Mirrors/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-16 11:57:51 +01:00
Code Issues Packages Projects Releases Wiki Activity

Add user related headers when calling an external embedding api

Browse Source
This commit is contained in:
Didier FOURNOUT
2025-01-29 10:55:52 +00:00
parent b72150c881
commit 6ca295ec59
6 changed files with 70 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
backend/open_webui/retrieval/utils.py
View File

@@ -15,8 +15,9 @@ from langchain_core.documents import Document
from open_webui.config import VECTOR_DB
from open_webui.retrieval.vector.connector import VECTOR_DB_CLIENT
from open_webui.utils.misc import get_last_user_message
from open_webui.models.users import UserModel
from open_webui.env import SRC_LOG_LEVELS, OFFLINE_MODE
from open_webui.env import SRC_LOG_LEVELS, OFFLINE_MODE, ENABLE_FORWARD_USER_INFO_HEADERS
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["RAG"])
@@ -64,6 +65,7 @@ def query_doc(
collection_name: str,
query_embedding: list[float],
k: int,
user: UserModel=None
):
try:
result = VECTOR_DB_CLIENT.search(
@@ -256,29 +258,32 @@ def get_embedding_function(
embedding_function,
url,
key,
embedding_batch_size,
embedding_batch_size
):
if embedding_engine == "":
return lambda query: embedding_function.encode(query).tolist()
return lambda query, user=None: embedding_function.encode(query).tolist()
elif embedding_engine in ["ollama", "openai"]:
func = lambda query: generate_embeddings(
func = lambda query, user=None: generate_embeddings(
engine=embedding_engine,
model=embedding_model,
text=query,
url=url,
key=key,
user=user
)
def generate_multiple(query, func):
def generate_multiple(query, user, func):
if isinstance(query, list):
embeddings = []
for i in range(0, len(query), embedding_batch_size):
embeddings.extend(func(query[i : i + embedding_batch_size]))
embeddings.extend(func(query[i : i + embedding_batch_size], user=user))
return embeddings
else:
return func(query)
return func(query, user)
return lambda query: generate_multiple(query, func)
return lambda query, user=None: generate_multiple(query, user, func)
else:
raise ValueError(f"Unknown embedding engine: {embedding_engine}")
def get_sources_from_files(
@@ -423,7 +428,7 @@ def get_model_path(model: str, update_model: bool = False):
def generate_openai_batch_embeddings(
model: str, texts: list[str], url: str = "https://api.openai.com/v1", key: str = ""
model: str, texts: list[str], url: str = "https://api.openai.com/v1", key: str = "", user: UserModel = None
) -> Optional[list[list[float]]]:
try:
r = requests.post(
@@ -431,6 +436,16 @@ def generate_openai_batch_embeddings(
headers={
"Content-Type": "application/json",
"Authorization": f"Bearer {key}",
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
}
if ENABLE_FORWARD_USER_INFO_HEADERS and user
else {}
),
},
json={"input": texts, "model": model},
)
@@ -446,7 +461,7 @@ def generate_openai_batch_embeddings(
def generate_ollama_batch_embeddings(
model: str, texts: list[str], url: str, key: str = ""
model: str, texts: list[str], url: str, key: str = "", user: UserModel = None
) -> Optional[list[list[float]]]:
try:
r = requests.post(
@@ -454,6 +469,16 @@ def generate_ollama_batch_embeddings(
headers={
"Content-Type": "application/json",
"Authorization": f"Bearer {key}",
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
}
if ENABLE_FORWARD_USER_INFO_HEADERS
else {}
),
},
json={"input": texts, "model": model},
)
@@ -472,22 +497,23 @@ def generate_ollama_batch_embeddings(
def generate_embeddings(engine: str, model: str, text: Union[str, list[str]], **kwargs):
url = kwargs.get("url", "")
key = kwargs.get("key", "")
user = kwargs.get("user")
if engine == "ollama":
if isinstance(text, list):
embeddings = generate_ollama_batch_embeddings(
**{"model": model, "texts": text, "url": url, "key": key}
**{"model": model, "texts": text, "url": url, "key": key, "user": user}
)
else:
embeddings = generate_ollama_batch_embeddings(
**{"model": model, "texts": [text], "url": url, "key": key}
**{"model": model, "texts": [text], "url": url, "key": key, "user": user}
)
return embeddings[0] if isinstance(text, str) else embeddings
elif engine == "openai":
if isinstance(text, list):
embeddings = generate_openai_batch_embeddings(model, text, url, key)
embeddings = generate_openai_batch_embeddings(model, text, url, key, user)
else:
embeddings = generate_openai_batch_embeddings(model, [text], url, key)
embeddings = generate_openai_batch_embeddings(model, [text], url, key, user)
return embeddings[0] if isinstance(text, str) else embeddings