mirror of
https://github.com/open-webui/open-webui
synced 2025-06-13 18:02:50 +00:00
rename BM25_WEIGHT -> HYBRID_BM25_WEIGHT
This commit is contained in:
parent
308d8ac04a
commit
e70dd33233
@ -1928,10 +1928,10 @@ RAG_RELEVANCE_THRESHOLD = PersistentConfig(
|
|||||||
"rag.relevance_threshold",
|
"rag.relevance_threshold",
|
||||||
float(os.environ.get("RAG_RELEVANCE_THRESHOLD", "0.0")),
|
float(os.environ.get("RAG_RELEVANCE_THRESHOLD", "0.0")),
|
||||||
)
|
)
|
||||||
RAG_BM25_WEIGHT = PersistentConfig(
|
RAG_HYBRID_BM25_WEIGHT = PersistentConfig(
|
||||||
"RAG_BM25_WEIGHT",
|
"RAG_HYBRID_BM25_WEIGHT",
|
||||||
"rag.bm25_weight",
|
"rag.hybrid_bm25_weight",
|
||||||
float(os.environ.get("RAG_BM25_WEIGHT", "0.5")),
|
float(os.environ.get("RAG_HYBRID_BM25_WEIGHT", "0.5")),
|
||||||
)
|
)
|
||||||
|
|
||||||
ENABLE_RAG_HYBRID_SEARCH = PersistentConfig(
|
ENABLE_RAG_HYBRID_SEARCH = PersistentConfig(
|
||||||
|
@ -199,7 +199,7 @@ from open_webui.config import (
|
|||||||
RAG_TOP_K,
|
RAG_TOP_K,
|
||||||
RAG_TOP_K_RERANKER,
|
RAG_TOP_K_RERANKER,
|
||||||
RAG_RELEVANCE_THRESHOLD,
|
RAG_RELEVANCE_THRESHOLD,
|
||||||
RAG_BM25_WEIGHT,
|
RAG_HYBRID_BM25_WEIGHT,
|
||||||
RAG_ALLOWED_FILE_EXTENSIONS,
|
RAG_ALLOWED_FILE_EXTENSIONS,
|
||||||
RAG_FILE_MAX_COUNT,
|
RAG_FILE_MAX_COUNT,
|
||||||
RAG_FILE_MAX_SIZE,
|
RAG_FILE_MAX_SIZE,
|
||||||
@ -647,7 +647,7 @@ app.state.FUNCTIONS = {}
|
|||||||
app.state.config.TOP_K = RAG_TOP_K
|
app.state.config.TOP_K = RAG_TOP_K
|
||||||
app.state.config.TOP_K_RERANKER = RAG_TOP_K_RERANKER
|
app.state.config.TOP_K_RERANKER = RAG_TOP_K_RERANKER
|
||||||
app.state.config.RELEVANCE_THRESHOLD = RAG_RELEVANCE_THRESHOLD
|
app.state.config.RELEVANCE_THRESHOLD = RAG_RELEVANCE_THRESHOLD
|
||||||
app.state.config.BM25_WEIGHT = RAG_BM25_WEIGHT
|
app.state.config.HYBRID_BM25_WEIGHT = RAG_HYBRID_BM25_WEIGHT
|
||||||
app.state.config.ALLOWED_FILE_EXTENSIONS = RAG_ALLOWED_FILE_EXTENSIONS
|
app.state.config.ALLOWED_FILE_EXTENSIONS = RAG_ALLOWED_FILE_EXTENSIONS
|
||||||
app.state.config.FILE_MAX_SIZE = RAG_FILE_MAX_SIZE
|
app.state.config.FILE_MAX_SIZE = RAG_FILE_MAX_SIZE
|
||||||
app.state.config.FILE_MAX_COUNT = RAG_FILE_MAX_COUNT
|
app.state.config.FILE_MAX_COUNT = RAG_FILE_MAX_COUNT
|
||||||
|
@ -116,7 +116,7 @@ def query_doc_with_hybrid_search(
|
|||||||
reranking_function,
|
reranking_function,
|
||||||
k_reranker: int,
|
k_reranker: int,
|
||||||
r: float,
|
r: float,
|
||||||
bm25_weight: float,
|
hybrid_bm25_weight: float,
|
||||||
) -> dict:
|
) -> dict:
|
||||||
try:
|
try:
|
||||||
log.debug(f"query_doc_with_hybrid_search:doc {collection_name}")
|
log.debug(f"query_doc_with_hybrid_search:doc {collection_name}")
|
||||||
@ -132,18 +132,18 @@ def query_doc_with_hybrid_search(
|
|||||||
top_k=k,
|
top_k=k,
|
||||||
)
|
)
|
||||||
|
|
||||||
if bm25_weight <= 0:
|
if hybrid_bm25_weight <= 0:
|
||||||
ensemble_retriever = EnsembleRetriever(
|
ensemble_retriever = EnsembleRetriever(
|
||||||
retrievers=[vector_search_retriever], weights=[1.]
