zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-08-25 09:32:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

Refactor: do not include compliation chunks in retrieval testing (#18364)

Browse Source 
Retrieval Testing: do not include compilation result.
Search: include compilation result.
This commit is contained in:
Wang Qi
2026-08-17 16:19:05 +08:00
committed by GitHub
parent 3e38b6cacb
commit 57b907cd1e
11 changed files with 47 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
api/apps/restful_apis/dataset_api.py
View File

@@ -515,7 +515,7 @@ async def search_datasets(tenant_id):
POST /api/v1/datasets/search
JSON body: {"dataset_ids": list[str] (required), "question": str (required), "doc_ids": list[str], "top_k": int, "page": int, "size": int,
"similarity_threshold": float, "vector_similarity_weight": float, "use_kg": bool,
"cross_languages": list[str], "keyword": bool, "meta_data_filter": dict}
"cross_languages": list[str], "keyword": bool, "meta_data_filter": dict, "include_knowledge_compilation": bool (default true)}
Success: {"code": 0, "data": {"chunks": [...], "total": int, "labels": [...]}}
Errors: ARGUMENT_ERROR (101) for invalid payload; DATA_ERROR (102) for access denied or internal errors.
"""
@@ -538,7 +538,7 @@ async def search(tenant_id, dataset_id):
POST /api/v1/datasets/<dataset_id>/search
JSON body: {"question": str (required), "doc_ids": list[str], "top_k": int, "page": int, "size": int,
"similarity_threshold": float, "vector_similarity_weight": float, "use_kg": bool,
"cross_languages": list[str], "keyword": bool, "meta_data_filter": dict}
"cross_languages": list[str], "keyword": bool, "meta_data_filter": dict, "include_knowledge_compilation": bool (default true)}
Success: {"code": 0, "data": {"chunks": [...], "total": int, "labels": [...]}}
Errors: ARGUMENT_ERROR (101) for invalid payload; DATA_ERROR (102) for access denied or internal errors.
"""

1
api/apps/services/dataset_api_service.py
View File

@@ -1530,6 +1530,7 @@ async def search_datasets(tenant_id: str, req: dict):
rerank_mdl=rerank_mdl,
rank_feature=labels,
trace_id=search_id,
must_not=None if req.get("include_knowledge_compilation", True) else {"exists": "compile_kwd"},
)
if use_kg:

2
api/utils/validation_utils.py
View File

@@ -992,6 +992,7 @@ class SearchDatasetReq(BaseModel):
rerank_id: Annotated[str | None, Field(default=None)]
tenant_rerank_id: Annotated[str | None, Field(default=None)]
meta_data_filter: Annotated[dict | None, Field(default=None)]
include_knowledge_compilation: Annotated[bool, Field(default=True)]
class SearchDatasetsReq(BaseModel):
@@ -1014,6 +1015,7 @@ class SearchDatasetsReq(BaseModel):
rerank_id: Annotated[str | None, Field(default=None)]
tenant_rerank_id: Annotated[str | None, Field(default=None)]
meta_data_filter: Annotated[dict | None, Field(default=None)]
include_knowledge_compilation: Annotated[bool, Field(default=True)]
class BaseListReq(BaseModel):