fix: file logs not displayed in dataset ingestion page (#14479)

### What problem does this PR solve?

## Summary

Fixed a bug where the **File Logs** tab in the dataset ingestion page
always showed "No logs" even after files were parsed successfully.

## Root Cause

Both the **File Logs** and **Dataset Logs** tabs on the frontend called
the same backend endpoint `/datasets/{dataset_id}/ingestions`. However,
the backend only queried `get_dataset_logs_by_kb_id`, which
hard-filtered records by `document_id == GRAPH_RAPTOR_FAKE_DOC_ID`
(dataset-level logs). As a result, real file-level logs were never
returned, causing the table to appear empty.

## Changes

### Backend

- **`api/apps/restful_apis/dataset_api.py`**
  - Added two new query parameters to `list_ingestion_logs`:
    - `log_type` — `"file"` or `"dataset"` (default: `"dataset"`)
    - `keywords` — search keyword for filtering by document / task name

- **`api/apps/services/dataset_api_service.py`**
- Updated `list_ingestion_logs` signature to accept `log_type` and
`keywords`.
  - Added conditional routing:
- When `log_type == "file"`, call
`PipelineOperationLogService.get_file_logs_by_kb_id`
- Otherwise, call
`PipelineOperationLogService.get_dataset_logs_by_kb_id`

- **`api/db/services/pipeline_operation_log_service.py`**
- Extended `get_dataset_logs_by_kb_id` with an optional `keywords`
parameter so dataset logs can also be searched.

### Frontend

- **`web/src/pages/dataset/dataset-overview/hook.ts`**
- Removed the separate API function switching (`listPipelineDatasetLogs`
vs `listDataPipelineLogDocument`).
- Unified both tabs to call `listDataPipelineLogDocument` with the new
`log_type` query parameter (`"file"` or `"dataset"`).
  - Ensured `keywords` and filter values are passed through correctly.

## Behavior After Fix

| Tab | `log_type` | Returned Records | Searchable Field |
|---|---|---|---|
| File Logs | `file` | Real document-level logs | `document_name` (file
name) |
| Dataset Logs | `dataset` | GraphRAG / RAPTOR / MindMap logs |
`document_name` (task type) |
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Signed-off-by: noob <yixiao121314@outlook.com>
Co-authored-by: Wang Qi <wangq8@outlook.com>
Co-authored-by: Yingfeng Zhang <yingfeng.zhang@gmail.com>

api/apps/restful_apis/dataset_api.py

@@ -79,7 +79,7 @@ def get_flattened_metadata(tenant_id):
 @manager.route("/datasets", methods=["POST"])  # noqa: F821
 @login_required
 @add_tenant_id_to_kwargs
-async def create(tenant_id: str=None):
+async def create(tenant_id: str = None):
     """
     Create a new dataset.
     ---
@@ -477,7 +477,7 @@ async def rename_tag(tenant_id, dataset_id):
         return get_error_data_result(message="Internal server error")
 
 
-@manager.route('/datasets/<dataset_id>/search', methods=['POST'])  # noqa: F821
+@manager.route("/datasets/<dataset_id>/search", methods=["POST"])  # noqa: F821
 @login_required
 @add_tenant_id_to_kwargs
 async def search(tenant_id, dataset_id):
@@ -506,7 +506,7 @@ async def search(tenant_id, dataset_id):
         return get_error_data_result(message="Internal server error")
 
 
-@manager.route('/datasets/<dataset_id>/graph/search', methods=['GET'])  # noqa: F821
+@manager.route("/datasets/<dataset_id>/graph/search", methods=["GET"])  # noqa: F821
 @login_required
 @add_tenant_id_to_kwargs
 async def knowledge_graph(tenant_id, dataset_id):
@@ -515,17 +515,13 @@ async def knowledge_graph(tenant_id, dataset_id):
         if success:
             return get_result(data=result)
         else:
-            return get_result(
-                data=False,
-                message=result,
-                code=RetCode.AUTHENTICATION_ERROR
-            )
+            return get_result(data=False, message=result, code=RetCode.AUTHENTICATION_ERROR)
     except Exception as e:
         logging.exception(e)
         return get_error_data_result(message="Internal server error")
 