|
retrievers=[vector_search_retriever], weights=[1.]
|
||||||
)
|
)
|
||||||
elif bm25_weight >= 1:
|
elif hybrid_bm25_weight >= 1:
|
||||||
ensemble_retriever = EnsembleRetriever(
|
ensemble_retriever = EnsembleRetriever(
|
||||||
retrievers=[bm25_retriever], weights=[1.]
|
retrievers=[bm25_retriever], weights=[1.]
|
||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
ensemble_retriever = EnsembleRetriever(
|
ensemble_retriever = EnsembleRetriever(
|
||||||
retrievers=[bm25_retriever, vector_search_retriever],
|
retrievers=[bm25_retriever, vector_search_retriever],
|
||||||
weights=[bm25_weight, 1. - bm25_weight]
|
weights=[hybrid_bm25_weight, 1. - hybrid_bm25_weight]
|
||||||
)
|
)
|
||||||
|
|
||||||
compressor = RerankCompressor(
|
compressor = RerankCompressor(
|
||||||
@ -325,7 +325,7 @@ def query_collection_with_hybrid_search(
|
|||||||
reranking_function,
|
reranking_function,
|
||||||
k_reranker: int,
|
k_reranker: int,
|
||||||
r: float,
|
r: float,
|
||||||
bm25_weight: float,
|
hybrid_bm25_weight: float,
|
||||||
) -> dict:
|
) -> dict:
|
||||||
results = []
|
results = []
|
||||||
error = False
|
error = False
|
||||||
@ -359,7 +359,7 @@ def query_collection_with_hybrid_search(
|
|||||||
reranking_function=reranking_function,
|
reranking_function=reranking_function,
|
||||||
k_reranker=k_reranker,
|
k_reranker=k_reranker,
|
||||||
r=r,
|
r=r,
|
||||||
bm25_weight=bm25_weight,
|
hybrid_bm25_weight=hybrid_bm25_weight,
|
||||||
)
|
)
|
||||||
return result, None
|
return result, None
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
@ -447,7 +447,7 @@ def get_sources_from_files(
|
|||||||
reranking_function,
|
reranking_function,
|
||||||
k_reranker,
|
k_reranker,
|
||||||
r,
|
r,
|
||||||
bm25_weight,
|
hybrid_bm25_weight,
|
||||||
hybrid_search,
|
hybrid_search,
|
||||||
full_context=False,
|
full_context=False,
|
||||||
):
|
):
|
||||||
@ -565,7 +565,7 @@ def get_sources_from_files(
|
|||||||
reranking_function=reranking_function,
|
reranking_function=reranking_function,
|
||||||
k_reranker=k_reranker,
|
k_reranker=k_reranker,
|
||||||
r=r,
|
r=r,
|
||||||
bm25_weight=bm25_weight,
|
hybrid_bm25_weight=hybrid_bm25_weight,
|
||||||
)
|
)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
log.debug(
|
log.debug(
|
||||||
|
@ -349,7 +349,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
|
|||||||
"ENABLE_RAG_HYBRID_SEARCH": request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
|
"ENABLE_RAG_HYBRID_SEARCH": request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
|
||||||
"TOP_K_RERANKER": request.app.state.config.TOP_K_RERANKER,
|
"TOP_K_RERANKER": request.app.state.config.TOP_K_RERANKER,
|
||||||
"RELEVANCE_THRESHOLD": request.app.state.config.RELEVANCE_THRESHOLD,
|
"RELEVANCE_THRESHOLD": request.app.state.config.RELEVANCE_THRESHOLD,
|
||||||
"BM25_WEIGHT": request.app.state.config.BM25_WEIGHT,
|
