youngkingdom/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-04-19 18:27:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: support dense_vector from ES fields response (ES 9.x compatibility) (#13972)

Browse Source 
fix: support dense_vector from ES fields response (ES 9.x compatibility)

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Configuration Chore (non-breaking change which updates
configuration)


## Summary by CodeRabbit

* **Bug Fixes**
* More accurate handling and unwrapping of dense-vector fields so
returned values have correct shapes.
* Field selection reliably limits returned data and falls back to
alternate result locations when needed.
* Use of consistent result IDs and tolerant handling when score values
are missing.

* **Chores / Configuration**
* Increased build memory and adjusted build-time flags for the frontend
build.
* Simplified runtime model/GPU checks and removed an automated runtime
GPU-install attempt.

* **Build Fixes**
* `web/vite.config.ts`: make `build.minify` and `build.sourcemap`
respect `VITE_MINIFY` and `VITE_BUILD_SOURCEMAP` env vars from
Dockerfile instead of hardcoding `terser` and `true`.

* **Environment**
* Allow stack version override and default the runtime image tag to
"latest".

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

* **Bug Fixes**
* Correct unwrapping of dense-vector fields and reliable field selection
with fallback locations.
* Consistent use of hit-level IDs and tolerant handling when score
values are missing.

* **Chores / Configuration**
* Increased frontend build memory and added build-time minify/sourcemap
flags; build minification and sourcemap now configurable.
* Removed runtime GPU detection for model initialization; force CPU
initialization.

* **Environment**
* Allow stack version override and default runtime image tag to
"latest".

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Zhichang Yu
2026-04-09 17:44:13 +08:00
committed by GitHub
parent 107fe6cf90
commit b7744e053e
50 changed files with 142 additions and 124 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
Dockerfile
View File

@ -35,26 +35,14 @@ RUN --mount=type=cache,id=ragflow_apt,target=/var/cache/apt,sharing=locked \
apt update && \
apt --no-install-recommends install -y ca-certificates; \
if [ "$NEED_MIRROR" == "1" ]; then \
sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /etc/apt/sources.list.d/ubuntu.sources; \
sed -i 's|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /etc/apt/sources.list.d/ubuntu.sources; \
sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.aliyun.com/ubuntu|g' /etc/apt/sources.list.d/ubuntu.sources; \
sed -i 's|http://security.ubuntu.com/ubuntu|https://mirrors.aliyun.com/ubuntu|g' /etc/apt/sources.list.d/ubuntu.sources; \
fi; \
rm -f /etc/apt/apt.conf.d/docker-clean && \
echo 'Binary::apt::APT::Keep-Downloaded-Packages "true";' > /etc/apt/apt.conf.d/keep-cache && \
chmod 1777 /tmp && \
apt update && \
apt install -y build-essential && \
apt install -y libglib2.0-0 libglx-mesa0 libgl1 && \
apt install -y pkg-config libicu-dev libgdiplus && \
apt install -y default-jdk && \
apt install -y libatk-bridge2.0-0 && \
apt install -y libpython3-dev libgtk-4-1 libnss3 xdg-utils libgbm-dev && \
apt install -y libjemalloc-dev && \
apt install -y gnupg unzip curl wget git vim less && \
apt install -y ghostscript && \
apt install -y pandoc && \
apt install -y texlive && \
apt install -y fonts-freefont-ttf fonts-noto-cjk && \
apt install -y postgresql-client
apt install -y build-essential libglib2.0-0 libglx-mesa0 libgl1 pkg-config libicu-dev libgdiplus default-jdk libatk-bridge2.0-0 libpython3-dev libgtk-4-1 libnss3 xdg-utils libgbm-dev libjemalloc-dev gnupg unzip curl wget git vim less ghostscript pandoc texlive fonts-freefont-ttf fonts-noto-cjk postgresql-client
# Download resource from GitHub to /usr/share/infinity
RUN mkdir -p /usr/share/infinity/resource && \
@ -165,8 +153,8 @@ RUN --mount=type=cache,id=ragflow_uv,target=/root/.cache/uv,sharing=locked \
COPY web web
COPY docs docs
RUN --mount=type=cache,id=ragflow_npm,target=/root/.npm,sharing=locked \
export NODE_OPTIONS="--max-old-space-size=4096" && \
cd web && npm install && npm run build
cd web && NODE_OPTIONS="--max-old-space-size=8192" npm install && \
NODE_OPTIONS="--max-old-space-size=8192" VITE_BUILD_SOURCEMAP=false VITE_MINIFY=esbuild npm run build
COPY .git /ragflow/.git