 
-@manager.route('/datasets/<dataset_id>/graph', methods=['GET'])  # noqa: F821
+@manager.route("/datasets/<dataset_id>/graph", methods=["GET"])  # noqa: F821
 @login_required
 @add_tenant_id_to_kwargs
 async def get_knowledge_graph(tenant_id, dataset_id):
@@ -541,17 +537,13 @@ async def get_knowledge_graph(tenant_id, dataset_id):
         if success:
             return get_result(data=result)
         else:
-            return get_result(
-                data=False,
-                message=result,
-                code=RetCode.AUTHENTICATION_ERROR
-            )
+            return get_result(data=False, message=result, code=RetCode.AUTHENTICATION_ERROR)
     except Exception as e:
         logging.exception(e)
         return get_error_data_result(message="Internal server error")
 
 
-@manager.route('/datasets/<dataset_id>/graph', methods=['DELETE'])  # noqa: F821
+@manager.route("/datasets/<dataset_id>/graph", methods=["DELETE"])  # noqa: F821
 @login_required
 @add_tenant_id_to_kwargs
 def delete_knowledge_graph(tenant_id, dataset_id):
@@ -560,11 +552,7 @@ def delete_knowledge_graph(tenant_id, dataset_id):
         if success:
             return get_result(data=result)
         else:
-            return get_result(
-                data=False,
-                message=result,
-                code=RetCode.AUTHENTICATION_ERROR
-            )
+            return get_result(data=False, message=result, code=RetCode.AUTHENTICATION_ERROR)
     except Exception as e:
         logging.exception(e)
         return get_error_data_result(message="Internal server error")
@@ -655,9 +643,9 @@ def list_ingestion_logs(tenant_id, dataset_id):
         operation_status = request.args.getlist("operation_status")
         create_date_from = request.args.get("create_date_from", None)
         create_date_to = request.args.get("create_date_to", None)
-        success, result = dataset_api_service.list_ingestion_logs(
-            dataset_id, tenant_id, page, page_size, orderby, desc, operation_status, create_date_from, create_date_to
-        )
+        log_type = request.args.get("log_type", "dataset")
+        keywords = request.args.get("keywords", None)
+        success, result = dataset_api_service.list_ingestion_logs(dataset_id, tenant_id, page, page_size, orderby, desc, operation_status, create_date_from, create_date_to, log_type, keywords)
         if success:
             return get_result(data=result)
         else:
@@ -762,6 +750,7 @@ async def update_auto_metadata(tenant_id, dataset_id):
           type: object
     """
     from api.utils.validation_utils import AutoMetadataConfig
+
     cfg, err = await validate_and_parse_json_request(request, AutoMetadataConfig)
     if err is not None:
         return get_error_argument_result(err)

api/apps/sdk/dify_retrieval.py

@@ -122,6 +122,8 @@ async def retrieval(tenant_id):
     retrieval_setting = req.get("retrieval_setting", {})
     similarity_threshold = float(retrieval_setting.get("score_threshold", 0.0))
     top = int(retrieval_setting.get("top_k", 1024))
+    if top <= 0:
+        return build_error_result(message="`top_k` must be greater than 0", code=RetCode.DATA_ERROR)
     metadata_condition = req.get("metadata_condition", {}) or {}
     metas = DocMetadataService.get_flatted_meta_by_kbs([kb_id])
 

api/apps/sdk/doc.py

@@ -436,6 +436,8 @@ async def retrieval_test(tenant_id):
     similarity_threshold = float(req.get("similarity_threshold", 0.2))
     vector_similarity_weight = float(req.get("vector_similarity_weight", 0.3))
     top = int(req.get("top_k", 1024))
+    if top <= 0:
+        return get_error_data_result("`top_k` must be greater than 0")
     highlight_val = req.get("highlight", None)
     if highlight_val is None:
         highlight = False

