618.591 55.0198V7.00977H608.771V85.2698H618.591V67.2298L629.24 58.1498L650.42 85.2498H661.16V83.0698L636.49 51.9398L661.16 30.9098V28.7298H648.54L618.591 55.0198Z" class="fill-black dark:fill-white"></path><path d="M695.19 52.8899L687.12 51.3699C679.38 49.8999 675.99 48.2799 675.99 43.5999C675.99 38.9199 679.82 35.4499 688.98 35.4499C698.14 35.4499 703.38 38.9399 704.14 46.6499H714.14C713.03 32.8799 702.34 27.1299 688.94 27.1299C675.54 27.1299 666.13 32.8899 666.13 43.7399C666.13 54.5899 673.83 58.3499 684.91 60.4099L692.98 61.9299C700.84 63.3999 704.77 65.0899 704.77 69.9699C704.77 74.8499 700.83 78.4899 691.35 78.4899C681.87 78.4899 675.58 74.5799 674.82 67.0799H664.83C665.76 80.5499 676.73 86.8499 691.36 86.8499C705.99 86.8499 714.61 80.6099 714.61 69.4099C714.61 58.2099 705.55 54.8399 695.19 52.8899Z" class="fill-black dark:fill-white"></path><path d="M834.64 7.00977H823.63V85.2698H834.64V7.00977Z" class="fill-black dark:fill-white"></path><path d="M770.23 7.77L739.71 83.8398V85.2698H750.61L758.34 64.8398H795.08L802.81 85.2698H814.04V83.8598L783.3 7.00977H770.23ZM761.97 55.3798L775.09 21.0098H775.08C775.3 20.4198 775.87 20.0298 776.5 20.0298H777.04C777.67 20.0298 778.24 20.4198 778.46 21.0098L791.48 55.3798H761.97Z" class="fill-black dark:fill-white"></path><path d="M299.68 7.00977H289.86V18.5298H299.68V7.00977Z" class="fill-black dark:fill-white"></path></svg>

api/core/model_runtime/model_providers/fireworks/_assets/icon_s_en.svg

@@ -1,5 +0,0 @@
-<svg width="638" height="315" viewBox="0 0 638 315" fill="none" xmlns="http://www.w3.org/2000/svg">
-<path d="M318.563 221.755C300.863 221.755 284.979 211.247 278.206 194.978L196.549 0H244.342L318.842 178.361L393.273 0H441.066L358.92 195.048C352.112 211.247 336.263 221.755 318.563 221.755Z" fill="#6720FF"/>
-<path d="M425.111 314.933C407.481 314.933 391.667 304.494 384.824 288.366C377.947 272.097 381.507 253.524 393.936 240.921L542.657 90.2803L561.229 134.094L425.076 271.748L619.147 270.666L637.72 314.479L425.146 315.003L425.076 314.933H425.111Z" fill="#6720FF"/>
-<path d="M0 314.408L18.5727 270.595L212.643 271.677L76.525 133.988L95.0977 90.1748L243.819 240.816C256.247 253.384 259.843 272.026 252.93 288.26C246.088 304.424 230.203 314.827 212.643 314.827L0.0698221 314.339L0 314.408Z" fill="#6720FF"/>
-</svg>

api/core/model_runtime/model_providers/fireworks/_common.py

@@ -1,52 +0,0 @@
-from collections.abc import Mapping
-
-import openai
-
-from core.model_runtime.errors.invoke import (
-    InvokeAuthorizationError,
-    InvokeBadRequestError,
-    InvokeConnectionError,
-    InvokeError,
-    InvokeRateLimitError,
-    InvokeServerUnavailableError,
-)
-
-
-class _CommonFireworks:
-    def _to_credential_kwargs(self, credentials: Mapping) -> dict:
-        """
-        Transform credentials to kwargs for model instance
-
-        :param credentials:
-        :return:
-        """
-        credentials_kwargs = {
-            "api_key": credentials["fireworks_api_key"],
-            "base_url": "https://api.fireworks.ai/inference/v1",
-            "max_retries": 1,
-        }
-
-        return credentials_kwargs
-
-    @property
-    def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
-        """
-        Map model invoke error to unified error
-        The key is the error type thrown to the caller
-        The value is the error type thrown by the model,
-        which needs to be converted into a unified error type for the caller.
-
-        :return: Invoke error mapping
-        """
-        return {
-            InvokeConnectionError: [openai.APIConnectionError, openai.APITimeoutError],
-            InvokeServerUnavailableError: [openai.InternalServerError],
-            InvokeRateLimitError: [openai.RateLimitError],
-            InvokeAuthorizationError: [openai.AuthenticationError, openai.PermissionDeniedError],
-            InvokeBadRequestError: [
-                openai.BadRequestError,
-                openai.NotFoundError,
-                openai.UnprocessableEntityError,
-                openai.APIError,
-            ],
-        }

