OpenWebUI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2025-06-26 18:26:48 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'upstream-dev' into dev

Browse Source
This commit is contained in:
Jannik Streidl
2024-10-14 09:50:40 +02:00
parent f47c9c69e3 6233494ed1
commit f0f4de59eb
39 changed files with 1235 additions and 469 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
backend/open_webui/apps/openai/main.py
View File

@@ -18,7 +18,10 @@ from open_webui.config import (
OPENAI_API_KEYS,
AppConfig,
)
from open_webui.env import AIOHTTP_CLIENT_TIMEOUT
from open_webui.env import (
AIOHTTP_CLIENT_TIMEOUT,
AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST,
)
from open_webui.constants import ERROR_MESSAGES
from open_webui.env import SRC_LOG_LEVELS
@@ -179,7 +182,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
async def fetch_url(url, key):
timeout = aiohttp.ClientTimeout(total=3)
timeout = aiohttp.ClientTimeout(total=AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST)
try:
headers = {"Authorization": f"Bearer {key}"}
async with aiohttp.ClientSession(timeout=timeout, trust_env=True) as session:

89
backend/open_webui/apps/retrieval/main.py
View File

@@ -15,6 +15,9 @@ from fastapi import Depends, FastAPI, File, Form, HTTPException, UploadFile, sta
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from open_webui.apps.webui.models.knowledge import Knowledges
from open_webui.apps.retrieval.vector.connector import VECTOR_DB_CLIENT
# Document loaders
@@ -47,6 +50,8 @@ from open_webui.apps.retrieval.utils import (
from open_webui.apps.webui.models.files import Files
from open_webui.config import (
BRAVE_SEARCH_API_KEY,
TIKTOKEN_ENCODING_NAME,
RAG_TEXT_SPLITTER,
CHUNK_OVERLAP,
CHUNK_SIZE,
CONTENT_EXTRACTION_ENGINE,
@@ -102,7 +107,7 @@ from open_webui.utils.misc import (
)
from open_webui.utils.utils import get_admin_user, get_verified_user
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.text_splitter import RecursiveCharacterTextSplitter, TokenTextSplitter
from langchain_community.document_loaders import (
YoutubeLoader,
)
@@ -129,6 +134,9 @@ app.state.config.ENABLE_RAG_WEB_LOADER_SSL_VERIFICATION = (
app.state.config.CONTENT_EXTRACTION_ENGINE = CONTENT_EXTRACTION_ENGINE
app.state.config.TIKA_SERVER_URL = TIKA_SERVER_URL
app.state.config.TEXT_SPLITTER = RAG_TEXT_SPLITTER
app.state.config.TIKTOKEN_ENCODING_NAME = TIKTOKEN_ENCODING_NAME
app.state.config.CHUNK_SIZE = CHUNK_SIZE
app.state.config.CHUNK_OVERLAP = CHUNK_OVERLAP
@@ -171,9 +179,9 @@ def update_embedding_model(
auto_update: bool = False,
):
if embedding_model and app.state.config.RAG_EMBEDDING_ENGINE == "":
import sentence_transformers
from sentence_transformers import SentenceTransformer
app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
app.state.sentence_transformer_ef = SentenceTransformer(
get_model_path(embedding_model, auto_update),
device=DEVICE_TYPE,
trust_remote_code=RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE,
@@ -384,18 +392,19 @@ async def get_rag_config(user=Depends(get_admin_user)):
return {
"status": True,
"pdf_extract_images": app.state.config.PDF_EXTRACT_IMAGES,
"file": {
"max_size": app.state.config.FILE_MAX_SIZE,
"max_count": app.state.config.FILE_MAX_COUNT,
},
"content_extraction": {
"engine": app.state.config.CONTENT_EXTRACTION_ENGINE,
"tika_server_url": app.state.config.TIKA_SERVER_URL,
},
"chunk": {
"text_splitter": app.state.config.TEXT_SPLITTER,
"chunk_size": app.state.config.CHUNK_SIZE,
"chunk_overlap": app.state.config.CHUNK_OVERLAP,
},
"file": {
"max_size": app.state.config.FILE_MAX_SIZE,
"max_count": app.state.config.FILE_MAX_COUNT,
},
"youtube": {
"language": app.state.config.YOUTUBE_LOADER_LANGUAGE,
