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

chore: format

Browse Source
This commit is contained in:
Timothy Jaeryang Baek
2026-02-11 16:24:11 -06:00
parent 89fddcc741
commit f376d4f378
202 changed files with 8328 additions and 2046 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/retrieval/models/external.py
-1
View File
@@ -8,7 +8,6 @@ from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS, REQUESTS_VERIFY
from open_webui.retrieval.models.base_reranker import BaseReranker
from open_webui.utils.headers import include_user_info_headers
log = logging.getLogger(__name__)
backend/open_webui/retrieval/utils.py
+3 -1
View File
@@ -695,7 +695,9 @@ async def agenerate_azure_openai_batch_embeddings(
trust_env=True, timeout=aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT)
) as session:
async with session.post(
full_url, headers=headers, json=form_data,
full_url,
headers=headers,
json=form_data,
ssl=AIOHTTP_CLIENT_SESSION_SSL,
) as r:
r.raise_for_status()
backend/open_webui/retrieval/vector/dbs/oracle23ai.py
+6 -12
View File
@@ -256,8 +256,7 @@ class Oracle23aiClient(VectorDBBase):
with connection.cursor() as cursor:
try:
log.info("Creating Table document_chunk")
cursor.execute(
"""
cursor.execute("""
BEGIN
EXECUTE IMMEDIATE '
CREATE TABLE IF NOT EXISTS document_chunk (
@@ -274,12 +273,10 @@ class Oracle23aiClient(VectorDBBase):
RAISE;
END IF;
END;
"""
)
""")
log.info("Creating Index document_chunk_collection_name_idx")
cursor.execute(
"""
cursor.execute("""
BEGIN
EXECUTE IMMEDIATE '
CREATE INDEX IF NOT EXISTS document_chunk_collection_name_idx
@@ -291,12 +288,10 @@ class Oracle23aiClient(VectorDBBase):
RAISE;
END IF;
END;
"""
)
""")
log.info("Creating VECTOR INDEX document_chunk_vector_ivf_idx")
cursor.execute(
"""
cursor.execute("""
BEGIN
EXECUTE IMMEDIATE '
CREATE VECTOR INDEX IF NOT EXISTS document_chunk_vector_ivf_idx
@@ -312,8 +307,7 @@ class Oracle23aiClient(VectorDBBase):
RAISE;
END IF;
END;
"""
)
""")
connection.commit()
log.info("Database initialization completed successfully.")
backend/open_webui/retrieval/vector/dbs/pgvector.py
+10 -25
View File
@@ -51,7 +51,6 @@ from open_webui.config import (
PGVECTOR_USE_HALFVEC,
)
VECTOR_LENGTH = PGVECTOR_INITIALIZE_MAX_VECTOR_LENGTH
USE_HALFVEC = PGVECTOR_USE_HALFVEC
@@ -121,34 +120,26 @@ class PgvectorClient(VectorDBBase):
# Ensure the pgvector extension is available
# Use a conditional check to avoid permission issues on Azure PostgreSQL
if PGVECTOR_CREATE_EXTENSION:
self.session.execute(
text(
"""
self.session.execute(text("""
DO $$
BEGIN
IF NOT EXISTS (SELECT 1 FROM pg_extension WHERE extname = 'vector') THEN
CREATE EXTENSION IF NOT EXISTS vector;
END IF;
END $$;
"""
)
)
"""))
if PGVECTOR_PGCRYPTO:
# Ensure the pgcrypto extension is available for encryption
# Use a conditional check to avoid permission issues on Azure PostgreSQL
self.session.execute(
text(
"""
self.session.execute(text("""
DO $$
BEGIN
IF NOT EXISTS (SELECT 1 FROM pg_extension WHERE extname = 'pgcrypto') THEN
CREATE EXTENSION IF NOT EXISTS pgcrypto;
END IF;
END $$;
"""
)
)
"""))
if not PGVECTOR_PGCRYPTO_KEY:
raise ValueError(
@@ -216,15 +207,13 @@ class PgvectorClient(VectorDBBase):
def _ensure_vector_index(self, index_method: str, index_options: str) -> None:
index_name = "idx_document_chunk_vector"
existing_index_def = self.session.execute(
text(
"""
text("""
SELECT indexdef
FROM pg_indexes
WHERE schemaname = current_schema()
AND tablename = 'document_chunk'
AND indexname = :index_name
"""
),
"""),
{"index_name": index_name},
).scalar()
@@ -310,8 +299,7 @@ class PgvectorClient(VectorDBBase):
# Ensure metadata is converted to its JSON text representation
json_metadata = json.dumps(item["metadata"])
self.session.execute(
text(
"""
text("""
INSERT INTO document_chunk
(id, vector, collection_name, text, vmetadata)
VALUES (
@@ -320,8 +308,7 @@ class PgvectorClient(VectorDBBase):
pgp_sym_encrypt(:metadata_text, :key)
)