api/apps/sdk/session.py

@@ -319,6 +319,8 @@ async def retrieval_test_embedded():
     vector_similarity_weight = float(req.get("vector_similarity_weight", 0.3))
     use_kg = req.get("use_kg", False)
     top = int(req.get("top_k", 1024))
+    if top <= 0:
+        return get_error_data_result("`top_k` must be greater than 0")
     langs = req.get("cross_languages", [])
     rerank_id = req.get("rerank_id", "")
     tenant_rerank_id = req.get("tenant_rerank_id", "")

api/apps/services/dataset_api_service.py

@@ -81,12 +81,7 @@ async def create_dataset(tenant_id: str, req: dict):
         req["parser_config"] = parser_cfg
     req.update(ext_fields)
 
-    e, create_dict = KnowledgebaseService.create_with_name(
-        name=req.pop("name", None),
-        tenant_id=tenant_id,
-        parser_id=req.pop("parser_id", None),
-        **req
-    )
+    e, create_dict = KnowledgebaseService.create_with_name(name=req.pop("name", None), tenant_id=tenant_id, parser_id=req.pop("parser_id", None), **req)
 
     if not e:
         return False, create_dict
@@ -152,12 +147,12 @@ async def delete_datasets(tenant_id: str, ids: list = None, delete_all: bool = F
                 ]
             )
             File2DocumentService.delete_by_document_id(doc.id)
-        FileService.filter_delete(
-            [File.source_type == FileSource.KNOWLEDGEBASE, File.type == "folder", File.name == kb.name])
+        FileService.filter_delete([File.source_type == FileSource.KNOWLEDGEBASE, File.type == "folder", File.name == kb.name])
 
         # Drop index for this dataset
         try:
             from rag.nlp import search
+
             idxnm = search.index_name(kb.tenant_id)
             settings.docStoreConn.delete_idx(idxnm, kb_id)
         except Exception as e:
@@ -266,7 +261,7 @@ async def update_dataset(tenant_id: str, dataset_id: str, req: dict):
         parser_cfg["metadata"] = fields
         parser_cfg["enable_metadata"] = auto_meta.get("enabled", True)
         req["parser_config"] = parser_cfg
-    
+
     # Merge ext fields with req
     req.update(ext_fields)
 
@@ -303,8 +298,7 @@ async def update_dataset(tenant_id: str, dataset_id: str, req: dict):
         req["pipeline_id"] = ""
 
     if "name" in req and req["name"].lower() != kb.name.lower():
-        exists = KnowledgebaseService.get_or_none(name=req["name"], tenant_id=tenant_id,
-                                                  status=StatusEnum.VALID.value)
+        exists = KnowledgebaseService.get_or_none(name=req["name"], tenant_id=tenant_id, status=StatusEnum.VALID.value)
         if exists:
             return False, f"Dataset name '{req['name']}' already exists"
 
@@ -323,13 +317,13 @@ async def update_dataset(tenant_id: str, dataset_id: str, req: dict):
 
         if req["pagerank"] > 0:
             from rag.nlp import search
-            settings.docStoreConn.update({"kb_id": kb.id}, {PAGERANK_FLD: req["pagerank"]},
-                                         search.index_name(kb.tenant_id), kb.id)
+
+            settings.docStoreConn.update({"kb_id": kb.id}, {PAGERANK_FLD: req["pagerank"]}, search.index_name(kb.tenant_id), kb.id)
         else:
             # Elasticsearch requires PAGERANK_FLD be non-zero!
             from rag.nlp import search
-            settings.docStoreConn.update({"exists": PAGERANK_FLD}, {"remove": PAGERANK_FLD},
-                                         search.index_name(kb.tenant_id), kb.id)
+
+            settings.docStoreConn.update({"exists": PAGERANK_FLD}, {"remove": PAGERANK_FLD}, search.index_name(kb.tenant_id), kb.id)
     if "parse_type" in req:
         del req["parse_type"]
 