"translation": app.state.YOUTUBE_LOADER_TRANSLATION,
@@ -434,6 +443,7 @@ class ContentExtractionConfig(BaseModel):
class ChunkParamUpdateForm(BaseModel):
text_splitter: Optional[str] = None
chunk_size: int
chunk_overlap: int
@@ -493,6 +503,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
app.state.config.TIKA_SERVER_URL = form_data.content_extraction.tika_server_url
if form_data.chunk is not None:
app.state.config.TEXT_SPLITTER = form_data.chunk.text_splitter
app.state.config.CHUNK_SIZE = form_data.chunk.chunk_size
app.state.config.CHUNK_OVERLAP = form_data.chunk.chunk_overlap
@@ -539,6 +550,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
"tika_server_url": app.state.config.TIKA_SERVER_URL,
},
"chunk": {
"text_splitter": app.state.config.TEXT_SPLITTER,
"chunk_size": app.state.config.CHUNK_SIZE,
"chunk_overlap": app.state.config.CHUNK_OVERLAP,
},
@@ -599,11 +611,10 @@ class QuerySettingsForm(BaseModel):
async def update_query_settings(
form_data: QuerySettingsForm, user=Depends(get_admin_user)
):
app.state.config.RAG_TEMPLATE = (
form_data.template if form_data.template != "" else DEFAULT_RAG_TEMPLATE
)
app.state.config.RAG_TEMPLATE = form_data.template
app.state.config.TOP_K = form_data.k if form_data.k else 4
app.state.config.RELEVANCE_THRESHOLD = form_data.r if form_data.r else 0.0
app.state.config.ENABLE_RAG_HYBRID_SEARCH = (
form_data.hybrid if form_data.hybrid else False
)
@@ -648,18 +659,41 @@ def save_docs_to_vector_db(
raise ValueError(ERROR_MESSAGES.DUPLICATE_CONTENT)
if split:
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=app.state.config.CHUNK_SIZE,
chunk_overlap=app.state.config.CHUNK_OVERLAP,
add_start_index=True,
)
if app.state.config.TEXT_SPLITTER in ["", "character"]:
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=app.state.config.CHUNK_SIZE,
chunk_overlap=app.state.config.CHUNK_OVERLAP,
add_start_index=True,
)
elif app.state.config.TEXT_SPLITTER == "token":
text_splitter = TokenTextSplitter(
encoding_name=app.state.config.TIKTOKEN_ENCODING_NAME,
chunk_size=app.state.config.CHUNK_SIZE,
chunk_overlap=app.state.config.CHUNK_OVERLAP,
add_start_index=True,
)
else:
raise ValueError(ERROR_MESSAGES.DEFAULT("Invalid text splitter"))
docs = text_splitter.split_documents(docs)
if len(docs) == 0:
raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
texts = [doc.page_content for doc in docs]
metadatas = [{**doc.metadata, **(metadata if metadata else {})} for doc in docs]
metadatas = [
{
**doc.metadata,
**(metadata if metadata else {}),
"embedding_config": json.dumps(
{
"engine": app.state.config.RAG_EMBEDDING_ENGINE,
"model": app.state.config.RAG_EMBEDDING_MODEL,
}
),
}
for doc in docs
]
# ChromaDB does not like datetime formats
# for meta-data so convert them to string.
@@ -1255,6 +1289,7 @@ def delete_entries_from_collection(form_data: DeleteForm, user=Depends(get_admin
@app.post("/reset/db")
def reset_vector_db(user=Depends(get_admin_user)):
VECTOR_DB_CLIENT.reset()
Knowledges.delete_all_knowledge()
@app.post("/reset/uploads")
@@ -1277,28 +1312,6 @@ def reset_upload_dir(user=Depends(get_admin_user)) -> bool:
print(f"The directory {folder} does not exist")
except Exception as e:
print(f"Failed to process the directory {folder}. Reason: {e}")
return True
@app.post("/reset")
def reset(user=Depends(get_admin_user)) -> bool:
folder = f"{UPLOAD_DIR}"
for filename in os.listdir(folder):
file_path = os.path.join(folder, filename)
try:
if os.path.isfile(file_path) or os.path.islink(file_path):
os.unlink(file_path)
elif os.path.isdir(file_path):
shutil.rmtree(file_path)
except Exception as e:
log.error("Failed to delete %s. Reason: %s" % (file_path, e))
try:
VECTOR_DB_CLIENT.reset()
except Exception as e:
log.exception(e)
return True