12
deepdoc/parser/pdf_parser.py
View File

@ -38,7 +38,6 @@ from sklearn.cluster import KMeans
from sklearn.metrics import silhouette_score
from common.file_utils import get_project_base_directory
from common.misc_utils import pip_install_torch
from deepdoc.vision import OCR, AscendLayoutRecognizer, LayoutRecognizer, Recognizer, TableStructureRecognizer
from rag.nlp import rag_tokenizer
from rag.prompts.generator import vision_llm_describe_prompt
@ -91,14 +90,9 @@ class RAGFlowPdfParser:
self.tbl_det = TableStructureRecognizer()
self.updown_cnt_mdl = xgb.Booster()
try:
pip_install_torch()
import torch.cuda
if torch.cuda.is_available():
self.updown_cnt_mdl.set_param({"device": "cuda"})
except Exception:
logging.info("No torch found.")
# xgboost model is very small; using CPU explicitly
self.updown_cnt_mdl.set_param({"device": "cpu"})
logging.info("updown_cnt_mdl initialized on CPU")
try:
model_dir = os.path.join(get_project_base_directory(), "rag/res/deepdoc")
self.updown_cnt_mdl.load_model(os.path.join(model_dir, "updown_concat_xgb.model"))

4
docker/.env
View File

@ -28,7 +28,7 @@ DEVICE=${DEVICE:-cpu}
COMPOSE_PROFILES=${DOC_ENGINE},${DEVICE}
# The version of Elasticsearch.
STACK_VERSION=8.11.3
STACK_VERSION=${STACK_VERSION:-8.11.3}
# The hostname where the Elasticsearch service is exposed
ES_HOST=es01
@ -159,7 +159,7 @@ GO_ADMIN_PORT=9383
API_PROXY_SCHEME=python # use pure python server deployment
# The RAGFlow Docker image to download. v0.22+ doesn't include embedding models.
RAGFLOW_IMAGE=infiniflow/ragflow:v0.24.0
RAGFLOW_IMAGE=infiniflow/ragflow:latest
# If you cannot download the RAGFlow Docker image:
# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:v0.24.0

2
rag/flow/parser/parser.py
View File

@ -762,7 +762,7 @@ class Parser(ProcessBase):
sections = [line.strip() for line in content.splitlines() if line and line.strip()]
if conf.get("remove_toc"):
sections = remove_toc_word(sections, outlines)
sections = remove_toc_word(sections, [])
if conf.get("output_format") == "json":
self.set_output(

4
rag/graphrag/search.py
View File

@ -91,7 +91,7 @@ class KGSearch(Dealer):
es_res = self.dataStore.get_fields(es_res, ["content_with_weight", "_score", "from_entity_kwd", "to_entity_kwd",
"weight_int"])
for _, ent in es_res.items():
if get_float(ent["_score"]) < sim_thr:
if get_float(ent.get("_score", 0)) < sim_thr:
continue
f, t = sorted([ent["from_entity_kwd"], ent["to_entity_kwd"]])
if isinstance(f, list):
@ -99,7 +99,7 @@ class KGSearch(Dealer):
if isinstance(t, list):
t = t[0]
res[(f, t)] = {
"sim": get_float(ent["_score"]),
"sim": get_float(ent.get("_score", 0)),
"pagerank": get_float(ent.get("weight_int", 0)),
"description": ent["content_with_weight"]
}

