Emil_Shanaty/open-webui-ai4me
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'upstream/dev' into playwright

Browse Source
This commit is contained in:
Rory
2025-02-05 17:47:58 -06:00
parent 7bac1a170d b8fe9497fb
commit ec6fe9939b
95 changed files with 2173 additions and 800 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/routers/retrieval.py
+42 -9
View File
@@ -55,6 +55,7 @@ from open_webui.retrieval.web.serply import search_serply
from open_webui.retrieval.web.serpstack import search_serpstack
from open_webui.retrieval.web.tavily import search_tavily
from open_webui.retrieval.web.bing import search_bing
from open_webui.retrieval.web.exa import search_exa
from open_webui.retrieval.utils import (
@@ -388,6 +389,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"jina_api_key": request.app.state.config.JINA_API_KEY,
"bing_search_v7_endpoint": request.app.state.config.BING_SEARCH_V7_ENDPOINT,
"bing_search_v7_subscription_key": request.app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
"exa_api_key": request.app.state.config.EXA_API_KEY,
"result_count": request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
"concurrent_requests": request.app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
},
@@ -436,6 +438,7 @@ class WebSearchConfig(BaseModel):
jina_api_key: Optional[str] = None
bing_search_v7_endpoint: Optional[str] = None
bing_search_v7_subscription_key: Optional[str] = None
exa_api_key: Optional[str] = None
result_count: Optional[int] = None
concurrent_requests: Optional[int] = None
@@ -542,6 +545,8 @@ async def update_rag_config(
form_data.web.search.bing_search_v7_subscription_key
)
request.app.state.config.EXA_API_KEY = form_data.web.search.exa_api_key
request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT = (
form_data.web.search.result_count
)
@@ -591,6 +596,7 @@ async def update_rag_config(
"jina_api_key": request.app.state.config.JINA_API_KEY,
"bing_search_v7_endpoint": request.app.state.config.BING_SEARCH_V7_ENDPOINT,
"bing_search_v7_subscription_key": request.app.state.config.BING_SEARCH_V7_SUBSCRIPTION_KEY,
"exa_api_key": request.app.state.config.EXA_API_KEY,
"result_count": request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
"concurrent_requests": request.app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
},
@@ -660,6 +666,7 @@ def save_docs_to_vector_db(
overwrite: bool = False,
split: bool = True,
add: bool = False,
user=None,
) -> bool:
def _get_docs_info(docs: list[Document]) -> str:
docs_info = set()
@@ -775,7 +782,7 @@ def save_docs_to_vector_db(
)
embeddings = embedding_function(
list(map(lambda x: x.replace("\n", " "), texts))
list(map(lambda x: x.replace("\n", " "), texts)), user=user
)
items = [
@@ -933,6 +940,7 @@ def process_file(
"hash": hash,
},
add=(True if form_data.collection_name else False),
user=user,
)
if result:
@@ -990,7 +998,7 @@ def process_text(
text_content = form_data.content
log.debug(f"text_content: {text_content}")
result = save_docs_to_vector_db(request, docs, collection_name)
result = save_docs_to_vector_db(request, docs, collection_name, user=user)
if result:
return {
"status": True,
@@ -1023,7 +1031,9 @@ def process_youtube_video(
content = " ".join([doc.page_content for doc in docs])
log.debug(f"text_content: {content}")
save_docs_to_vector_db(request, docs, collection_name, overwrite=True)
save_docs_to_vector_db(
request, docs, collection_name, overwrite=True, user=user
)
return {
"status": True,
@@ -1064,7 +1074,9 @@ def process_web(
content = " ".join([doc.page_content for doc in docs])
log.debug(f"text_content: {content}")
save_docs_to_vector_db(request, docs, collection_name, overwrite=True)
save_docs_to_vector_db(
request, docs, collection_name, overwrite=True, user=user
)
return {
"status": True,
@@ -1099,6 +1111,7 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
- SERPER_API_KEY
- SERPLY_API_KEY
- TAVILY_API_KEY
- EXA_API_KEY
- SEARCHAPI_API_KEY + SEARCHAPI_ENGINE (by default `google`)
Args:
query (str): The query to search for
@@ -1233,6 +1246,13 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
request.app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
)
elif engine == "exa":
return search_exa(
request.app.state.config.EXA_API_KEY,
query,
request.app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
request.app.state.config.RAG_WEB_SEARCH_DOMAIN_FILTER_LIST,
)
else:
raise Exception("No search engine API key found in environment variables")
@@ -1273,7 +1293,9 @@ async def process_web_search(
)
docs = [doc async for doc in loader.alazy_load()]
# docs = loader.load()
save_docs_to_vector_db(request, docs, collection_name, overwrite=True)
save_docs_to_vector_db(
request, docs, collection_name, overwrite=True, user=user
)
return {
"status": True,
@@ -1307,7 +1329,9 @@ def query_doc_handler(
return query_doc_with_hybrid_search(
collection_name=form_data.collection_name,
query=form_data.query,
embedding_function=request.app.state.EMBEDDING_FUNCTION,
embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(
query, user=user
),
k=form_data.k if form_data.k else request.app.state.config.TOP_K,
reranking_function=request.app.state.rf,
r=(
@@ -1315,12 +1339,16 @@ def query_doc_handler(
if form_data.r
else request.app.state.config.RELEVANCE_THRESHOLD
),
user=user,
)
else:
return query_doc(
collection_name=form_data.collection_name,
query_embedding=request.app.state.EMBEDDING_FUNCTION(form_data.query),
query_embedding=request.app.state.EMBEDDING_FUNCTION(
form_data.query, user=user
),
k=form_data.k if form_data.k else request.app.state.config.TOP_K,
user=user,
)
except Exception as e:
log.exception(e)
@@ -1349,7 +1377,9 @@ def query_collection_handler(
return query_collection_with_hybrid_search(
collection_names=form_data.collection_names,
queries=[form_data.query],
embedding_function=request.app.state.EMBEDDING_FUNCTION,
embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(
query, user=user
),
k=form_data.k if form_data.k else request.app.state.config.TOP_K,
reranking_function=request.app.state.rf,
r=(
@@ -1362,7 +1392,9 @@ def query_collection_handler(
return query_collection(
collection_names=form_data.collection_names,
queries=[form_data.query],
embedding_function=request.app.state.EMBEDDING_FUNCTION,
embedding_function=lambda query: request.app.state.EMBEDDING_FUNCTION(
query, user=user
),
k=form_data.k if form_data.k else request.app.state.config.TOP_K,
)
@@ -1510,6 +1542,7 @@ def process_files_batch(
docs=all_docs,
collection_name=collection_name,
add=True,
user=user,
)
# Update all files with collection name