47
backend/open_webui/apps/retrieval/utils.py
View File

@@ -19,6 +19,7 @@ from open_webui.apps.retrieval.vector.connector import VECTOR_DB_CLIENT
from open_webui.utils.misc import get_last_user_message
from open_webui.env import SRC_LOG_LEVELS
from open_webui.config import DEFAULT_RAG_TEMPLATE
log = logging.getLogger(__name__)
@@ -239,8 +240,13 @@ def query_collection_with_hybrid_search(
def rag_template(template: str, context: str, query: str):
count = template.count("[context]")
assert "[context]" in template, "RAG template does not contain '[context]'"
if template == "":
template = DEFAULT_RAG_TEMPLATE
if "[context]" not in template and "{{CONTEXT}}" not in template:
log.debug(
"WARNING: The RAG template does not contain the '[context]' or '{{CONTEXT}}' placeholder."
)
if "<context>" in context and "</context>" in context:
log.debug(
@@ -249,14 +255,25 @@ def rag_template(template: str, context: str, query: str):
"nothing, or the user might be trying to hack something."
)
query_placeholders = []
if "[query]" in context:
query_placeholder = f"[query-{str(uuid.uuid4())}]"
query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}"
template = template.replace("[query]", query_placeholder)
template = template.replace("[context]", context)
query_placeholders.append(query_placeholder)
if "{{QUERY}}" in context:
query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}"
template = template.replace("{{QUERY}}", query_placeholder)
query_placeholders.append(query_placeholder)
template = template.replace("[context]", context)
template = template.replace("{{CONTEXT}}", context)
template = template.replace("[query]", query)
template = template.replace("{{QUERY}}", query)
for query_placeholder in query_placeholders:
template = template.replace(query_placeholder, query)
else:
template = template.replace("[context]", context)
template = template.replace("[query]", query)
return template
@@ -375,8 +392,21 @@ def get_rag_context(
for context in relevant_contexts:
try:
if "documents" in context:
file_names = list(
set(
[
metadata["name"]
for metadata in context["metadatas"][0]
if metadata is not None and "name" in metadata
]
)
)
contexts.append(
"\n\n".join(
(", ".join(file_names) + ":\n\n")
if file_names
else ""
+ "\n\n".join(
[text for text in context["documents"][0] if text is not None]
)
)
@@ -393,6 +423,7 @@ def get_rag_context(
except Exception as e:
log.exception(e)
print(contexts, citations)
return contexts, citations

3
backend/open_webui/apps/webui/models/chats.py
View File

@@ -61,6 +61,9 @@ class ChatModel(BaseModel):
class ChatForm(BaseModel):
chat: dict
class ChatTitleMessagesForm(BaseModel):
title: str
messages: list[dict]
class ChatTitleForm(BaseModel):
title: str

10
backend/open_webui/apps/webui/models/knowledge.py
View File

@@ -154,5 +154,15 @@ class KnowledgeTable:
except Exception:
return False
def delete_all_knowledge(self) -> bool:
with get_db() as db:
try:
db.query(Knowledge).delete()
db.commit()
return True
except Exception:
return False
Knowledges = KnowledgeTable()

18
backend/open_webui/apps/webui/models/tags.py
View File

@@ -8,7 +8,7 @@ from open_webui.apps.webui.internal.db import Base, get_db
from open_webui.env import SRC_LOG_LEVELS
from pydantic import BaseModel, ConfigDict
from sqlalchemy import BigInteger, Column, String, JSON
from sqlalchemy import BigInteger, Column, String, JSON, PrimaryKeyConstraint
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -19,11 +19,14 @@ log.setLevel(SRC_LOG_LEVELS["MODELS"])
####################
class Tag(Base):
__tablename__ = "tag"
id = Column(String, primary_key=True)
id = Column(String)
name = Column(String)
user_id = Column(String)
meta = Column(JSON, nullable=True)
# Unique constraint ensuring (id, user_id) is unique, not just the `id` column
__table_args__ = (PrimaryKeyConstraint("id", "user_id", name="pk_id_user_id"),)
class TagModel(BaseModel):
id: str
@@ -57,7 +60,8 @@ class TagTable:
return TagModel.model_validate(result)
else:
return None
except Exception:
except Exception as e:
print(e)
return None
def get_tag_by_name_and_user_id(
@@ -78,11 +82,15 @@ class TagTable:
for tag in (db.query(Tag).filter_by(user_id=user_id).all())
]
def get_tags_by_ids(self, ids: list[str]) -> list[TagModel]:
def get_tags_by_ids_and_user_id(
self, ids: list[str], user_id: str
) -> list[TagModel]:
with get_db() as db:
return [
TagModel.model_validate(tag)
for tag in (db.query(Tag).filter(Tag.id.in_(ids)).all())
for tag in (
db.query(Tag).filter(Tag.id.in_(ids), Tag.user_id == user_id).all()
)
]
def delete_tag_by_name_and_user_id(self, name: str, user_id: str) -> bool:

8
backend/open_webui/apps/webui/routers/chats.py
View File

@@ -465,7 +465,7 @@ async def get_chat_tags_by_id(id: str, user=Depends(get_verified_user)):
chat = Chats.get_chat_by_id_and_user_id(id, user.id)
if chat:
tags = chat.meta.get("tags", [])
return Tags.get_tags_by_ids(tags)
return Tags.get_tags_by_ids_and_user_id(tags, user.id)
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
@@ -494,7 +494,7 @@ async def add_tag_by_id_and_tag_name(
chat = Chats.get_chat_by_id_and_user_id(id, user.id)
tags = chat.meta.get("tags", [])
return Tags.get_tags_by_ids(tags)
return Tags.get_tags_by_ids_and_user_id(tags, user.id)
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.DEFAULT()
@@ -519,7 +519,7 @@ async def delete_tag_by_id_and_tag_name(
chat = Chats.get_chat_by_id_and_user_id(id, user.id)
tags = chat.meta.get("tags", [])
return Tags.get_tags_by_ids(tags)
return Tags.get_tags_by_ids_and_user_id(tags, user.id)
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
@@ -543,7 +543,7 @@ async def delete_all_chat_tags_by_id(id: str, user=Depends(get_verified_user)):
chat = Chats.get_chat_by_id_and_user_id(id, user.id)
tags = chat.meta.get("tags", [])
return Tags.get_tags_by_ids(tags)
return Tags.get_tags_by_ids_and_user_id(tags, user.id)
else:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND

69
backend/open_webui/apps/webui/routers/utils.py
View File

@@ -1,16 +1,14 @@
import site
from pathlib import Path
import black
import markdown
from open_webui.apps.webui.models.chats import ChatTitleMessagesForm
from open_webui.config import DATA_DIR, ENABLE_ADMIN_EXPORT
from open_webui.env import FONTS_DIR
from open_webui.constants import ERROR_MESSAGES
from fastapi import APIRouter, Depends, HTTPException, Response, status
from fpdf import FPDF
from pydantic import BaseModel
from starlette.responses import FileResponse
from open_webui.utils.misc import get_gravatar_url
from open_webui.utils.pdf_generator import PDFGenerator
from open_webui.utils.utils import get_admin_user
router = APIRouter()
@@ -56,58 +54,19 @@ class ChatForm(BaseModel):
@router.post("/pdf")
async def download_chat_as_pdf(
form_data: ChatForm,
form_data: ChatTitleMessagesForm,
):
global FONTS_DIR
try:
pdf_bytes = PDFGenerator(form_data).generate_chat_pdf()
pdf = FPDF()
pdf.add_page()
# When running using `pip install` the static directory is in the site packages.
if not FONTS_DIR.exists():
FONTS_DIR = Path(site.getsitepackages()[0]) / "static/fonts"
# When running using `pip install -e .` the static directory is in the site packages.
# This path only works if `open-webui serve` is run from the root of this project.
if not FONTS_DIR.exists():
FONTS_DIR = Path("./backend/static/fonts")
pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")
pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf")
pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf")
pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf")
pdf.add_font("NotoSansSC", "", f"{FONTS_DIR}/NotoSansSC-Regular.ttf")
pdf.set_font("NotoSans", size=12)
pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP", "NotoSansSC"])
pdf.set_auto_page_break(auto=True, margin=15)
# Adjust the effective page width for multi_cell
effective_page_width = (
pdf.w - 2 * pdf.l_margin - 10
) # Subtracted an additional 10 for extra padding
# Add chat messages
for message in form_data.messages:
role = message["role"]
content = message["content"]
pdf.set_font("NotoSans", "B", size=14) # Bold for the role
pdf.multi_cell(effective_page_width, 10, f"{role.upper()}", 0, "L")
pdf.ln(1) # Extra space between messages
pdf.set_font("NotoSans", size=10) # Regular for content
pdf.multi_cell(effective_page_width, 6, content, 0, "L")
pdf.ln(1.5) # Extra space between messages
# Save the pdf with name .pdf
pdf_bytes = pdf.output()
return Response(
content=bytes(pdf_bytes),
media_type="application/pdf",
headers={"Content-Disposition": "attachment;filename=chat.pdf"},
)
return Response(
content=pdf_bytes,
media_type="application/pdf",
headers={"Content-Disposition": "attachment;filename=chat.pdf"},
)
except Exception as e:
print(e)
raise HTTPException(status_code=400, detail=str(e))
@router.get("/db/download")

16
backend/open_webui/config.py
View File

@@ -1014,6 +1014,22 @@ RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
)
RAG_TEXT_SPLITTER = PersistentConfig(
"RAG_TEXT_SPLITTER",
"rag.text_splitter",
os.environ.get("RAG_TEXT_SPLITTER", ""),
)
TIKTOKEN_CACHE_DIR = os.environ.get("TIKTOKEN_CACHE_DIR", f"{CACHE_DIR}/tiktoken")
TIKTOKEN_ENCODING_NAME = PersistentConfig(
"TIKTOKEN_ENCODING_NAME",
"rag.tiktoken_encoding_name",
os.environ.get("TIKTOKEN_ENCODING_NAME", "cl100k_base"),
)
CHUNK_SIZE = PersistentConfig(
"CHUNK_SIZE", "rag.chunk_size", int(os.environ.get("CHUNK_SIZE", "1000"))
)

2
backend/open_webui/constants.py
View File

@@ -20,7 +20,7 @@ class ERROR_MESSAGES(str, Enum):
def __str__(self) -> str:
return super().__str__()
DEFAULT = lambda err="": f"Something went wrong :/\n{err if err else ''}"
DEFAULT = lambda err="": f"Something went wrong :/\n[ERROR: {err if err else ''}]"
ENV_VAR_NOT_FOUND = "Required environment variable not found. Terminating now."
CREATE_USER_ERROR = "Oops! Something went wrong while creating your account. Please try again later. If the issue persists, contact support for assistance."
DELETE_USER_ERROR = "Oops! Something went wrong. We encountered an issue while trying to delete the user. Please give it another shot."

16
backend/open_webui/env.py
View File

@@ -230,6 +230,8 @@ if FROM_INIT_PY:
DATA_DIR = Path(os.getenv("DATA_DIR", OPEN_WEBUI_DIR / "data"))
STATIC_DIR = Path(os.getenv("STATIC_DIR", OPEN_WEBUI_DIR / "static"))
FONTS_DIR = Path(os.getenv("FONTS_DIR", OPEN_WEBUI_DIR / "static" / "fonts"))
FRONTEND_BUILD_DIR = Path(os.getenv("FRONTEND_BUILD_DIR", BASE_DIR / "build")).resolve()
@@ -361,6 +363,20 @@ else:
except Exception:
AIOHTTP_CLIENT_TIMEOUT = 300
AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = os.environ.get(
"AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST", "3"
)
if AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST == "":
AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = None
else:
try:
AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = int(
AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST
)
except Exception:
AIOHTTP_CLIENT_TIMEOUT_OPENAI_MODEL_LIST = 3
####################################
# OFFLINE_MODE
####################################

14
backend/open_webui/main.py
View File

@@ -578,7 +578,7 @@ class ChatCompletionMiddleware(BaseHTTPMiddleware):
}
# Initialize data_items to store additional data to be sent to the client
# Initalize contexts and citation
# Initialize contexts and citation
data_items = []
contexts = []
citations = []
@@ -990,11 +990,13 @@ async def get_all_models():
owned_by = model["owned_by"]
if "pipe" in model:
pipe = model["pipe"]
if "info" in model and "meta" in model["info"]:
action_ids.extend(model["info"]["meta"].get("actionIds", []))
break
if custom_model.meta:
meta = custom_model.meta.model_dump()
if "actionIds" in meta:
action_ids.extend(meta["actionIds"])
models.append(
{
"id": custom_model.id,
@@ -2277,7 +2279,7 @@ async def oauth_login(provider: str, request: Request):
# 2. If OAUTH_MERGE_ACCOUNTS_BY_EMAIL is true, find a user with the email address provided via OAuth
# - This is considered insecure in general, as OAuth providers do not always verify email addresses
# 3. If there is no user, and ENABLE_OAUTH_SIGNUP is true, create a user
# - Email addresses are considered unique, so we fail registration if the email address is alreayd taken
# - Email addresses are considered unique, so we fail registration if the email address is already taken
@app.get("/oauth/{provider}/callback")
async def oauth_callback(provider: str, request: Request, response: Response):
if provider not in OAUTH_PROVIDERS:
@@ -2385,7 +2387,7 @@ async def oauth_callback(provider: str, request: Request, response: Response):
key="token",
value=jwt_token,
httponly=True, # Ensures the cookie is not accessible via JavaScript
samesite=WEBUI_SESSION_COOKIE_SAME_SITE,
samesite=WEBUI_SESSION_COOKIE_SAME_SITE,
secure=WEBUI_SESSION_COOKIE_SECURE,
)

67
backend/open_webui/migrations/versions/3ab32c4b8f59_update_tags.py Normal file
View File

@@ -0,0 +1,67 @@
"""Update tags
Revision ID: 3ab32c4b8f59
Revises: 1af9b942657b
Create Date: 2024-10-09 21:02:35.241684
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.sql import table, select, update, column
from sqlalchemy.engine.reflection import Inspector
import json
revision = "3ab32c4b8f59"
down_revision = "1af9b942657b"
branch_labels = None
depends_on = None
def upgrade():
conn = op.get_bind()
inspector = Inspector.from_engine(conn)
# Inspecting the 'tag' table constraints and structure
existing_pk = inspector.get_pk_constraint("tag")
unique_constraints = inspector.get_unique_constraints("tag")
existing_indexes = inspector.get_indexes("tag")
print(existing_pk, unique_constraints)
with op.batch_alter_table("tag", schema=None) as batch_op:
# Drop unique constraints that could conflict with new primary key
for constraint in unique_constraints:
if constraint["name"] == "uq_id_user_id":
batch_op.drop_constraint(constraint["name"], type_="unique")
for index in existing_indexes:
if index["unique"]:
# Drop the unique index
batch_op.drop_index(index["name"])
# Drop existing primary key constraint if it exists
if existing_pk and existing_pk.get("constrained_columns"):
batch_op.drop_constraint(existing_pk["name"], type_="primary")
# Immediately after dropping the old primary key, create the new one
batch_op.create_primary_key("pk_id_user_id", ["id", "user_id"])
def downgrade():
conn = op.get_bind()
inspector = Inspector.from_engine(conn)
current_pk = inspector.get_pk_constraint("tag")
with op.batch_alter_table("tag", schema=None) as batch_op:
# Drop the current primary key first, if it matches the one we know we added in upgrade
if current_pk and "pk_id_user_id" == current_pk.get("name"):
batch_op.drop_constraint("pk_id_user_id", type_="primary")
# Restore the original primary key
batch_op.create_primary_key("pk_id", ["id"])
# Since primary key on just 'id' is restored, we now add back any unique constraints if necessary
batch_op.create_unique_constraint("uq_id_user_id", ["id", "user_id"])

319
backend/open_webui/static/assets/pdf-style.css Normal file
View File

@@ -0,0 +1,319 @@
/* HTML and Body */
@font-face {
font-family: 'NotoSans';
src: url('fonts/NotoSans-Variable.ttf');
}
@font-face {
font-family: 'NotoSansJP';
src: url('fonts/NotoSansJP-Variable.ttf');
}
@font-face {
font-family: 'NotoSansKR';
src: url('fonts/NotoSansKR-Variable.ttf');
}
@font-face {
font-family: 'NotoSansSC';
src: url('fonts/NotoSansSC-Variable.ttf');
}
@font-face {
font-family: 'NotoSansSC-Regular';
src: url('fonts/NotoSansSC-Regular.ttf');
}
html {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', 'NotoSans', 'NotoSansJP', 'NotoSansKR',
'NotoSansSC', 'STSong-Light', 'MSung-Light', 'HeiseiMin-W3', 'HYSMyeongJo-Medium', Roboto,
'Helvetica Neue', Arial, sans-serif;
font-size: 14px; /* Default font size */
line-height: 1.5;
}
*,
*::before,
*::after {
box-sizing: inherit;
}
body {
margin: 0;
color: #212529;
background-color: #fff;
width: auto;
}
/* Typography */
h1,
h2,
h3,
h4,
h5,
h6 {
font-weight: 500;
margin: 0;
}
h1 {
font-size: 2.5rem;
}
h2 {
font-size: 2rem;
}
h3 {
font-size: 1.75rem;
}
h4 {
font-size: 1.5rem;
}
h5 {
font-size: 1.25rem;
}
h6 {
font-size: 1rem;
}
p {
margin-top: 0;
margin-bottom: 1rem;
}
/* Grid System */
.container {
width: 100%;
padding-right: 15px;
padding-left: 15px;
margin-right: auto;
margin-left: auto;
}
/* Utilities */
.text-center {
text-align: center;
}
/* Additional Text Utilities */
.text-muted {
color: #6c757d; /* Muted text color */
}
/* Small Text */
small {
font-size: 80%; /* Smaller font size relative to the base */
color: #6c757d; /* Lighter text color for secondary information */
margin-bottom: 0;
margin-top: 0;
}
/* Strong Element Styles */
strong {
font-weight: bolder; /* Ensures the text is bold */
color: inherit; /* Inherits the color from its parent element */
}
/* link */
a {
color: #007bff;
text-decoration: none;
background-color: transparent;
}
a:hover {
color: #0056b3;
text-decoration: underline;
}
/* General styles for lists */
ol,
ul,
li {
padding-left: 40px; /* Increase padding to move bullet points to the right */
margin-left: 20px; /* Indent lists from the left */
}
/* Ordered list styles */
ol {
list-style-type: decimal; /* Use numbers for ordered lists */
margin-bottom: 10px; /* Space after each list */
}
ol li {
margin-bottom: 0.5rem; /* Space between ordered list items */
}
/* Unordered list styles */
ul {
list-style-type: disc; /* Use bullets for unordered lists */
margin-bottom: 10px; /* Space after each list */
}
ul li {
margin-bottom: 0.5rem; /* Space between unordered list items */
}
/* List item styles */
li {
margin-bottom: 5px; /* Space between list items */
line-height: 1.5; /* Line height for better readability */
}
/* Nested lists */
ol ol,
ol ul,
ul ol,
ul ul {
padding-left: 20px;
margin-left: 30px; /* Further indent nested lists */
margin-bottom: 0; /* Remove extra margin at the bottom of nested lists */
}
/* Code blocks */
pre {
background-color: #f4f4f4;
padding: 10px;
overflow-x: auto;
max-width: 100%; /* Ensure it doesn't overflow the page */
width: 80%; /* Set a specific width for a container-like appearance */
margin: 0 1em; /* Center the pre block */
box-sizing: border-box; /* Include padding in the width */
border: 1px solid #ccc; /* Optional: Add a border for better definition */
border-radius: 4px; /* Optional: Add rounded corners */
}
code {
font-family: 'Courier New', Courier, monospace;
background-color: #f4f4f4;
padding: 2px 4px;
border-radius: 4px;
box-sizing: border-box; /* Include padding in the width */
}
.message {
margin-top: 8px;
margin-bottom: 8px;
max-width: 100%;
overflow-wrap: break-word;
}
/* Table Styles */
table {
width: 100%;
margin-bottom: 1rem;
color: #212529;
border-collapse: collapse; /* Removes the space between borders */
}
th,
td {
margin: 0;
padding: 0.75rem;
vertical-align: top;
border-top: 1px solid #dee2e6;
}
thead th {
vertical-align: bottom;
border-bottom: 2px solid #dee2e6;
}
tbody + tbody {
border-top: 2px solid #dee2e6;
}
/* markdown-section styles */
.markdown-section blockquote,
.markdown-section h1,
.markdown-section h2,
.markdown-section h3,
.markdown-section h4,
.markdown-section h5,
.markdown-section h6,
.markdown-section p,
.markdown-section pre,
.markdown-section table,
.markdown-section ul {
/* Give most block elements margin top and bottom */
margin-top: 1rem;
}
/* Remove top margin if it's the first child */
.markdown-section blockquote:first-child,
.markdown-section h1:first-child,
.markdown-section h2:first-child,
.markdown-section h3:first-child,
.markdown-section h4:first-child,
.markdown-section h5:first-child,
.markdown-section h6:first-child,
.markdown-section p:first-child,
.markdown-section pre:first-child,
.markdown-section table:first-child,
.markdown-section ul:first-child {
margin-top: 0;
}
/* Remove top margin of <ul> following a <p> */
.markdown-section p + ul {
margin-top: 0;
}
/* Remove bottom margin of <p> if it is followed by a <ul> */
/* Note: :has is not supported in CSS, so you would need JavaScript for this behavior */
.markdown-section p {
margin-bottom: 0;
}
/* Add a rule to reset margin-bottom for <p> not followed by <ul> */
.markdown-section p + ul {
margin-top: 0;
}
/* List item styles */
.markdown-section li {
padding: 2px;
}
.markdown-section li p {
margin-bottom: 0;
padding: 0;
}
/* Avoid margins for nested lists */
.markdown-section li > ul {
margin-top: 0;
margin-bottom: 0;
}
/* Table styles */
.markdown-section table {
width: 100%;
border-collapse: collapse;
margin: 1rem 0;
}
.markdown-section th,
.markdown-section td {
border: 1px solid #ddd;
padding: 0.5rem;
text-align: left;
}
.markdown-section th {
background-color: #f2f2f2;
}
.markdown-section pre {
padding: 10px;
margin: 10px;
}
.markdown-section pre code {
position: relative;
color: rgb(172, 0, 95);
}

BIN
backend/open_webui/static/fonts/NotoSans-Variable.ttf Normal file
View File

Binary file not shown.

BIN
backend/open_webui/static/fonts/NotoSansJP-Variable.ttf Normal file
View File

Binary file not shown.

BIN
backend/open_webui/static/fonts/NotoSansKR-Variable.ttf Normal file
View File

Binary file not shown.

BIN
backend/open_webui/static/fonts/NotoSansSC-Variable.ttf Normal file
View File

Binary file not shown.

139
backend/open_webui/utils/pdf_generator.py Normal file
View File

@@ -0,0 +1,139 @@
from datetime import datetime
from io import BytesIO
from pathlib import Path
from typing import Dict, Any, List
from markdown import markdown
import site
from fpdf import FPDF
from open_webui.env import STATIC_DIR, FONTS_DIR
from open_webui.apps.webui.models.chats import ChatTitleMessagesForm
class PDFGenerator:
"""
Description:
The `PDFGenerator` class is designed to create PDF documents from chat messages.
The process involves transforming markdown content into HTML and then into a PDF format
Attributes:
- `form_data`: An instance of `ChatTitleMessagesForm` containing title and messages.
"""
def __init__(self, form_data: ChatTitleMessagesForm):
self.html_body = None
self.messages_html = None
self.form_data = form_data
self.css = Path(STATIC_DIR / "assets" / "pdf-style.css").read_text()
def format_timestamp(self, timestamp: float) -> str:
"""Convert a UNIX timestamp to a formatted date string."""
try:
date_time = datetime.fromtimestamp(timestamp)
return date_time.strftime("%Y-%m-%d, %H:%M:%S")
except (ValueError, TypeError) as e:
# Log the error if necessary
return ""
def _build_html_message(self, message: Dict[str, Any]) -> str:
"""Build HTML for a single message."""
role = message.get("role", "user")
content = message.get("content", "")
timestamp = message.get("timestamp")
model = message.get("model") if role == "assistant" else ""
date_str = self.format_timestamp(timestamp) if timestamp else ""
# extends pymdownx extension to convert markdown to html.
# - https://facelessuser.github.io/pymdown-extensions/usage_notes/
html_content = markdown(content, extensions=["pymdownx.extra"])
html_message = f"""
<div class="message">
<small> {date_str} </small>
<div>
<h2>
<strong>{role.title()}</strong>
<small class="text-muted">{model}</small>
</h2>
</div>
<div class="markdown-section">
{html_content}
</div>
</div>
"""
return html_message
def _generate_html_body(self) -> str:
"""Generate the full HTML body for the PDF."""
return f"""
<html>
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
</head>
<body>
<div class="container">
<div class="text-center">
<h1>{self.form_data.title}</h1>
</div>
<div>
{self.messages_html}
</div>
</div>
</body>
</html>
"""
def generate_chat_pdf(self) -> bytes:
"""
Generate a PDF from chat messages.
"""
try:
global FONTS_DIR
pdf = FPDF()
pdf.add_page()
# When running using `pip install` the static directory is in the site packages.
if not FONTS_DIR.exists():
FONTS_DIR = Path(site.getsitepackages()[0]) / "static/fonts"
# When running using `pip install -e .` the static directory is in the site packages.
# This path only works if `open-webui serve` is run from the root of this project.
if not FONTS_DIR.exists():
FONTS_DIR = Path("./backend/static/fonts")
pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")
pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf")
pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf")
pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf")
pdf.add_font("NotoSansSC", "", f"{FONTS_DIR}/NotoSansSC-Regular.ttf")
pdf.set_font("NotoSans", size=12)
pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP", "NotoSansSC"])
pdf.set_auto_page_break(auto=True, margin=15)
# Build HTML messages
messages_html_list: List[str] = [
self._build_html_message(msg) for msg in self.form_data.messages
]
self.messages_html = "<div>" + "".join(messages_html_list) + "</div>"
# Generate full HTML body
self.html_body = self._generate_html_body()
pdf.write_html(self.html_body)
# Save the pdf with name .pdf
pdf_bytes = pdf.output()
return bytes(pdf_bytes)
except Exception as e:
raise e

4
backend/requirements.txt
View File

@@ -44,13 +44,15 @@ chromadb==0.5.9
pymilvus==2.4.7
qdrant-client~=1.12.0
sentence-transformers==3.0.1
sentence-transformers==3.2.0
colbert-ai==0.2.21
einops==0.8.0
ftfy==6.2.3
pypdf==4.3.1
xhtml2pdf==0.2.16
pymdown-extensions==10.11.2
docx2txt==0.8
python-pptx==1.0.0
unstructured==0.15.9