90
rag/svr/sync_data_source.py
View File

@ -278,7 +278,7 @@ class _BlobLikeBase(SyncBase):
)
)
begin_info = (
_begin_info = (
"totally"
if task["reindex"] == "1" or not task["poll_range_start"]
else "from {}".format(task["poll_range_start"])
@ -289,7 +289,7 @@ class _BlobLikeBase(SyncBase):
bucket_type,
self.conf["bucket_name"],
self.conf.get("prefix", ""),
begin_info,
_begin_info,
)
)
return document_batch_generator
@ -377,10 +377,10 @@ class Confluence(SyncBase):
# Determine the time range for synchronization based on reindex or poll_range_start
if task["reindex"] == "1" or not task["poll_range_start"]:
start_time = 0.0
begin_info = "totally"
_begin_info = "totally"
else:
start_time = task["poll_range_start"].timestamp()
begin_info = f"from {task['poll_range_start']}"
_begin_info = f"from {task['poll_range_start']}"
end_time = datetime.now(timezone.utc).timestamp()
@ -442,7 +442,7 @@ class Notion(SyncBase):
datetime.now(timezone.utc).timestamp())
)
begin_info = "totally" if task["reindex"] == "1" or not task["poll_range_start"] else "from {}".format(
_begin_info = "totally" if task["reindex"] == "1" or not task["poll_range_start"] else "from {}".format(
task["poll_range_start"])
self.log_connection("Notion", f"root({self.conf['root_page_id']})", task)
return document_generator
@ -470,7 +470,7 @@ class Discord(SyncBase):
datetime.now(timezone.utc).timestamp())
)
begin_info = "totally" if task["reindex"] == "1" or not task["poll_range_start"] else "from {}".format(
_begin_info = "totally" if task["reindex"] == "1" or not task["poll_range_start"] else "from {}".format(
task["poll_range_start"])
self.log_connection("Discord", f"servers({server_ids}), channel({channel_names})", task)
return document_generator
@ -516,7 +516,7 @@ class Gmail(SyncBase):
if task["reindex"] == "1" or not task.get("poll_range_start"):
start_time = None
end_time = None
begin_info = "totally"
_begin_info = "totally"
document_generator = self.connector.load_from_state()
else:
poll_start = task["poll_range_start"]
@ -524,12 +524,12 @@ class Gmail(SyncBase):
if poll_start is None:
start_time = None
end_time = None
begin_info = "totally"
_begin_info = "totally"
document_generator = self.connector.load_from_state()
else:
start_time = poll_start.timestamp()
end_time = datetime.now(timezone.utc).timestamp()
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
document_generator = self.connector.poll_source(start_time, end_time)
try:
@ -549,13 +549,13 @@ class Dropbox(SyncBase):
if task["reindex"] == "1" or not task["poll_range_start"]:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
poll_start = task["poll_range_start"]
document_generator = self.connector.poll_source(
poll_start.timestamp(), datetime.now(timezone.utc).timestamp()
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
self.log_connection("Dropbox", "workspace", task)
return document_generator
@ -588,10 +588,10 @@ class GoogleDrive(SyncBase):
if task["reindex"] == "1" or not task["poll_range_start"]:
start_time = 0.0
begin_info = "totally"
_begin_info = "totally"
else:
start_time = task["poll_range_start"].timestamp()
begin_info = f"from {task['poll_range_start']}"
_begin_info = f"from {task['poll_range_start']}"
end_time = datetime.now(timezone.utc).timestamp()
raw_batch_size = self.conf.get("sync_batch_size") or self.conf.get("batch_size") or INDEX_BATCH_SIZE
@ -682,10 +682,10 @@ class Jira(SyncBase):
if task["reindex"] == "1" or not task["poll_range_start"]:
start_time = 0.0
begin_info = "totally"
_begin_info = "totally"
else:
start_time = task["poll_range_start"].timestamp()
begin_info = f"from {task['poll_range_start']}"
_begin_info = f"from {task['poll_range_start']}"
end_time = datetime.now(timezone.utc).timestamp()
@ -788,12 +788,12 @@ class WebDAV(SyncBase):
if task["reindex"] == "1" or not task["poll_range_start"]:
document_batch_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
start_ts = task["poll_range_start"].timestamp()
end_ts = datetime.now(timezone.utc).timestamp()
document_batch_generator = self.connector.poll_source(start_ts, end_ts)
begin_info = "from {}".format(task["poll_range_start"])
_begin_info = "from {}".format(task["poll_range_start"])
self.log_connection("WebDAV", f"{self.conf['base_url']}(path: {self.conf.get('remote_path', '/')})", task)
@ -820,13 +820,13 @@ class Moodle(SyncBase):
if task["reindex"] == "1" or poll_start is None:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp(),
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
self.log_connection("Moodle", self.conf["moodle_url"], task)
return document_generator
@ -860,13 +860,13 @@ class BOX(SyncBase):
if task["reindex"] == "1" or poll_start is None:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp(),
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
self.log_connection("Box", f"folder_id({self.conf['folder_id']})", task)
return document_generator
@ -896,13 +896,13 @@ class Airtable(SyncBase):
if task.get("reindex") == "1" or poll_start is None:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp(),
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
self.log_connection(
"Airtable",
@ -931,18 +931,18 @@ class Asana(SyncBase):
if task.get("reindex") == "1" or not task.get("poll_range_start"):
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
poll_start = task.get("poll_range_start")
if poll_start is None:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp(),
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
self.log_connection(
"Asana",
@ -979,10 +979,10 @@ class Github(SyncBase):
file_list = None
if task.get("reindex") == "1" or not task.get("poll_range_start"):
start_time = datetime.fromtimestamp(0, tz=timezone.utc)
begin_info = "totally"
_begin_info = "totally"
else:
start_time = task.get("poll_range_start")
begin_info = f"from {start_time}"
_begin_info = f"from {start_time}"
if self.conf.get("sync_deleted_files"):
file_list = []
for slim_batch in self.connector.retrieve_all_slim_docs_perm_sync():
@ -1041,10 +1041,10 @@ class IMAP(SyncBase):
end_time = datetime.now(timezone.utc).timestamp()
if task["reindex"] == "1" or not task["poll_range_start"]:
start_time = end_time - self.conf.get("poll_range",30) * 24 * 60 * 60
begin_info = "totally"
_begin_info = "totally"
else:
start_time = task["poll_range_start"].timestamp()
begin_info = f"from {task['poll_range_start']}"
_begin_info = f"from {task['poll_range_start']}"
raw_batch_size = self.conf.get("sync_batch_size") or self.conf.get("batch_size") or INDEX_BATCH_SIZE
try:
batch_size = int(raw_batch_size)
@ -1101,10 +1101,10 @@ class Zendesk(SyncBase):
end_time = datetime.now(timezone.utc).timestamp()
if task["reindex"] == "1" or not task.get("poll_range_start"):
start_time = 0
begin_info = "totally"
_begin_info = "totally"
else:
start_time = task["poll_range_start"].timestamp()
begin_info = f"from {task['poll_range_start']}"
_begin_info = f"from {task['poll_range_start']}"
raw_batch_size = (
self.conf.get("sync_batch_size")
@ -1193,18 +1193,18 @@ class Gitlab(SyncBase):
if task["reindex"] == "1" or not task["poll_range_start"]:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
poll_start = task["poll_range_start"]
if poll_start is None:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp()
)
begin_info = "from {}".format(poll_start)
_begin_info = "from {}".format(poll_start)
self.log_connection("Gitlab", f"({self.conf['project_name']})", task)
return document_generator
@ -1228,10 +1228,10 @@ class Bitbucket(SyncBase):
if task["reindex"] == "1" or not task["poll_range_start"]:
start_time = datetime.fromtimestamp(0, tz=timezone.utc)
begin_info = "totally"
_begin_info = "totally"
else:
start_time = task.get("poll_range_start")
begin_info = f"from {start_time}"
_begin_info = f"from {start_time}"
end_time = datetime.now(timezone.utc)
@ -1284,13 +1284,13 @@ class SeaFile(SyncBase):
poll_start = task.get("poll_range_start")
if task["reindex"] == "1" or poll_start is None:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp(),
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
scope = conf.get("sync_scope", "account")
extra = ""
@ -1328,13 +1328,13 @@ class DingTalkAITable(SyncBase):
if task.get("reindex") == "1" or poll_start is None:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp(),
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
self.log_connection(
"DingTalk AI Table",
@ -1371,14 +1371,14 @@ class MySQL(SyncBase):
if task["reindex"] == "1" or not task["poll_range_start"]:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
poll_start = task["poll_range_start"]
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp()
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
self.log_connection("MySQL", f"{self.conf.get('host')}:{self.conf.get('database')}", task)
return document_generator
@ -1410,14 +1410,14 @@ class PostgreSQL(SyncBase):
if task["reindex"] == "1" or not task["poll_range_start"]:
document_generator = self.connector.load_from_state()
begin_info = "totally"
_begin_info = "totally"
else:
poll_start = task["poll_range_start"]
document_generator = self.connector.poll_source(
poll_start.timestamp(),
datetime.now(timezone.utc).timestamp()
)
begin_info = f"from {poll_start}"
_begin_info = f"from {poll_start}"
self.log_connection("PostgreSQL", f"{self.conf.get('host')}:{self.conf.get('database')}", task)
return document_generator

33
rag/utils/es_conn.py
View File

@ -253,7 +253,18 @@ class ESConnection(ESConnectionBase):
if limit > 0 and not use_search_after:
s = s[offset:offset + limit]
# Filter _source to only requested fields for efficiency, and add vector
# fields to "fields" param so they appear in hit.fields when ES 9.x
# exclude_source_vectors is enabled (dense_vector not in _source).
if select_fields:
s = s.source(select_fields)
q = s.to_dict()
# ES 9.x: dense_vector fields excluded from _source; request them via fields.
# Note: knn does NOT have a "fields" parameter - adding it inside the knn
# object causes BadRequestError on ES 9.x. We add "fields" at top level.
vector_fields = [f for f in (select_fields or []) if f.endswith("_vec")]
if vector_fields:
q["fields"] = vector_fields
self.logger.debug(f"ESConnection.search {str(index_names)} query: " + json.dumps(q))
for i in range(ATTEMPT_TIME):
@ -565,8 +576,24 @@ class ESConnection(ESConnectionBase):
res_fields = {}
if not fields:
return {}
for d in self._get_source(res):
m = {n: d.get(n) for n in fields if d.get(n) is not None}
hits = res.get("hits", {}).get("hits", [])
for hit in hits:
doc_id = hit.get("_id")
d = hit.get("_source", {})
# Also extract fields from ES "fields" response (used by dense_vector in ES 9.x)
hit_fields = hit.get("fields", {})
m = {}
for n in fields:
# First check _source
if d.get(n) is not None:
m[n] = d.get(n)
# Then check fields (ES 9.x stores dense_vector here, not in _source)
elif n in hit_fields:
vals = hit_fields[n]
# ES fields response wraps dense_vector in 2 levels: [[v1,v2,...]] -> [v1,v2,...]
if isinstance(vals, list) and len(vals) == 1:
vals = vals[0]
m[n] = vals
for n, v in m.items():
if isinstance(v, list):
m[n] = v
@ -580,5 +607,5 @@ class ESConnection(ESConnectionBase):
# m[n] = remove_redundant_spaces(m[n])
if m:
res_fields[d["id"]] = m
res_fields[doc_id] = m
return res_fields

2
test/testcases/test_web_api/conftest.py
View File

@ -18,7 +18,7 @@ from time import sleep
from ragflow_sdk import RAGFlow
from configs import HOST_ADDRESS, VERSION
import pytest
from common import (
from test_common import (
batch_add_chunks,
batch_create_datasets,
bulk_upload_documents,

2
test/testcases/test_web_api/test_api_app/test_api_tokens.py
View File

@ -14,7 +14,7 @@
# limitations under the License.
#
import pytest
from common import api_new_token, api_rm_token, api_stats, api_token_list, batch_create_chats
from test_common import api_new_token, api_rm_token, api_stats, api_token_list, batch_create_chats
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_chunk_app/conftest.py
View File

@ -18,7 +18,7 @@
from time import sleep
import pytest
from common import batch_add_chunks, delete_chunks, list_chunks, list_documents, parse_documents
from test_common import batch_add_chunks, delete_chunks, list_chunks, list_documents, parse_documents
from utils import wait_for

2
test/testcases/test_web_api/test_chunk_app/test_create_chunk.py
View File

@ -16,7 +16,7 @@
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from common import add_chunk, delete_document, get_chunk, list_chunks
from test_common import add_chunk, delete_document, get_chunk, list_chunks
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_chunk_app/test_list_chunks.py
View File

@ -17,7 +17,7 @@ import os
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from common import batch_add_chunks, list_chunks, update_chunk
from test_common import batch_add_chunks, list_chunks, update_chunk
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_chunk_app/test_retrieval_chunks.py
View File

@ -17,7 +17,7 @@ import os
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from common import retrieval_chunks
from test_common import retrieval_chunks
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_chunk_app/test_rm_chunks.py
View File

@ -16,7 +16,7 @@
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from common import batch_add_chunks, delete_chunks, list_chunks
from test_common import batch_add_chunks, delete_chunks, list_chunks
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_chunk_app/test_update_chunk.py
View File

@ -20,7 +20,7 @@ from random import randint
from time import sleep
import pytest
from common import delete_document, list_chunks, update_chunk
from test_common import delete_document, list_chunks, update_chunk
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

4
test/testcases/test_web_api/test_chunk_feedback/__init__.py
View File

@ -13,6 +13,4 @@
# See the License for the specific language governing permissions and
# limitations under the License.
from rag.flow.chunker.token_chunker import TokenChunker, TokenChunkerParam
__all__ = ["TokenChunker", "TokenChunkerParam"]
__all__ = []

0
test/testcases/test_web_api/common.py → test/testcases/test_web_api/test_common.py
View File

2
test/testcases/test_web_api/test_document_app/conftest.py
View File

@ -21,7 +21,7 @@ from pathlib import Path
from types import ModuleType, SimpleNamespace
import pytest
from common import bulk_upload_documents, delete_document, list_documents
from test_common import bulk_upload_documents, delete_document, list_documents
class _DummyManager:

2
test/testcases/test_web_api/test_document_app/test_create_document.py
View File

@ -19,7 +19,7 @@ from types import SimpleNamespace
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from test_web_api.common import create_document, list_datasets
from test_common import create_document, list_datasets
from configs import DOCUMENT_NAME_LIMIT, INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth
from utils.file_utils import create_txt_file

2
test/testcases/test_web_api/test_document_app/test_document_metadata.py
View File

@ -17,7 +17,7 @@ import asyncio
from types import SimpleNamespace
import pytest
from common import (
from test_common import (
document_change_status,
document_filter,
document_infos,

2
test/testcases/test_web_api/test_document_app/test_list_documents.py
View File

@ -18,7 +18,7 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
from types import SimpleNamespace
import pytest
from common import list_documents
from test_common import list_documents
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth
from utils import is_sorted

2
test/testcases/test_web_api/test_document_app/test_paser_documents.py
View File

@ -18,7 +18,7 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
from types import SimpleNamespace
import pytest
from common import bulk_upload_documents, list_documents, parse_documents
from test_common import bulk_upload_documents, list_documents, parse_documents
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth
from utils import wait_for

2
test/testcases/test_web_api/test_document_app/test_rm_documents.py
View File

@ -17,7 +17,7 @@ import asyncio
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from common import bulk_upload_documents, delete_document, list_documents
from test_common import bulk_upload_documents, delete_document, list_documents
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_document_app/test_upload_documents.py
View File

@ -20,7 +20,7 @@ from types import ModuleType, SimpleNamespace
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from common import list_datasets, upload_documents
from test_common import list_datasets, upload_documents
from configs import DOCUMENT_NAME_LIMIT, INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth
from utils.file_utils import create_txt_file

2
test/testcases/test_web_api/test_kb_app/conftest.py
View File

@ -14,7 +14,7 @@
# limitations under the License.
#
import pytest
from common import batch_create_datasets, list_datasets, delete_datasets
from test_common import batch_create_datasets, list_datasets, delete_datasets
from libs.auth import RAGFlowWebApiAuth
from pytest import FixtureRequest
from ragflow_sdk import RAGFlow

2
test/testcases/test_web_api/test_kb_app/test_create_kb.py
View File

@ -16,7 +16,7 @@
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from common import create_dataset
from test_common import create_dataset
from configs import DATASET_NAME_LIMIT, INVALID_API_TOKEN
from hypothesis import example, given, settings
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_kb_app/test_detail_kb.py
View File

@ -14,7 +14,7 @@
# limitations under the License.
#
import pytest
from common import (
from test_common import (
detail_kb,
)
from configs import INVALID_API_TOKEN

2
test/testcases/test_web_api/test_kb_app/test_kb_pipeline_tasks.py
View File

@ -14,7 +14,7 @@
# limitations under the License.
#
import pytest
from test_web_api.common import (
from test_common import (
kb_delete_pipeline_logs,
kb_list_pipeline_dataset_logs,
kb_list_pipeline_logs,

2
test/testcases/test_web_api/test_kb_app/test_kb_tags_meta.py
View File

@ -16,7 +16,7 @@
import uuid
import pytest
from test_web_api.common import (
from test_common import (
delete_knowledge_graph,
kb_basic_info,
kb_get_meta,

2
test/testcases/test_web_api/test_kb_app/test_list_kbs.py
View File

@ -17,7 +17,7 @@ import json
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from common import list_datasets
from test_common import list_datasets
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth
from utils import is_sorted

2
test/testcases/test_web_api/test_kb_app/test_rm_kb.py
View File

@ -15,7 +15,7 @@
#
import pytest
from common import (
from test_common import (
list_datasets,
delete_datasets,
)

2
test/testcases/test_web_api/test_kb_app/test_update_kb.py
View File

@ -17,7 +17,7 @@ import os
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from test_web_api.common import update_dataset
from test_common import update_dataset
from configs import DATASET_NAME_LIMIT, INVALID_API_TOKEN
from hypothesis import HealthCheck, example, given, settings
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_llm_app/test_llm_list.py
View File

@ -14,7 +14,7 @@
# limitations under the License.
#
import pytest
from common import llm_factories, llm_list
from test_common import llm_factories, llm_list
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_memory_app/conftest.py
View File

@ -15,7 +15,7 @@
#
import pytest
import random
from test_web_api.common import create_memory, list_memory, delete_memory
from test_common import create_memory, list_memory, delete_memory
@pytest.fixture(scope="function")
def add_memory_func(request, WebApiAuth):

2
test/testcases/test_web_api/test_memory_app/test_create_memory.py
View File

@ -17,7 +17,7 @@ import random
import re
import pytest
from test_web_api.common import create_memory
from test_common import create_memory
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_memory_app/test_list_memory.py
View File

@ -16,7 +16,7 @@
from concurrent.futures import ThreadPoolExecutor, as_completed
import pytest
from test_web_api.common import list_memory, get_memory_config
from test_common import list_memory, get_memory_config
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_memory_app/test_rm_memory.py
View File

@ -14,7 +14,7 @@
# limitations under the License.
#
import pytest
from test_web_api.common import (list_memory, delete_memory)
from test_common import (list_memory, delete_memory)
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_memory_app/test_update_memory.py
View File

@ -16,7 +16,7 @@
import re
import pytest
from test_web_api.common import update_memory
from test_common import update_memory
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth
from utils import encode_avatar

2
test/testcases/test_web_api/test_message_app/conftest.py
View File

@ -18,7 +18,7 @@ import uuid
import pytest
import random
from test_web_api.common import create_memory, list_memory, add_message, delete_memory
from test_common import create_memory, list_memory, add_message, delete_memory
@pytest.fixture(scope="class")

2
test/testcases/test_web_api/test_message_app/test_add_message.py
View File

@ -17,7 +17,7 @@ import time
import uuid
import pytest
from test_web_api.common import list_memory_message, add_message
from test_common import list_memory_message, add_message
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_message_app/test_forget_message.py
View File

@ -16,7 +16,7 @@
import random
import pytest
import requests
from test_web_api.common import forget_message, list_memory_message, get_message_content
from test_common import forget_message, list_memory_message, get_message_content
from configs import HOST_ADDRESS, INVALID_API_TOKEN, VERSION
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_message_app/test_get_message_content.py
View File

@ -16,7 +16,7 @@
import random
import pytest
from test_web_api.common import get_message_content, get_recent_message
from test_common import get_message_content, get_recent_message
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_message_app/test_get_recent_message.py
View File

@ -16,7 +16,7 @@
import random
import pytest
from test_web_api.common import get_recent_message
from test_common import get_recent_message
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_message_app/test_list_message.py
View File

@ -17,7 +17,7 @@ import os
import random
import pytest
from test_web_api.common import list_memory_message
from test_common import list_memory_message
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_message_app/test_search_message.py
View File

@ -14,7 +14,7 @@
# limitations under the License.
#
import pytest
from test_web_api.common import search_message, list_memory_message
from test_common import search_message, list_memory_message
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_message_app/test_update_message_status.py
View File

@ -17,7 +17,7 @@ import random
import pytest
import requests
from test_web_api.common import update_message_status, list_memory_message, get_message_content
from test_common import update_message_status, list_memory_message, get_message_content
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth
from configs import HOST_ADDRESS, VERSION

2
test/testcases/test_web_api/test_plugin_app/test_llm_tools.py
View File

@ -19,7 +19,7 @@ from pathlib import Path
from types import ModuleType
import pytest
from common import plugin_llm_tools
from test_common import plugin_llm_tools
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_search_app/test_search_crud.py
View File

@ -16,7 +16,7 @@
import uuid
import pytest
from common import search_create, search_detail, search_list, search_rm, search_update
from test_common import search_create, search_detail, search_list, search_rm, search_update
from configs import INVALID_API_TOKEN
from libs.auth import RAGFlowWebApiAuth

2
test/testcases/test_web_api/test_system_app/test_system_basic.py
View File

@ -14,7 +14,7 @@
# limitations under the License.
#
import pytest
from common import (
from test_common import (
system_config,
system_delete_token,
system_new_token,

15
web/vite.config.ts
View File

@ -26,6 +26,17 @@ const inspectorBabelPlugin = (): import('vite').Plugin => ({
},
});
type MinifyValue = boolean | 'esbuild' | 'terser';
function resolveMinify(value: string | undefined): MinifyValue {
if (value === undefined) return 'terser';
const lower = value.toLowerCase();
if (lower === 'false') return false;
if (lower === 'esbuild') return 'esbuild';
if (lower === 'terser') return 'terser';
return 'terser';
}
// https://vitejs.dev/config/
export default defineConfig(({ mode }) => {
const env = loadEnv(mode, process.cwd(), '');
@ -229,7 +240,7 @@ export default defineConfig(({ mode }) => {
plugins: [],
treeshake: true,
},
minify: 'terser',
minify: resolveMinify(env.VITE_MINIFY),
terserOptions: {
compress: {
drop_console: true, // delete console
@ -246,7 +257,7 @@ export default defineConfig(({ mode }) => {
comments: false, // Delete comments
},
},
sourcemap: true,
sourcemap: env.VITE_BUILD_SOURCEMAP !== 'false',
cssCodeSplit: true,
target: 'es2015',
},