api/core/model_runtime/model_providers/fireworks/fireworks.py

@@ -1,27 +0,0 @@
-import logging
-
-from core.model_runtime.entities.model_entities import ModelType
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.model_providers.__base.model_provider import ModelProvider
-
-logger = logging.getLogger(__name__)
-
-
-class FireworksProvider(ModelProvider):
-    def validate_provider_credentials(self, credentials: dict) -> None:
-        """
-        Validate provider credentials
-        if validate failed, raise exception
-
-        :param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
-        """
-        try:
-            model_instance = self.get_model_instance(ModelType.LLM)
-            model_instance.validate_credentials(
-                model="accounts/fireworks/models/llama-v3p1-8b-instruct", credentials=credentials
-            )
-        except CredentialsValidateFailedError as ex:
-            raise ex
-        except Exception as ex:
-            logger.exception(f"{self.get_provider_schema().provider} credentials validate failed")
-            raise ex

api/core/model_runtime/model_providers/fireworks/fireworks.yaml

@@ -1,30 +0,0 @@
-provider: fireworks
-label:
-  zh_Hans: Fireworks AI
-  en_US: Fireworks AI
-icon_small:
-  en_US: icon_s_en.svg
-icon_large:
-  en_US: icon_l_en.svg
-background: "#FCFDFF"
-help:
-  title:
-    en_US: Get your API Key from Fireworks AI
-    zh_Hans: 从 Fireworks AI 获取 API Key
-  url:
-    en_US: https://fireworks.ai/account/api-keys
-supported_model_types:
-  - llm
-  - text-embedding
-configurate_methods:
-  - predefined-model
-provider_credential_schema:
-  credential_form_schemas:
-    - variable: fireworks_api_key
-      label:
-        en_US: API Key
-      type: secret-input
-      required: true
-      placeholder:
-        zh_Hans: 在此输入您的 API Key
-        en_US: Enter your API Key

api/core/model_runtime/model_providers/fireworks/llm/_position.yaml

@@ -1,16 +0,0 @@
-- llama-v3p1-405b-instruct
-- llama-v3p1-70b-instruct
-- llama-v3p1-8b-instruct
-- llama-v3-70b-instruct
-- mixtral-8x22b-instruct
-- mixtral-8x7b-instruct
-- firefunction-v2
-- firefunction-v1
-- gemma2-9b-it
-- llama-v3-70b-instruct-hf
-- llama-v3-8b-instruct
-- llama-v3-8b-instruct-hf
-- mixtral-8x7b-instruct-hf
-- mythomax-l2-13b
-- phi-3-vision-128k-instruct
-- yi-large

api/core/model_runtime/model_providers/fireworks/llm/firefunction-v1.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/firefunction-v1
-label:
-  zh_Hans: Firefunction V1
-  en_US: Firefunction V1
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 32768
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.5'
-  output: '0.5'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/firefunction-v2.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/firefunction-v2
-label:
-  zh_Hans: Firefunction V2
-  en_US: Firefunction V2
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.9'
-  output: '0.9'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/gemma2-9b-it.yaml