@@ -388,27 +382,13 @@ def list_datasets(tenant_id: str, args: dict):
     else:
         tenants = TenantService.get_joined_tenants_by_user_id(tenant_id)
         tenant_ids = [m["tenant_id"] for m in tenants]
-    kbs, total = KnowledgebaseService.get_list(
-        tenant_ids,
-        tenant_id,
-        page,
-        page_size,
-        orderby,
-        desc,
-        kb_id,
-        name,
-        keywords,
-        parser_id
-    )
+    kbs, total = KnowledgebaseService.get_list(tenant_ids, tenant_id, page, page_size, orderby, desc, kb_id, name, keywords, parser_id)
     users = UserService.get_by_ids([m["tenant_id"] for m in kbs])
     user_map = {m.id: m.to_dict() for m in users}
     response_data_list = []
     for kb in kbs:
         user_dict = user_map.get(kb["tenant_id"], {})
-        kb.update({
-            "nickname": user_dict.get("nickname", ""),
-            "tenant_avatar": user_dict.get("avatar", "")
-        })
+        kb.update({"nickname": user_dict.get("nickname", ""), "tenant_avatar": user_dict.get("avatar", "")})
         response_data_list.append(remap_dictionary_keys(kb))
     return True, {"data": response_data_list, "total": total}
 
@@ -425,13 +405,11 @@ async def get_knowledge_graph(dataset_id: str, tenant_id: str):
         return False, "No authorization."
     _, kb = KnowledgebaseService.get_by_id(dataset_id)
 
-    req = {
-        "kb_id": [dataset_id],
-        "knowledge_graph_kwd": ["graph"]
-    }
+    req = {"kb_id": [dataset_id], "knowledge_graph_kwd": ["graph"]}
 
     obj = {"graph": {}, "mind_map": {}}
     from rag.nlp import search
+
     if not settings.docStoreConn.index_exist(search.index_name(kb.tenant_id), dataset_id):
         return True, obj
     sres = await settings.retriever.search(req, search.index_name(kb.tenant_id), [dataset_id])
@@ -451,8 +429,7 @@ async def get_knowledge_graph(dataset_id: str, tenant_id: str):
         obj["graph"]["nodes"] = sorted(obj["graph"]["nodes"], key=lambda x: x.get("pagerank", 0), reverse=True)[:256]
         if "edges" in obj["graph"]:
             node_id_set = {o["id"] for o in obj["graph"]["nodes"]}
-            filtered_edges = [o for o in obj["graph"]["edges"] if
-                              o["source"] != o["target"] and o["source"] in node_id_set and o["target"] in node_id_set]
+            filtered_edges = [o for o in obj["graph"]["edges"] if o["source"] != o["target"] and o["source"] in node_id_set and o["target"] in node_id_set]
             obj["graph"]["edges"] = sorted(filtered_edges, key=lambda x: x.get("weight", 0), reverse=True)[:128]
     return True, obj
 
@@ -469,8 +446,8 @@ def delete_knowledge_graph(dataset_id: str, tenant_id: str):
         return False, "No authorization."
     _, kb = KnowledgebaseService.get_by_id(dataset_id)
     from rag.nlp import search
-    settings.docStoreConn.delete({"knowledge_graph_kwd": ["graph", "subgraph", "entity", "relation"]},
-                                 search.index_name(kb.tenant_id), dataset_id)
+
+    settings.docStoreConn.delete({"knowledge_graph_kwd": ["graph", "subgraph", "entity", "relation"]}, search.index_name(kb.tenant_id), dataset_id)
 
     return True, True
 
@@ -636,6 +613,7 @@ def get_flattened_metadata(dataset_ids: list[str], tenant_id: str):
             return False, f"No authorization for dataset '{dataset_id}'"
 
     from api.db.services.doc_metadata_service import DocMetadataService
+
     return True, DocMetadataService.get_flatted_meta_by_kbs(dataset_ids)
 