ON CONFLICT (id) DO NOTHING
"""
),
"""),
{
"id": item["id"],
"vector": vector,
@@ -363,8 +350,7 @@ class PgvectorClient(VectorDBBase):
vector = self.adjust_vector_length(item["vector"])
json_metadata = json.dumps(item["metadata"])
self.session.execute(
text(
"""
text("""
INSERT INTO document_chunk
(id, vector, collection_name, text, vmetadata)
VALUES (
@@ -377,8 +363,7 @@ class PgvectorClient(VectorDBBase):
collection_name = EXCLUDED.collection_name,
text = EXCLUDED.text,
vmetadata = EXCLUDED.vmetadata
"""
),
"""),
{
"id": item["id"],
"vector": vector,
backend/open_webui/retrieval/vector/dbs/pinecone.py
-1
View File
@@ -33,7 +33,6 @@ from open_webui.config import (
)
from open_webui.retrieval.vector.utils import process_metadata
NO_LIMIT = 10000 # Reasonable limit to avoid overwhelming the system
BATCH_SIZE = 100 # Recommended batch size for Pinecone operations
backend/open_webui/retrieval/web/external.py
-1
View File
@@ -10,7 +10,6 @@ from open_webui.retrieval.web.main import SearchResult, get_filtered_results
from open_webui.utils.headers import include_user_info_headers
from open_webui.env import FORWARD_SESSION_INFO_HEADER_CHAT_ID
log = logging.getLogger(__name__)
backend/open_webui/retrieval/web/firecrawl.py
-1
View File
@@ -3,7 +3,6 @@ from typing import Optional, List
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
log = logging.getLogger(__name__)
backend/open_webui/retrieval/web/perplexity_search.py
-1
View File
@@ -5,7 +5,6 @@ import requests
from open_webui.retrieval.web.main import SearchResult, get_filtered_results
from open_webui.utils.headers import include_user_info_headers
log = logging.getLogger(__name__)
backend/open_webui/retrieval/web/yandex.py
+32 -16
View File
@@ -31,14 +31,14 @@ def xml_element_contents_to_string(element: Element) -> str:
def search_yandex(
request: Request,
yandex_search_url: str,
yandex_search_api_key: str,
yandex_search_config: str,
query: str,
count: int,
filter_list: Optional[List[str]] = None,
user=None,
request: Request,
yandex_search_url: str,
yandex_search_api_key: str,
yandex_search_config: str,
query: str,
count: int,
filter_list: Optional[List[str]] = None,
user=None,
) -> List[SearchResult]:
try:
headers = {
@@ -73,7 +73,11 @@ def search_yandex(
payload["groupSpec"]["docsInGroup"] = 1
response = requests.post(
"https://searchapi.api.cloud.yandex.net/v2/web/search" if yandex_search_url == "" else yandex_search_url,
(
"https://searchapi.api.cloud.yandex.net/v2/web/search"
if yandex_search_url == ""
else yandex_search_url
),
headers=headers,
json=payload,
)
@@ -84,18 +88,28 @@ def search_yandex(
if "rawData" not in response_body:
raise Exception(f"No `rawData` in response body: {response_body}")
search_result_body_bytes = base64.decodebytes(bytes(response_body["rawData"], "utf-8"))
search_result_body_bytes = base64.decodebytes(
bytes(response_body["rawData"], "utf-8")
)
doc_root = ET.parse(io.BytesIO(search_result_body_bytes))
results = []
for group in doc_root.findall("response/results/grouping/group"):
results.append({
"url": xml_element_contents_to_string(group.find("doc/url")).strip("\n"),
"title": xml_element_contents_to_string(group.find("doc/title")).strip("\n"),
"snippet": xml_element_contents_to_string(group.find("doc/passages/passage")),
})
results.append(
{
"url": xml_element_contents_to_string(group.find("doc/url")).strip(
"\n"
),
"title": xml_element_contents_to_string(
group.find("doc/title")
).strip("\n"),
"snippet": xml_element_contents_to_string(
group.find("doc/passages/passage")
),
}
)
results = get_filtered_results(results, filter_list)
@@ -140,7 +154,9 @@ if __name__ == "__main__":
),
os.environ.get("YANDEX_WEB_SEARCH_URL", ""),
os.environ.get("YANDEX_WEB_SEARCH_API_KEY", ""),
os.environ.get("YANDEX_WEB_SEARCH_CONFIG", "{\"query\": {\"searchType\": \"SEARCH_TYPE_COM\"}}"),
os.environ.get(
"YANDEX_WEB_SEARCH_CONFIG", '{"query": {"searchType": "SEARCH_TYPE_COM"}}'
),
"TOP movies of the past year",
3,
)