"HYBRID_BM25_WEIGHT": request.app.state.config.HYBRID_BM25_WEIGHT,
|
||||||
# Content extraction settings
|
# Content extraction settings
|
||||||
"CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
|
"CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
|
||||||
"PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
|
"PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
|
||||||
@ -493,7 +493,7 @@ class ConfigForm(BaseModel):
|
|||||||
ENABLE_RAG_HYBRID_SEARCH: Optional[bool] = None
|
ENABLE_RAG_HYBRID_SEARCH: Optional[bool] = None
|
||||||
TOP_K_RERANKER: Optional[int] = None
|
TOP_K_RERANKER: Optional[int] = None
|
||||||
RELEVANCE_THRESHOLD: Optional[float] = None
|
RELEVANCE_THRESHOLD: Optional[float] = None
|
||||||
BM25_WEIGHT: Optional[float] = None
|
HYBRID_BM25_WEIGHT: Optional[float] = None
|
||||||
|
|
||||||
# Content extraction settings
|
# Content extraction settings
|
||||||
CONTENT_EXTRACTION_ENGINE: Optional[str] = None
|
CONTENT_EXTRACTION_ENGINE: Optional[str] = None
|
||||||
@ -580,10 +580,10 @@ async def update_rag_config(
|
|||||||
if form_data.RELEVANCE_THRESHOLD is not None
|
if form_data.RELEVANCE_THRESHOLD is not None
|
||||||
else request.app.state.config.RELEVANCE_THRESHOLD
|
else request.app.state.config.RELEVANCE_THRESHOLD
|
||||||
)
|
)
|
||||||
request.app.state.config.BM25_WEIGHT = (
|
request.app.state.config.HYBRID_BM25_WEIGHT = (
|
||||||
form_data.BM25_WEIGHT
|
form_data.HYBRID_BM25_WEIGHT
|
||||||
if form_data.BM25_WEIGHT is not None
|
if form_data.HYBRID_BM25_WEIGHT is not None
|
||||||
else request.app.state.config.BM25_WEIGHT
|
else request.app.state.config.HYBRID_BM25_WEIGHT
|
||||||
)
|
)
|
||||||
|
|
||||||
# Content extraction settings
|
# Content extraction settings
|
||||||
@ -844,7 +844,7 @@ async def update_rag_config(
|
|||||||
"ENABLE_RAG_HYBRID_SEARCH": request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
|
"ENABLE_RAG_HYBRID_SEARCH": request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
|
||||||
"TOP_K_RERANKER": request.app.state.config.TOP_K_RERANKER,
|
"TOP_K_RERANKER": request.app.state.config.TOP_K_RERANKER,
|
||||||
"RELEVANCE_THRESHOLD": request.app.state.config.RELEVANCE_THRESHOLD,
|
"RELEVANCE_THRESHOLD": request.app.state.config.RELEVANCE_THRESHOLD,
|
||||||
"BM25_WEIGHT": request.app.state.config.BM25_WEIGHT,
|
"HYBRID_BM25_WEIGHT": request.app.state.config.HYBRID_BM25_WEIGHT,
|
||||||
# Content extraction settings
|
# Content extraction settings
|
||||||
"CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
|
"CONTENT_EXTRACTION_ENGINE": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
|
||||||
"PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
|
"PDF_EXTRACT_IMAGES": request.app.state.config.PDF_EXTRACT_IMAGES,
|
||||||
@ -1782,10 +1782,10 @@ def query_doc_handler(
|
|||||||
if form_data.r
|
if form_data.r
|
||||||
else request.app.state.config.RELEVANCE_THRESHOLD
|
else request.app.state.config.RELEVANCE_THRESHOLD
|
||||||
),
|
),
|
||||||
bm25_weight=(
|
hybrid_bm25_weight=(
|
||||||
form_data.bm25_weight
|
form_data.hybrid_bm25_weight
|
||||||
if form_data.bm25_weight
|
if form_data.hybrid_bm25_weight
|
||||||
else request.app.state.config.BM25_WEIGHT
|
else request.app.state.config.HYBRID_BM25_WEIGHT
|
||||||
),
|
),
|
||||||
user=user,
|
user=user,
|
||||||
)
|
)
|
||||||
@ -1838,10 +1838,10 @@ def query_collection_handler(
|
|||||||
if form_data.r
|
if form_data.r
|
||||||
else request.app.state.config.RELEVANCE_THRESHOLD
|
else request.app.state.config.RELEVANCE_THRESHOLD
|
||||||
),
|
),
|
||||||
bm25_weight=(
|
hybrid_bm25_weight=(
|
||||||
form_data.bm25_weight
|
form_data.hybrid_bm25_weight
|
||||||
if form_data.bm25_weight
|
if form_data.hybrid_bm25_weight
|
||||||
else request.app.state.config.BM25_WEIGHT
|
else request.app.state.config.HYBRID_BM25_WEIGHT
|
||||||
),
|
),
|
||||||
)
|
)
|
||||||
else:
|
else:
|
||||||
|
@ -603,7 +603,7 @@ async def chat_completion_files_handler(
|
|||||||
reranking_function=request.app.state.rf,
|
reranking_function=request.app.state.rf,
|
||||||
k_reranker=request.app.state.config.TOP_K_RERANKER,
|
k_reranker=request.app.state.config.TOP_K_RERANKER,
|
||||||
r=request.app.state.config.RELEVANCE_THRESHOLD,
|
r=request.app.state.config.RELEVANCE_THRESHOLD,
|
||||||
bm25_weight=request.app.state.config.BM25_WEIGHT,
|
hybrid_bm25_weight=request.app.state.config.HYBRID_BM25_WEIGHT,
|
||||||
hybrid_search=request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
|
hybrid_search=request.app.state.config.ENABLE_RAG_HYBRID_SEARCH,
|
||||||
full_context=request.app.state.config.RAG_FULL_CONTEXT,
|
full_context=request.app.state.config.RAG_FULL_CONTEXT,
|
||||||
),
|
),
|
||||||
|
@ -773,14 +773,14 @@
|
|||||||
|
|
||||||
{#if RAGConfig.ENABLE_RAG_HYBRID_SEARCH === true}
|
{#if RAGConfig.ENABLE_RAG_HYBRID_SEARCH === true}
|
||||||
<div class="mb-2.5 flex w-full justify-between">
|
<div class="mb-2.5 flex w-full justify-between">
|
||||||
<div class="self-center text-xs font-medium">{$i18n.t('BM25 Weight')}</div>
|
<div class="self-center text-xs font-medium">{$i18n.t('Weight of BM25 Retrieval')}</div>
|
||||||
<div class="flex items-center relative">
|
<div class="flex items-center relative">
|
||||||
<input
|
<input
|
||||||
class="flex-1 w-full text-sm bg-transparent outline-hidden"
|
class="flex-1 w-full text-sm bg-transparent outline-hidden"
|
||||||
type="number"
|
type="number"
|
||||||
step="0.01"
|
step="0.01"
|
||||||
placeholder={$i18n.t('Enter BM25 Weight')}
|
placeholder={$i18n.t('Enter BM25 Weight')}
|
||||||
bind:value={RAGConfig.BM25_WEIGHT}
|
bind:value={RAGConfig.HYBRID_BM25_WEIGHT}
|
||||||
autocomplete="off"
|
autocomplete="off"
|
||||||
min="0.0"
|
min="0.0"
|
||||||
max="1.0"
|
max="1.0"
|
||||||
|
Loading…
Reference in New Issue
Block a user