 
@@ -697,15 +675,26 @@ def delete_tags(dataset_id: str, tenant_id: str, tags: list[str]):
         return False, "Invalid Dataset ID"
 
     from rag.nlp import search
+
     for t in tags:
-        settings.docStoreConn.update({"tag_kwd": t, "kb_id": [dataset_id]},
-                                     {"remove": {"tag_kwd": t}},
-                                     search.index_name(kb.tenant_id),
-                                     dataset_id)
+        settings.docStoreConn.update({"tag_kwd": t, "kb_id": [dataset_id]}, {"remove": {"tag_kwd": t}}, search.index_name(kb.tenant_id), dataset_id)
 
     return True, {}
 
-def list_ingestion_logs(dataset_id: str, tenant_id: str, page: int, page_size: int, orderby: str, desc: bool, operation_status: list = None, create_date_from: str = None, create_date_to: str = None):
+
+def list_ingestion_logs(
+    dataset_id: str,
+    tenant_id: str,
+    page: int,
+    page_size: int,
+    orderby: str,
+    desc: bool,
+    operation_status: list = None,
+    create_date_from: str = None,
+    create_date_to: str = None,
+    log_type: str = "dataset",
+    keywords: str = None,
+):
     """
     List ingestion logs for a dataset.
 
@@ -718,6 +707,8 @@ def list_ingestion_logs(dataset_id: str, tenant_id: str, page: int, page_size: i
     :param operation_status: filter by operation status
     :param create_date_from: filter start date
     :param create_date_to: filter end date
+    :param log_type: "dataset" or "file"
+    :param keywords: search keywords for file logs
     :return: (success, result) or (success, error_message)
     """
     if not dataset_id:
@@ -727,9 +718,30 @@ def list_ingestion_logs(dataset_id: str, tenant_id: str, page: int, page_size: i
         return False, "No authorization."
 
     from api.db.services.pipeline_operation_log_service import PipelineOperationLogService
-    logs, total = PipelineOperationLogService.get_dataset_logs_by_kb_id(
-        dataset_id, page, page_size, orderby, desc, operation_status or [], create_date_from, create_date_to
+
+    allowed_log_types = {"dataset", "file"}
+    if log_type not in allowed_log_types:
+        logging.warning(
+            "list_ingestion_logs invalid log_type: dataset_id=%s tenant_id=%s log_type=%s",
+            dataset_id,
+            tenant_id,
+            log_type,
+        )
+        return False, 'Invalid "log_type", expected "dataset" or "file"'
+
+    logging.info(
+        "list_ingestion_logs: dataset_id=%s tenant_id=%s log_type=%s page=%s page_size=%s",
+        dataset_id,
+        tenant_id,
+        log_type,
+        page,
+        page_size,
     )
+
+    if log_type == "file":
+        logs, total = PipelineOperationLogService.get_file_logs_by_kb_id(dataset_id, page, page_size, orderby, desc, keywords, operation_status or [], None, None, create_date_from, create_date_to)
+    else:
+        logs, total = PipelineOperationLogService.get_dataset_logs_by_kb_id(dataset_id, page, page_size, orderby, desc, operation_status or [], create_date_from, create_date_to, keywords)
     return True, {"total": total, "logs": logs}
 
 
@@ -749,10 +761,9 @@ def get_ingestion_log(dataset_id: str, tenant_id: str, log_id: str):
         return False, "No authorization."
 
     from api.db.services.pipeline_operation_log_service import PipelineOperationLogService
+
     fields = PipelineOperationLogService.get_dataset_logs_fields()
-    log = PipelineOperationLogService.model.select(*fields).where(
-        (PipelineOperationLogService.model.id == log_id) & (PipelineOperationLogService.model.kb_id == dataset_id)
-    ).first()
+    log = PipelineOperationLogService.model.select(*fields).where((PipelineOperationLogService.model.id == log_id) & (PipelineOperationLogService.model.kb_id == dataset_id)).first()
     if not log:
         return False, "Log not found"
 