@@ -1,45 +0,0 @@
-model: accounts/fireworks/models/gemma2-9b-it
-label:
-  zh_Hans: Gemma2 9B Instruct
-  en_US: Gemma2 9B Instruct
-model_type: llm
-features:
-  - agent-thought
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.2'
-  output: '0.2'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3-70b-instruct-hf.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3-70b-instruct-hf
-label:
-  zh_Hans: Llama3 70B Instruct(HF version)
-  en_US: Llama3 70B Instruct(HF version)
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.9'
-  output: '0.9'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3-70b-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3-70b-instruct
-label:
-  zh_Hans: Llama3 70B Instruct
-  en_US: Llama3 70B Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.9'
-  output: '0.9'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3-8b-instruct-hf.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3-8b-instruct-hf
-label:
-  zh_Hans: Llama3 8B Instruct(HF version)
-  en_US: Llama3 8B Instruct(HF version)
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.2'
-  output: '0.2'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3-8b-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3-8b-instruct
-label:
-  zh_Hans: Llama3 8B Instruct
-  en_US: Llama3 8B Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 8192
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.2'
-  output: '0.2'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3p1-405b-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3p1-405b-instruct
-label:
-  zh_Hans: Llama3.1 405B Instruct
-  en_US: Llama3.1 405B Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '3'
-  output: '3'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3p1-70b-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3p1-70b-instruct
-label:
-  zh_Hans: Llama3.1 70B Instruct
-  en_US: Llama3.1 70B Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.2'
-  output: '0.2'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3p1-8b-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3p1-8b-instruct
-label:
-  zh_Hans: Llama3.1 8B Instruct
-  en_US: Llama3.1 8B Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.2'
-  output: '0.2'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3p2-11b-vision-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
-label:
-  zh_Hans: Llama 3.2 11B Vision Instruct
-  en_US: Llama 3.2 11B Vision Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.2'
-  output: '0.2'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3p2-1b-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3p2-1b-instruct
-label:
-  zh_Hans: Llama 3.2 1B Instruct
-  en_US: Llama 3.2 1B Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.1'
-  output: '0.1'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3p2-3b-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3p2-3b-instruct
-label:
-  zh_Hans: Llama 3.2 3B Instruct
-  en_US: Llama 3.2 3B Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.1'
-  output: '0.1'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llama-v3p2-90b-vision-instruct.yaml

@@ -1,46 +0,0 @@
-model: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
-label:
-  zh_Hans: Llama 3.2 90B Vision Instruct
-  en_US: Llama 3.2 90B Vision Instruct
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-model_properties:
-  mode: chat
-  context_size: 131072
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-  - name: max_tokens
-    use_template: max_tokens
-  - name: context_length_exceeded_behavior
-    default: None
-    label:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    help:
-      zh_Hans: 上下文长度超出行为
-      en_US: Context Length Exceeded Behavior
-    type: string
-    options:
-      - None
-      - truncate
-      - error
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: '0.9'
-  output: '0.9'
-  unit: '0.000001'
-  currency: USD

api/core/model_runtime/model_providers/fireworks/llm/llm.py

@@ -1,610 +0,0 @@
-import logging
-from collections.abc import Generator
-from typing import Optional, Union, cast
-
-from openai import OpenAI, Stream
-from openai.types.chat import ChatCompletion, ChatCompletionChunk, ChatCompletionMessageToolCall
-from openai.types.chat.chat_completion_chunk import ChoiceDeltaFunctionCall, ChoiceDeltaToolCall
-from openai.types.chat.chat_completion_message import FunctionCall
-
-from core.model_runtime.callbacks.base_callback import Callback
-from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta
-from core.model_runtime.entities.message_entities import (
-    AssistantPromptMessage,
-    ImagePromptMessageContent,
-    PromptMessage,
-    PromptMessageContentType,
-    PromptMessageTool,
-    SystemPromptMessage,
-    TextPromptMessageContent,
-    ToolPromptMessage,
-    UserPromptMessage,
-)
-from core.model_runtime.errors.validate import CredentialsValidateFailedError
-from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
-from core.model_runtime.model_providers.fireworks._common import _CommonFireworks
-
-logger = logging.getLogger(__name__)
-
-FIREWORKS_BLOCK_MODE_PROMPT = """You should always follow the instructions and output a valid {{block}} object.
-The structure of the {{block}} object you can found in the instructions, use {"answer": "$your_answer"} as the default structure
-if you are not sure about the structure.
-
-<instructions>
-{{instructions}}
-</instructions>
-"""  # noqa: E501
-
-
-class FireworksLargeLanguageModel(_CommonFireworks, LargeLanguageModel):
-    """
-    Model class for Fireworks large language model.
-    """
-
-    def _invoke(
-        self,
-        model: str,
-        credentials: dict,
-        prompt_messages: list[PromptMessage],
-        model_parameters: dict,
-        tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
-        stream: bool = True,
-        user: Optional[str] = None,
-    ) -> Union[LLMResult, Generator]:
-        """
-        Invoke large language model
-
-        :param model: model name
-        :param credentials: model credentials
-        :param prompt_messages: prompt messages
-        :param model_parameters: model parameters
-        :param tools: tools for tool calling
-        :param stop: stop words
-        :param stream: is stream response
-        :param user: unique user id
-        :return: full response or stream response chunk generator result
-        """
-
-        return self._chat_generate(
-            model=model,
-            credentials=credentials,
-            prompt_messages=prompt_messages,
-            model_parameters=model_parameters,
-            tools=tools,
-            stop=stop,
-            stream=stream,
-            user=user,
-        )
-
-    def _code_block_mode_wrapper(
-        self,
-        model: str,
-        credentials: dict,
-        prompt_messages: list[PromptMessage],
-        model_parameters: dict,
-        tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
-        stream: bool = True,
-        user: Optional[str] = None,
-        callbacks: Optional[list[Callback]] = None,
-    ) -> Union[LLMResult, Generator]:
-        """
-        Code block mode wrapper for invoking large language model
-        """
-        if "response_format" in model_parameters and model_parameters["response_format"] in {"JSON", "XML"}:
-            stop = stop or []
-            self._transform_chat_json_prompts(
-                model=model,
-                credentials=credentials,
-                prompt_messages=prompt_messages,
-                model_parameters=model_parameters,
-                tools=tools,
-                stop=stop,
-                stream=stream,
-                user=user,
-                response_format=model_parameters["response_format"],
-            )
-            model_parameters.pop("response_format")
-
-            return self._invoke(
-                model=model,
-                credentials=credentials,
-                prompt_messages=prompt_messages,
-                model_parameters=model_parameters,
-                tools=tools,
-                stop=stop,
-                stream=stream,
-                user=user,
-            )
-
-    def _transform_chat_json_prompts(
-        self,
-        model: str,
-        credentials: dict,
-        prompt_messages: list[PromptMessage],
-        model_parameters: dict,
-        tools: list[PromptMessageTool] | None = None,
-        stop: list[str] | None = None,
-        stream: bool = True,
-        user: str | None = None,
-        response_format: str = "JSON",
-    ) -> None:
-        """
-        Transform json prompts
-        """
-        if stop is None:
-            stop = []
-        if "```\n" not in stop:
-            stop.append("```\n")
-        if "\n```" not in stop:
-            stop.append("\n```")
-
-        if len(prompt_messages) > 0 and isinstance(prompt_messages[0], SystemPromptMessage):
-            prompt_messages[0] = SystemPromptMessage(
-                content=FIREWORKS_BLOCK_MODE_PROMPT.replace("{{instructions}}", prompt_messages[0].content).replace(
-                    "{{block}}", response_format
-                )
-            )
-            prompt_messages.append(AssistantPromptMessage(content=f"\n```{response_format}\n"))
-        else:
-            prompt_messages.insert(
-                0,
-                SystemPromptMessage(
-                    content=FIREWORKS_BLOCK_MODE_PROMPT.replace(
-                        "{{instructions}}", f"Please output a valid {response_format} object."
-                    ).replace("{{block}}", response_format)
-                ),
-            )
-            prompt_messages.append(AssistantPromptMessage(content=f"\n```{response_format}"))
-
-    def get_num_tokens(
-        self,
-        model: str,
-        credentials: dict,
-        prompt_messages: list[PromptMessage],
-        tools: Optional[list[PromptMessageTool]] = None,
-    ) -> int:
-        """
-        Get number of tokens for given prompt messages
-
-        :param model: model name
-        :param credentials: model credentials
-        :param prompt_messages: prompt messages
-        :param tools: tools for tool calling
-        :return:
-        """
-        return self._num_tokens_from_messages(model, prompt_messages, tools)
-
-    def validate_credentials(self, model: str, credentials: dict) -> None:
-        """
-        Validate model credentials
-
-        :param model: model name
-        :param credentials: model credentials
-        :return:
-        """
-        try:
-            credentials_kwargs = self._to_credential_kwargs(credentials)
-            client = OpenAI(**credentials_kwargs)
-
-            client.chat.completions.create(
-                messages=[{"role": "user", "content": "ping"}], model=model, temperature=0, max_tokens=10, stream=False
-            )
-        except Exception as e:
-            raise CredentialsValidateFailedError(str(e))
-
-    def _chat_generate(
-        self,
-        model: str,
-        credentials: dict,
-        prompt_messages: list[PromptMessage],
-        model_parameters: dict,
-        tools: Optional[list[PromptMessageTool]] = None,
-        stop: Optional[list[str]] = None,
-        stream: bool = True,
-        user: Optional[str] = None,
-    ) -> Union[LLMResult, Generator]:
-        credentials_kwargs = self._to_credential_kwargs(credentials)
-        client = OpenAI(**credentials_kwargs)
-
-        extra_model_kwargs = {}
-
-        if tools:
-            extra_model_kwargs["functions"] = [
-                {"name": tool.name, "description": tool.description, "parameters": tool.parameters} for tool in tools
-            ]
-
-        if stop:
-            extra_model_kwargs["stop"] = stop
-
-        if user:
-            extra_model_kwargs["user"] = user
-
-        # chat model
-        response = client.chat.completions.create(
-            messages=[self._convert_prompt_message_to_dict(m) for m in prompt_messages],
-            model=model,
-            stream=stream,
-            **model_parameters,
-            **extra_model_kwargs,
-        )
-
-        if stream:
-            return self._handle_chat_generate_stream_response(model, credentials, response, prompt_messages, tools)
-        return self._handle_chat_generate_response(model, credentials, response, prompt_messages, tools)
-
-    def _handle_chat_generate_response(
-        self,
-        model: str,
-        credentials: dict,
-        response: ChatCompletion,
-        prompt_messages: list[PromptMessage],
-        tools: Optional[list[PromptMessageTool]] = None,
-    ) -> LLMResult:
-        """
-        Handle llm chat response
-
-        :param model: model name
-        :param credentials: credentials
-        :param response: response
-        :param prompt_messages: prompt messages
-        :param tools: tools for tool calling
-        :return: llm response
-        """
-        assistant_message = response.choices[0].message
-        # assistant_message_tool_calls = assistant_message.tool_calls
-        assistant_message_function_call = assistant_message.function_call
-
-        # extract tool calls from response
-        # tool_calls = self._extract_response_tool_calls(assistant_message_tool_calls)
-        function_call = self._extract_response_function_call(assistant_message_function_call)
-        tool_calls = [function_call] if function_call else []
-
-        # transform assistant message to prompt message
-        assistant_prompt_message = AssistantPromptMessage(content=assistant_message.content, tool_calls=tool_calls)
-
-        # calculate num tokens
-        if response.usage:
-            # transform usage
-            prompt_tokens = response.usage.prompt_tokens
-            completion_tokens = response.usage.completion_tokens
-        else:
-            # calculate num tokens
-            prompt_tokens = self._num_tokens_from_messages(model, prompt_messages, tools)
-            completion_tokens = self._num_tokens_from_messages(model, [assistant_prompt_message])
-
-        # transform usage
-        usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
-
-        # transform response
-        response = LLMResult(
-            model=response.model,
-            prompt_messages=prompt_messages,
-            message=assistant_prompt_message,
-            usage=usage,
-            system_fingerprint=response.system_fingerprint,
-        )
-
-        return response
-
-    def _handle_chat_generate_stream_response(
-        self,
-        model: str,
-        credentials: dict,
-        response: Stream[ChatCompletionChunk],
-        prompt_messages: list[PromptMessage],
-        tools: Optional[list[PromptMessageTool]] = None,
-    ) -> Generator:
-        """
-        Handle llm chat stream response
-
-        :param model: model name
-        :param response: response
-        :param prompt_messages: prompt messages
-        :param tools: tools for tool calling
-        :return: llm response chunk generator
-        """
-        full_assistant_content = ""
-        delta_assistant_message_function_call_storage: Optional[ChoiceDeltaFunctionCall] = None
-        prompt_tokens = 0
-        completion_tokens = 0
-        final_tool_calls = []
-        final_chunk = LLMResultChunk(
-            model=model,
-            prompt_messages=prompt_messages,
-            delta=LLMResultChunkDelta(
-                index=0,
-                message=AssistantPromptMessage(content=""),
-            ),
-        )
-
-        for chunk in response:
-            if len(chunk.choices) == 0:
-                if chunk.usage:
-                    # calculate num tokens
-                    prompt_tokens = chunk.usage.prompt_tokens
-                    completion_tokens = chunk.usage.completion_tokens
-                continue
-
-            delta = chunk.choices[0]
-            has_finish_reason = delta.finish_reason is not None
-
-            if (
-                not has_finish_reason
-                and (delta.delta.content is None or delta.delta.content == "")
-                and delta.delta.function_call is None
-            ):
-                continue
-
-            # assistant_message_tool_calls = delta.delta.tool_calls
-            assistant_message_function_call = delta.delta.function_call
-
-            # extract tool calls from response
-            if delta_assistant_message_function_call_storage is not None:
-                # handle process of stream function call
-                if assistant_message_function_call:
-                    # message has not ended ever
-                    delta_assistant_message_function_call_storage.arguments += assistant_message_function_call.arguments
-                    continue
-                else:
-                    # message has ended
-                    assistant_message_function_call = delta_assistant_message_function_call_storage
-                    delta_assistant_message_function_call_storage = None
-            else:
-                if assistant_message_function_call:
-                    # start of stream function call
-                    delta_assistant_message_function_call_storage = assistant_message_function_call
-                    if delta_assistant_message_function_call_storage.arguments is None:
-                        delta_assistant_message_function_call_storage.arguments = ""
-                    if not has_finish_reason:
-                        continue
-
-            # tool_calls = self._extract_response_tool_calls(assistant_message_tool_calls)
-            function_call = self._extract_response_function_call(assistant_message_function_call)
-            tool_calls = [function_call] if function_call else []
-            if tool_calls:
-                final_tool_calls.extend(tool_calls)
-
-            # transform assistant message to prompt message
-            assistant_prompt_message = AssistantPromptMessage(content=delta.delta.content or "", tool_calls=tool_calls)
-
-            full_assistant_content += delta.delta.content or ""
-
-            if has_finish_reason:
-                final_chunk = LLMResultChunk(
-                    model=chunk.model,
-                    prompt_messages=prompt_messages,
-                    system_fingerprint=chunk.system_fingerprint,
-                    delta=LLMResultChunkDelta(
-                        index=delta.index,
-                        message=assistant_prompt_message,
-                        finish_reason=delta.finish_reason,
-                    ),
-                )
-            else:
-                yield LLMResultChunk(
-                    model=chunk.model,
-                    prompt_messages=prompt_messages,
-                    system_fingerprint=chunk.system_fingerprint,
-                    delta=LLMResultChunkDelta(
-                        index=delta.index,
-                        message=assistant_prompt_message,
-                    ),
-                )
-
-        if not prompt_tokens:
-            prompt_tokens = self._num_tokens_from_messages(model, prompt_messages, tools)
-
-        if not completion_tokens:
-            full_assistant_prompt_message = AssistantPromptMessage(
-                content=full_assistant_content, tool_calls=final_tool_calls
-            )
-            completion_tokens = self._num_tokens_from_messages(model, [full_assistant_prompt_message])
-
-        # transform usage
-        usage = self._calc_response_usage(model, credentials, prompt_tokens, completion_tokens)
-        final_chunk.delta.usage = usage
-
-        yield final_chunk
-
-    def _extract_response_tool_calls(
-        self, response_tool_calls: list[ChatCompletionMessageToolCall | ChoiceDeltaToolCall]
-    ) -> list[AssistantPromptMessage.ToolCall]:
-        """
-        Extract tool calls from response
-
-        :param response_tool_calls: response tool calls
-        :return: list of tool calls
-        """
-        tool_calls = []
-        if response_tool_calls:
-            for response_tool_call in response_tool_calls:
-                function = AssistantPromptMessage.ToolCall.ToolCallFunction(
-                    name=response_tool_call.function.name, arguments=response_tool_call.function.arguments
-                )
-
-                tool_call = AssistantPromptMessage.ToolCall(
-                    id=response_tool_call.id, type=response_tool_call.type, function=function
-                )
-                tool_calls.append(tool_call)
-
-        return tool_calls
-
-    def _extract_response_function_call(
-        self, response_function_call: FunctionCall | ChoiceDeltaFunctionCall
-    ) -> AssistantPromptMessage.ToolCall:
-        """
-        Extract function call from response
-
-        :param response_function_call: response function call
-        :return: tool call
-        """
-        tool_call = None
-        if response_function_call:
-            function = AssistantPromptMessage.ToolCall.ToolCallFunction(
-                name=response_function_call.name, arguments=response_function_call.arguments
-            )
-
-            tool_call = AssistantPromptMessage.ToolCall(
-                id=response_function_call.name, type="function", function=function
-            )
-
-        return tool_call
-
-    def _convert_prompt_message_to_dict(self, message: PromptMessage) -> dict:
-        """
-        Convert PromptMessage to dict for Fireworks API
-        """
-        if isinstance(message, UserPromptMessage):
-            message = cast(UserPromptMessage, message)
-            if isinstance(message.content, str):
-                message_dict = {"role": "user", "content": message.content}
-            else:
-                sub_messages = []
-                for message_content in message.content:
-                    if message_content.type == PromptMessageContentType.TEXT:
-                        message_content = cast(TextPromptMessageContent, message_content)
-                        sub_message_dict = {"type": "text", "text": message_content.data}
-                        sub_messages.append(sub_message_dict)
-                    elif message_content.type == PromptMessageContentType.IMAGE:
-                        message_content = cast(ImagePromptMessageContent, message_content)
-                        sub_message_dict = {
-                            "type": "image_url",
-                            "image_url": {"url": message_content.data, "detail": message_content.detail.value},
-                        }
-                        sub_messages.append(sub_message_dict)
-
-                message_dict = {"role": "user", "content": sub_messages}
-        elif isinstance(message, AssistantPromptMessage):
-            message = cast(AssistantPromptMessage, message)
-            message_dict = {"role": "assistant", "content": message.content}
-            if message.tool_calls:
-                # message_dict["tool_calls"] = [tool_call.dict() for tool_call in
-                #                               message.tool_calls]
-                function_call = message.tool_calls[0]
-                message_dict["function_call"] = {
-                    "name": function_call.function.name,
-                    "arguments": function_call.function.arguments,
-                }
-        elif isinstance(message, SystemPromptMessage):
-            message = cast(SystemPromptMessage, message)
-            message_dict = {"role": "system", "content": message.content}
-        elif isinstance(message, ToolPromptMessage):
-            message = cast(ToolPromptMessage, message)
-            # message_dict = {
-            #     "role": "tool",
-            #     "content": message.content,
-            #     "tool_call_id": message.tool_call_id
-            # }
-            message_dict = {"role": "function", "content": message.content, "name": message.tool_call_id}
-        else:
-            raise ValueError(f"Got unknown type {message}")
-
-        if message.name:
-            message_dict["name"] = message.name
-
-        return message_dict
-
-    def _num_tokens_from_messages(
-        self,
-        model: str,
-        messages: list[PromptMessage],
-        tools: Optional[list[PromptMessageTool]] = None,
-        credentials: dict = None,
-    ) -> int:
-        """
-        Approximate num tokens with GPT2 tokenizer.
-        """
-
-        tokens_per_message = 3
-        tokens_per_name = 1
-
-        num_tokens = 0
-        messages_dict = [self._convert_prompt_message_to_dict(m) for m in messages]
-        for message in messages_dict:
-            num_tokens += tokens_per_message
-            for key, value in message.items():
-                # Cast str(value) in case the message value is not a string
-                # This occurs with function messages
-                # TODO: The current token calculation method for the image type is not implemented,
-                #  which need to download the image and then get the resolution for calculation,
-                #  and will increase the request delay
-                if isinstance(value, list):
-                    text = ""
-                    for item in value:
-                        if isinstance(item, dict) and item["type"] == "text":
-                            text += item["text"]
-
-                    value = text
-
-                if key == "tool_calls":
-                    for tool_call in value:
-                        for t_key, t_value in tool_call.items():
-                            num_tokens += self._get_num_tokens_by_gpt2(t_key)
-                            if t_key == "function":
-                                for f_key, f_value in t_value.items():
-                                    num_tokens += self._get_num_tokens_by_gpt2(f_key)
-                                    num_tokens += self._get_num_tokens_by_gpt2(f_value)
-                            else:
-                                num_tokens += self._get_num_tokens_by_gpt2(t_key)
-                                num_tokens += self._get_num_tokens_by_gpt2(t_value)
-                else:
-                    num_tokens += self._get_num_tokens_by_gpt2(str(value))
-
-                if key == "name":
-                    num_tokens += tokens_per_name
-
-        # every reply is primed with <im_start>assistant
-        num_tokens += 3
-
-        if tools:
-            num_tokens += self._num_tokens_for_tools(tools)
-
-        return num_tokens
-
-    def _num_tokens_for_tools(self, tools: list[PromptMessageTool]) -> int:
-        """
-        Calculate num tokens for tool calling with tiktoken package.
-
-        :param tools: tools for tool calling
-        :return: number of tokens
-        """
-        num_tokens = 0
-        for tool in tools:
-            num_tokens += self._get_num_tokens_by_gpt2("type")
-            num_tokens += self._get_num_tokens_by_gpt2("function")
-            num_tokens += self._get_num_tokens_by_gpt2("function")
-
-            # calculate num tokens for function object
-            num_tokens += self._get_num_tokens_by_gpt2("name")
-            num_tokens += self._get_num_tokens_by_gpt2(tool.name)
-            num_tokens += self._get_num_tokens_by_gpt2("description")
-            num_tokens += self._get_num_tokens_by_gpt2(tool.description)
-            parameters = tool.parameters
-            num_tokens += self._get_num_tokens_by_gpt2("parameters")
-            if "title" in parameters:
-                num_tokens += self._get_num_tokens_by_gpt2("title")
-                num_tokens += self._get_num_tokens_by_gpt2(parameters.get("title"))
-            num_tokens += self._get_num_tokens_by_gpt2("type")
-            num_tokens += self._get_num_tokens_by_gpt2(parameters.get("type"))
-            if "properties" in parameters:
-                num_tokens += self._get_num_tokens_by_gpt2("properties")
-                for key, value in parameters.get("properties").items():
-                    num_tokens += self._get_num_tokens_by_gpt2(key)
-                    for field_key, field_value in value.items():
-                        num_tokens += self._get_num_tokens_by_gpt2(field_key)
-                        if field_key == "enum":
-                            for enum_field in field_value:
-                                num_tokens += 3
-                                num_tokens += self._get_num_tokens_by_gpt2(enum_field)
-                        else:
-                            num_tokens += self._get_num_tokens_by_gpt2(field_key)
-                            num_tokens += self._get_num_tokens_by_gpt2(str(field_value))
-            if "required" in parameters:
-                num_tokens += self._get_num_tokens_by_gpt2("required")
-                for required_field in parameters["required"]:
-                    num_tokens += 3
-                    num_tokens += self._get_num_tokens_by_gpt2(required_field)
-
-        return num_tokens