@@ -787,6 +798,7 @@ def delete_index(dataset_id: str, tenant_id: str, index_type: str):
 
     if task_id:
         from rag.utils.redis_conn import REDIS_CONN
+
         try:
             REDIS_CONN.set(f"{task_id}-cancel", "x")
         except Exception as e:
@@ -795,12 +807,12 @@ def delete_index(dataset_id: str, tenant_id: str, index_type: str):
 
     if index_type == "graph":
         from rag.nlp import search
-        settings.docStoreConn.delete({"knowledge_graph_kwd": ["graph", "subgraph", "entity", "relation"]},
-                                     search.index_name(kb.tenant_id), dataset_id)
+
+        settings.docStoreConn.delete({"knowledge_graph_kwd": ["graph", "subgraph", "entity", "relation"]}, search.index_name(kb.tenant_id), dataset_id)
     elif index_type == "raptor":
         from rag.nlp import search
-        settings.docStoreConn.delete({"raptor_kwd": ["raptor"]},
-                                     search.index_name(kb.tenant_id), dataset_id)
+
+        settings.docStoreConn.delete({"raptor_kwd": ["raptor"]}, search.index_name(kb.tenant_id), dataset_id)
 
     KnowledgebaseService.update_by_id(kb.id, {task_id_field: "", task_finish_at_field: None})
     return True, {}
@@ -867,10 +879,8 @@ def rename_tag(dataset_id: str, tenant_id: str, from_tag: str, to_tag: str):
         return False, "Invalid Dataset ID"
 
     from rag.nlp import search
-    settings.docStoreConn.update({"tag_kwd": from_tag, "kb_id": [dataset_id]},
-                                 {"remove": {"tag_kwd": from_tag.strip()}, "add": {"tag_kwd": to_tag}},
-                                 search.index_name(kb.tenant_id),
-                                 dataset_id)
+
+    settings.docStoreConn.update({"tag_kwd": from_tag, "kb_id": [dataset_id]}, {"remove": {"tag_kwd": from_tag.strip()}, "add": {"tag_kwd": to_tag}}, search.index_name(kb.tenant_id), dataset_id)
 
     return True, {"from": from_tag, "to": to_tag}
 
@@ -987,36 +997,30 @@ async def search(dataset_id: str, tenant_id: str, req: dict):
 
     labels = label_question(_question, [kb])
     ranks = await settings.retriever.retrieval(
-                    _question,
-                    embd_mdl,
-                    tenant_ids,
-                    [dataset_id],
-                    page,
-                    size,
-                    float(req.get("similarity_threshold", 0.0)),
-                    float(req.get("vector_similarity_weight", 0.3)),
-                    doc_ids=local_doc_ids,
-                    top=top,
-                    rerank_mdl=rerank_mdl,
-                    rank_feature=labels
-                )
+        _question,
+        embd_mdl,
+        tenant_ids,
+        [dataset_id],
+        page,
+        size,
+        float(req.get("similarity_threshold", 0.0)),
+        float(req.get("vector_similarity_weight", 0.3)),
+        doc_ids=local_doc_ids,
+        top=top,
+        rerank_mdl=rerank_mdl,
+        rank_feature=labels,
+    )
 
     if use_kg:
         try:
             default_chat_model_config = get_tenant_default_model_by_type(tenant_id, LLMType.CHAT)
-            ck = await settings.kg_retriever.retrieval(_question,
-                                                   tenant_ids,
-                                                   [dataset_id],
-                                                   embd_mdl,
-                                                   LLMBundle(kb.tenant_id, default_chat_model_config))
+            ck = await settings.kg_retriever.retrieval(_question, tenant_ids, [dataset_id], embd_mdl, LLMBundle(kb.tenant_id, default_chat_model_config))
             if ck["content_with_weight"]:
                 ranks["chunks"].insert(0, ck)
         except Exception:
             logging.warning("search KG retrieval failed: dataset=%s tenant=%s", dataset_id, tenant_id, exc_info=True)
     total = ranks.get("total", 0)
-    ranks["chunks"] = settings.retriever.retrieval_by_children(
-        ranks["chunks"], tenant_ids
-    )
+    ranks["chunks"] = settings.retriever.retrieval_by_children(ranks["chunks"], tenant_ids)
     ranks["total"] = total
 
     for c in ranks["chunks"]: