Merge pull request #2245 from tcztzy/dev

changed: packaging for publishing

.github/workflows/ci.yml

@@ -0,0 +1,31 @@
+name: Release
+
+on:
+  push:
+    branches:
+      - main # or whatever branch you want to use
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    environment:
+        name: pypi
+        url: https://pypi.org/p/open-webui
+    permissions:
+        id-token: write
+    steps:
+        - name: Checkout repository
+          uses: actions/checkout@v4
+        - uses: actions/setup-node@v4
+          with:
+            node-version: 18
+        - uses: actions/setup-python@v5
+          with:
+            python-version: 3.11
+        - name: Build
+          run: |
+            python -m pip install --upgrade pip
+            pip install build
+            python -m build .
+        - name: Publish package distributions to PyPI
+          uses: pypa/gh-action-pypi-publish@release/v1

backend/apps/web/internal/db.py

@@ -1,7 +1,7 @@
 from peewee import *
 from peewee_migrate import Router
 from playhouse.db_url import connect
-from config import SRC_LOG_LEVELS, DATA_DIR, DATABASE_URL
+from config import SRC_LOG_LEVELS, DATA_DIR, DATABASE_URL, BACKEND_DIR
 import os
 import logging
 
@@ -18,6 +18,8 @@ else:
 
 DB = connect(DATABASE_URL)
 log.info(f"Connected to a {DB.__class__.__name__} database.")
-router = Router(DB, migrate_dir="apps/web/internal/migrations", logger=log)
+router = Router(
+    DB, migrate_dir=BACKEND_DIR / "apps" / "web" / "internal" / "migrations", logger=log
+)
 router.run()
 DB.connect(reuse_if_open=True)

backend/config.py

@@ -1,6 +1,8 @@
 import os
 import sys
 import logging
+import importlib.metadata
+import pkgutil
 import chromadb
 from chromadb import Settings
 from base64 import b64encode
@@ -22,10 +24,13 @@ from constants import ERROR_MESSAGES
 # Load .env file
 ####################################
 
+BACKEND_DIR = Path(__file__).parent  # the path containing this file
+BASE_DIR = BACKEND_DIR.parent  # the path containing the backend/
+
 try:
     from dotenv import load_dotenv, find_dotenv
 
-    load_dotenv(find_dotenv("../.env"))
+    load_dotenv(find_dotenv(str(BASE_DIR / ".env")))
 except ImportError:
     print("dotenv not installed, skipping...")
 
@@ -87,9 +92,11 @@ WEBUI_FAVICON_URL = "https://openwebui.com/favicon.png"
 ENV = os.environ.get("ENV", "dev")
 
 try:
-    with open(f"../package.json", "r") as f:
+    PACKAGE_DATA = json.loads((BASE_DIR / "package.json").read_text())
-        PACKAGE_DATA = json.load(f)
 except:
+    try:
+        PACKAGE_DATA = {"version": importlib.metadata.version("open-webui")}
+    except importlib.metadata.PackageNotFoundError:
         PACKAGE_DATA = {"version": "0.0.0"}
 
 VERSION = PACKAGE_DATA["version"]
@@ -115,10 +122,10 @@ def parse_section(section):
 
 
 try:
-    with open("../CHANGELOG.md", "r") as file:
+    changelog_content = (BASE_DIR / "CHANGELOG.md").read_text()
-        changelog_content = file.read()
 except:
-    changelog_content = ""
+    changelog_content = (pkgutil.get_data("open_webui", "CHANGELOG.md") or b"").decode()
+
 
 # Convert markdown content to HTML
 html_content = markdown.markdown(changelog_content)
@@ -164,12 +171,11 @@ WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.100")
 # DATA/FRONTEND BUILD DIR
 ####################################
 
-DATA_DIR = str(Path(os.getenv("DATA_DIR", "./data")).resolve())
+DATA_DIR = Path(os.getenv("DATA_DIR", BACKEND_DIR / "data")).resolve()
-FRONTEND_BUILD_DIR = str(Path(os.getenv("FRONTEND_BUILD_DIR", "../build")))
+FRONTEND_BUILD_DIR = Path(os.getenv("FRONTEND_BUILD_DIR", BASE_DIR / "build")).resolve()
 
 try:
-    with open(f"{DATA_DIR}/config.json", "r") as f:
+    CONFIG_DATA = json.loads((DATA_DIR / "config.json").read_text())
-        CONFIG_DATA = json.load(f)
 except:
     CONFIG_DATA = {}
 
@@ -279,11 +285,11 @@ JWT_EXPIRES_IN = PersistentConfig(
 # Static DIR
 ####################################
 
-STATIC_DIR = str(Path(os.getenv("STATIC_DIR", "./static")).resolve())
+STATIC_DIR = Path(os.getenv("STATIC_DIR", BACKEND_DIR / "static")).resolve()
 
-frontend_favicon = f"{FRONTEND_BUILD_DIR}/favicon.png"
+frontend_favicon = FRONTEND_BUILD_DIR / "favicon.png"
-if os.path.exists(frontend_favicon):
+if frontend_favicon.exists():
-    shutil.copyfile(frontend_favicon, f"{STATIC_DIR}/favicon.png")
+    shutil.copyfile(frontend_favicon, STATIC_DIR / "favicon.png")
 else:
     logging.warning(f"Frontend favicon not found at {frontend_favicon}")
 

backend/open_webui/__init__.py

@@ -0,0 +1,60 @@
+import base64
+import os
+import random
+from pathlib import Path
+
+import typer
+import uvicorn
+
+app = typer.Typer()
+
+KEY_FILE = Path.cwd() / ".webui_secret_key"
+if (frontend_build_dir := Path(__file__).parent / "frontend").exists():
+    os.environ["FRONTEND_BUILD_DIR"] = str(frontend_build_dir)
+
+
+@app.command()
+def serve(
+    host: str = "0.0.0.0",
+    port: int = 8080,
+):
+    if os.getenv("WEBUI_SECRET_KEY") is None:
+        typer.echo(
+            "Loading WEBUI_SECRET_KEY from file, not provided as an environment variable."
+        )
+        if not KEY_FILE.exists():
+            typer.echo(f"Generating a new secret key and saving it to {KEY_FILE}")
+            KEY_FILE.write_bytes(base64.b64encode(random.randbytes(12)))
+        typer.echo(f"Loading WEBUI_SECRET_KEY from {KEY_FILE}")
+        os.environ["WEBUI_SECRET_KEY"] = KEY_FILE.read_text()
+
+    if os.getenv("USE_CUDA_DOCKER", "false") == "true":
+        typer.echo(
+            "CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries."
+        )
+        LD_LIBRARY_PATH = os.getenv("LD_LIBRARY_PATH", "").split(":")
+        os.environ["LD_LIBRARY_PATH"] = ":".join(
+            LD_LIBRARY_PATH
+            + [
+                "/usr/local/lib/python3.11/site-packages/torch/lib",
+                "/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib",
+            ]
+        )
+    import main  # we need set environment variables before importing main
+
+    uvicorn.run(main.app, host=host, port=port, forwarded_allow_ips="*")
+
+
+@app.command()
+def dev(
+    host: str = "0.0.0.0",
+    port: int = 8080,
+    reload: bool = True,
+):
+    uvicorn.run(
+        "main:app", host=host, port=port, reload=reload, forwarded_allow_ips="*"
+    )
+
+
+if __name__ == "__main__":
+    app()

hatch_build.py

@@ -0,0 +1,21 @@
+# noqa: INP001
+import shutil
+import subprocess
+from sys import stderr
+
+from hatchling.builders.hooks.plugin.interface import BuildHookInterface
+
+
+class CustomBuildHook(BuildHookInterface):
+    def initialize(self, version, build_data):
+        super().initialize(version, build_data)
+        stderr.write(">>> Building Open Webui frontend\n")
+        npm = shutil.which("npm")
+        if npm is None:
+            raise RuntimeError(
+                "NodeJS `npm` is required for building Open Webui but it was not found"
+            )
+        stderr.write("### npm install\n")
+        subprocess.run([npm, "install"], check=True)  # noqa: S603
+        stderr.write("\n### npm run build\n")
+        subprocess.run([npm, "run", "build"], check=True)  # noqa: S603

pyproject.toml

@@ -0,0 +1,115 @@
+[project]
+name = "open-webui"
+description = "Open WebUI (Formerly Ollama WebUI)"
+authors = [
+    { name = "Timothy Jaeryang Baek", email = "jaeryang_baek@sfu.ca" }
+]
+license = { file = "LICENSE" }
+dependencies = [
+    "fastapi==0.109.2",
+    "uvicorn[standard]==0.22.0",
+    "pydantic==2.7.1",
+    "python-multipart==0.0.9",
+
+    "Flask==3.0.3",
+    "Flask-Cors==4.0.0",
+
+    "python-socketio==5.11.2",
+    "python-jose==3.3.0",
+    "passlib[bcrypt]==1.7.4",
+
+    "requests==2.31.0",
+    "aiohttp==3.9.5",
+    "peewee==3.17.3",
+    "peewee-migrate==1.12.2",
+    "psycopg2-binary==2.9.9",
+    "PyMySQL==1.1.0",
+    "bcrypt==4.1.2",
+
+    "litellm[proxy]==1.35.28",
+
+    "boto3==1.34.95",
+
+    "argon2-cffi==23.1.0",
+    "APScheduler==3.10.4",
+    "google-generativeai==0.5.2",
+
+    "langchain==0.1.16",
+    "langchain-community==0.0.34",
+    "langchain-chroma==0.1.0",
+
+    "fake-useragent==1.5.1",
+    "chromadb==0.4.24",
+    "sentence-transformers==2.7.0",
+    "pypdf==4.2.0",
+    "docx2txt==0.8",
+    "unstructured==0.11.8",
+    "Markdown==3.6",
+    "pypandoc==1.13",
+    "pandas==2.2.2",
+    "openpyxl==3.1.2",
+    "pyxlsb==1.0.10",
+    "xlrd==2.0.1",
+    "validators==0.28.1",
+
+    "opencv-python-headless==4.9.0.80",
+    "rapidocr-onnxruntime==1.2.3",
+
+    "fpdf2==2.7.8",
+    "rank-bm25==0.2.2",
+
+    "faster-whisper==1.0.1",
+
+    "PyJWT[crypto]==2.8.0",
+
+    "black==24.4.2",
+    "langfuse==2.27.3",
+    "youtube-transcript-api==0.6.2",
+    "pytube",
+]
+readme = "README.md"
+requires-python = ">= 3.11, < 3.12.0a1"
+dynamic = ["version"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.11",
+    "Topic :: Communications :: Chat",
+    "Topic :: Multimedia",
+]
+
+[project.scripts]
+open-webui = "open_webui:app"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.rye]
+managed = true
+dev-dependencies = []
+
+[tool.hatch.metadata]
+allow-direct-references = true
+
+[tool.hatch.version]
+path = "package.json"
+pattern = '"version":\s*"(?P<version>[^"]+)"'
+
+[tool.hatch.build.hooks.custom]  # keep this for reading hooks from `hatch_build.py`
+
+[tool.hatch.build.targets.wheel]
+sources = ["backend"]
+exclude = [
+    ".dockerignore",
+    ".gitignore",
+    ".webui_secret_key",
+    "dev.sh",
+    "requirements.txt",
+    "start.sh",
+    "start_windows.bat",
+    "webui.db",
+    "chroma.sqlite3",
+]
+force-include = { "CHANGELOG.md" = "open_webui/CHANGELOG.md", build = "open_webui/frontend" }

requirements-dev.lock

@@ -0,0 +1,680 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+#   with-sources: false
+
+-e file:.
+aiohttp==3.9.5
+    # via langchain
+    # via langchain-community
+    # via litellm
+    # via open-webui
+aiosignal==1.3.1
+    # via aiohttp
+annotated-types==0.6.0
+    # via pydantic
+anyio==4.3.0
+    # via httpx
+    # via openai
+    # via starlette
+    # via watchfiles
+apscheduler==3.10.4
+    # via litellm
+    # via open-webui
+argon2-cffi==23.1.0
+    # via open-webui
+argon2-cffi-bindings==21.2.0
+    # via argon2-cffi
+asgiref==3.8.1
+    # via opentelemetry-instrumentation-asgi
+attrs==23.2.0
+    # via aiohttp
+av==11.0.0
+    # via faster-whisper
+backoff==2.2.1
+    # via langfuse
+    # via litellm
+    # via posthog
+    # via unstructured
+bcrypt==4.1.2
+    # via chromadb
+    # via open-webui
+    # via passlib
+beautifulsoup4==4.12.3
+    # via unstructured
+bidict==0.23.1
+    # via python-socketio
+black==24.4.2
+    # via open-webui
+blinker==1.8.2
+    # via flask
+boto3==1.34.95
+    # via open-webui
+botocore==1.34.103
+    # via boto3
+    # via s3transfer
+build==1.2.1
+    # via chromadb
+cachetools==5.3.3
+    # via google-auth
+certifi==2024.2.2
+    # via httpcore
+    # via httpx
+    # via kubernetes
+    # via pulsar-client
+    # via requests
+    # via unstructured-client
+cffi==1.16.0
+    # via argon2-cffi-bindings
+    # via cryptography
+chardet==5.2.0
+    # via unstructured
+charset-normalizer==3.3.2
+    # via requests
+    # via unstructured-client
+chroma-hnswlib==0.7.3
+    # via chromadb
+chromadb==0.4.24
+    # via langchain-chroma
+    # via open-webui
+click==8.1.7
+    # via black
+    # via flask
+    # via litellm
+    # via nltk
+    # via peewee-migrate
+    # via rq
+    # via typer
+    # via uvicorn
+coloredlogs==15.0.1
+    # via onnxruntime
+cryptography==42.0.7
+    # via litellm
+    # via pyjwt
+ctranslate2==4.2.1
+    # via faster-whisper
+dataclasses-json==0.6.6
+    # via langchain
+    # via langchain-community
+    # via unstructured
+    # via unstructured-client
+deepdiff==7.0.1
+    # via unstructured-client
+defusedxml==0.7.1
+    # via fpdf2
+deprecated==1.2.14
+    # via opentelemetry-api
+    # via opentelemetry-exporter-otlp-proto-grpc
+distro==1.9.0
+    # via openai
+dnspython==2.6.1
+    # via email-validator
+docx2txt==0.8
+    # via open-webui
+ecdsa==0.19.0
+    # via python-jose
+email-validator==2.1.1
+    # via pydantic
+emoji==2.11.1
+    # via unstructured
+et-xmlfile==1.1.0
+    # via openpyxl
+fake-useragent==1.5.1
+    # via open-webui
+fastapi==0.109.2
+    # via chromadb
+    # via fastapi-sso
+    # via langchain-chroma
+    # via litellm
+    # via open-webui
+fastapi-sso==0.10.0
+    # via litellm
+faster-whisper==1.0.1
+    # via open-webui
+filelock==3.14.0
+    # via huggingface-hub
+    # via torch
+    # via transformers
+filetype==1.2.0
+    # via unstructured
+flask==3.0.3
+    # via flask-cors
+    # via open-webui
+flask-cors==4.0.0
+    # via open-webui
+flatbuffers==24.3.25
+    # via onnxruntime
+fonttools==4.51.0
+    # via fpdf2
+fpdf2==2.7.8
+    # via open-webui
+frozenlist==1.4.1
+    # via aiohttp
+    # via aiosignal
+fsspec==2024.3.1
+    # via huggingface-hub
+    # via torch
+google-ai-generativelanguage==0.6.2
+    # via google-generativeai
+google-api-core==2.19.0
+    # via google-ai-generativelanguage
+    # via google-api-python-client
+    # via google-generativeai
+google-api-python-client==2.129.0
+    # via google-generativeai
+google-auth==2.29.0
+    # via google-ai-generativelanguage
+    # via google-api-core
+    # via google-api-python-client
+    # via google-auth-httplib2
+    # via google-generativeai
+    # via kubernetes
+google-auth-httplib2==0.2.0
+    # via google-api-python-client
+google-generativeai==0.5.2
+    # via open-webui
+googleapis-common-protos==1.63.0
+    # via google-api-core
+    # via grpcio-status
+    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio==1.63.0
+    # via chromadb
+    # via google-api-core
+    # via grpcio-status
+    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio-status==1.62.2
+    # via google-api-core
+gunicorn==21.2.0
+    # via litellm
+h11==0.14.0
+    # via httpcore
+    # via uvicorn
+    # via wsproto
+httpcore==1.0.5
+    # via httpx
+httplib2==0.22.0
+    # via google-api-python-client
+    # via google-auth-httplib2
+httptools==0.6.1
+    # via uvicorn
+httpx==0.27.0
+    # via fastapi-sso
+    # via langfuse
+    # via openai
+huggingface-hub==0.23.0
+    # via faster-whisper
+    # via sentence-transformers
+    # via tokenizers
+    # via transformers
+humanfriendly==10.0
+    # via coloredlogs
+idna==3.7
+    # via anyio
+    # via email-validator
+    # via httpx
+    # via langfuse
+    # via requests
+    # via unstructured-client
+    # via yarl
+importlib-metadata==7.0.0
+    # via litellm
+    # via opentelemetry-api
+importlib-resources==6.4.0
+    # via chromadb
+itsdangerous==2.2.0
+    # via flask
+jinja2==3.1.4
+    # via flask
+    # via litellm
+    # via torch
+jmespath==1.0.1
+    # via boto3
+    # via botocore
+joblib==1.4.2
+    # via nltk
+    # via scikit-learn
+jsonpatch==1.33
+    # via langchain
+    # via langchain-core
+jsonpath-python==1.0.6
+    # via unstructured-client
+jsonpointer==2.4
+    # via jsonpatch
+kubernetes==29.0.0
+    # via chromadb
+langchain==0.1.16
+    # via open-webui
+langchain-chroma==0.1.0
+    # via open-webui
+langchain-community==0.0.34
+    # via langchain
+    # via open-webui
+langchain-core==0.1.52
+    # via langchain
+    # via langchain-chroma
+    # via langchain-community
+    # via langchain-text-splitters
+langchain-text-splitters==0.0.1
+    # via langchain
+langdetect==1.0.9
+    # via unstructured
+langfuse==2.27.3
+    # via open-webui
+langsmith==0.1.57
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+litellm==1.35.28
+    # via open-webui
+lxml==5.2.2
+    # via unstructured
+markdown==3.6
+    # via open-webui
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via jinja2
+    # via werkzeug
+marshmallow==3.21.2
+    # via dataclasses-json
+    # via unstructured-client
+mdurl==0.1.2
+    # via markdown-it-py
+mmh3==4.1.0
+    # via chromadb
+monotonic==1.6
+    # via posthog
+mpmath==1.3.0
+    # via sympy
+multidict==6.0.5
+    # via aiohttp
+    # via yarl
+mypy-extensions==1.0.0
+    # via black
+    # via typing-inspect
+    # via unstructured-client
+networkx==3.3
+    # via torch
+nltk==3.8.1
+    # via unstructured
+numpy==1.26.4
+    # via chroma-hnswlib
+    # via chromadb
+    # via ctranslate2
+    # via langchain
+    # via langchain-chroma
+    # via langchain-community
+    # via onnxruntime
+    # via opencv-python
+    # via opencv-python-headless
+    # via pandas
+    # via rank-bm25
+    # via rapidocr-onnxruntime
+    # via scikit-learn
+    # via scipy
+    # via sentence-transformers
+    # via shapely
+    # via transformers
+    # via unstructured
+oauthlib==3.2.2
+    # via fastapi-sso
+    # via kubernetes
+    # via requests-oauthlib
+onnxruntime==1.17.3
+    # via chromadb
+    # via faster-whisper
+    # via rapidocr-onnxruntime
+openai==1.28.1
+    # via litellm
+opencv-python==4.9.0.80
+    # via rapidocr-onnxruntime
+opencv-python-headless==4.9.0.80
+    # via open-webui
+openpyxl==3.1.2
+    # via open-webui
+opentelemetry-api==1.24.0
+    # via chromadb
+    # via opentelemetry-exporter-otlp-proto-grpc
+    # via opentelemetry-instrumentation
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+    # via opentelemetry-sdk
+opentelemetry-exporter-otlp-proto-common==1.24.0
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-exporter-otlp-proto-grpc==1.24.0
+    # via chromadb
+opentelemetry-instrumentation==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+opentelemetry-instrumentation-asgi==0.45b0
+    # via opentelemetry-instrumentation-fastapi
+opentelemetry-instrumentation-fastapi==0.45b0
+    # via chromadb
+opentelemetry-proto==1.24.0
+    # via opentelemetry-exporter-otlp-proto-common
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-sdk==1.24.0
+    # via chromadb
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-semantic-conventions==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+    # via opentelemetry-sdk
+opentelemetry-util-http==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+ordered-set==4.1.0
+    # via deepdiff
+orjson==3.10.3
+    # via chromadb
+    # via langsmith
+    # via litellm
+overrides==7.7.0
+    # via chromadb
+packaging==23.2
+    # via black
+    # via build
+    # via gunicorn
+    # via huggingface-hub
+    # via langchain-core
+    # via langfuse
+    # via marshmallow
+    # via onnxruntime
+    # via transformers
+    # via unstructured-client
+pandas==2.2.2
+    # via open-webui
+passlib==1.7.4
+    # via open-webui
+pathspec==0.12.1
+    # via black
+peewee==3.17.3
+    # via open-webui
+    # via peewee-migrate
+peewee-migrate==1.12.2
+    # via open-webui
+pillow==10.3.0
+    # via fpdf2
+    # via rapidocr-onnxruntime
+    # via sentence-transformers
+platformdirs==4.2.1
+    # via black
+posthog==3.5.0
+    # via chromadb
+proto-plus==1.23.0
+    # via google-ai-generativelanguage
+    # via google-api-core
+protobuf==4.25.3
+    # via google-ai-generativelanguage
+    # via google-api-core
+    # via google-generativeai
+    # via googleapis-common-protos
+    # via grpcio-status
+    # via onnxruntime
+    # via opentelemetry-proto
+    # via proto-plus
+psycopg2-binary==2.9.9
+    # via open-webui
+pulsar-client==3.5.0
+    # via chromadb
+pyasn1==0.6.0
+    # via pyasn1-modules
+    # via python-jose
+    # via rsa
+pyasn1-modules==0.4.0
+    # via google-auth
+pyclipper==1.3.0.post5
+    # via rapidocr-onnxruntime
+pycparser==2.22
+    # via cffi
+pydantic==2.7.1
+    # via chromadb
+    # via fastapi
+    # via fastapi-sso
+    # via google-generativeai
+    # via langchain
+    # via langchain-core
+    # via langfuse
+    # via langsmith
+    # via open-webui
+    # via openai
+pydantic-core==2.18.2
+    # via pydantic
+pygments==2.18.0
+    # via rich
+pyjwt==2.8.0
+    # via litellm
+    # via open-webui
+pymysql==1.1.0
+    # via open-webui
+pypandoc==1.13
+    # via open-webui
+pyparsing==3.1.2
+    # via httplib2
+pypdf==4.2.0
+    # via open-webui
+    # via unstructured-client
+pypika==0.48.9
+    # via chromadb
+pyproject-hooks==1.1.0
+    # via build
+python-dateutil==2.9.0.post0
+    # via botocore
+    # via kubernetes
+    # via pandas
+    # via posthog
+    # via unstructured-client
+python-dotenv==1.0.1
+    # via litellm
+    # via uvicorn
+python-engineio==4.9.0
+    # via python-socketio
+python-iso639==2024.4.27
+    # via unstructured
+python-jose==3.3.0
+    # via open-webui
+python-magic==0.4.27
+    # via unstructured
+python-multipart==0.0.9
+    # via litellm
+    # via open-webui
+python-socketio==5.11.2
+    # via open-webui
+pytube==15.0.0
+    # via open-webui
+pytz==2024.1
+    # via apscheduler
+    # via pandas
+pyxlsb==1.0.10
+    # via open-webui
+pyyaml==6.0.1
+    # via chromadb
+    # via ctranslate2
+    # via huggingface-hub
+    # via kubernetes
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+    # via litellm
+    # via rapidocr-onnxruntime
+    # via transformers
+    # via uvicorn
+rank-bm25==0.2.2
+    # via open-webui
+rapidfuzz==3.9.0
+    # via unstructured
+rapidocr-onnxruntime==1.2.3
+    # via open-webui
+redis==5.0.4
+    # via rq
+regex==2024.5.10
+    # via nltk
+    # via tiktoken
+    # via transformers
+requests==2.31.0
+    # via chromadb
+    # via google-api-core
+    # via huggingface-hub
+    # via kubernetes
+    # via langchain
+    # via langchain-community
+    # via langsmith
+    # via litellm
+    # via open-webui
+    # via posthog
+    # via requests-oauthlib
+    # via tiktoken
+    # via transformers
+    # via unstructured
+    # via unstructured-client
+    # via youtube-transcript-api
+requests-oauthlib==2.0.0
+    # via kubernetes
+rich==13.7.1
+    # via typer
+rq==1.16.2
+    # via litellm
+rsa==4.9
+    # via google-auth
+    # via python-jose
+s3transfer==0.10.1
+    # via boto3
+safetensors==0.4.3
+    # via transformers
+scikit-learn==1.4.2
+    # via sentence-transformers
+scipy==1.13.0
+    # via scikit-learn
+    # via sentence-transformers
+sentence-transformers==2.7.0
+    # via open-webui
+setuptools==69.5.1
+    # via ctranslate2
+    # via opentelemetry-instrumentation
+shapely==2.0.4
+    # via rapidocr-onnxruntime
+shellingham==1.5.4
+    # via typer
+simple-websocket==1.0.0
+    # via python-engineio
+six==1.16.0
+    # via apscheduler
+    # via ecdsa
+    # via kubernetes
+    # via langdetect
+    # via posthog
+    # via python-dateutil
+    # via rapidocr-onnxruntime
+    # via unstructured-client
+sniffio==1.3.1
+    # via anyio
+    # via httpx
+    # via openai
+soupsieve==2.5
+    # via beautifulsoup4
+sqlalchemy==2.0.30
+    # via langchain
+    # via langchain-community
+starlette==0.36.3
+    # via fastapi
+sympy==1.12
+    # via onnxruntime
+    # via torch
+tabulate==0.9.0
+    # via unstructured
+tenacity==8.3.0
+    # via chromadb
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+threadpoolctl==3.5.0
+    # via scikit-learn
+tiktoken==0.6.0
+    # via litellm
+tokenizers==0.15.2
+    # via chromadb
+    # via faster-whisper
+    # via litellm
+    # via transformers
+torch==2.3.0
+    # via sentence-transformers
+tqdm==4.66.4
+    # via chromadb
+    # via google-generativeai
+    # via huggingface-hub
+    # via nltk
+    # via openai
+    # via sentence-transformers
+    # via transformers
+transformers==4.39.3
+    # via sentence-transformers
+typer==0.12.3
+    # via chromadb
+typing-extensions==4.11.0
+    # via chromadb
+    # via fastapi
+    # via google-generativeai
+    # via huggingface-hub
+    # via openai
+    # via opentelemetry-sdk
+    # via pydantic
+    # via pydantic-core
+    # via sqlalchemy
+    # via torch
+    # via typer
+    # via typing-inspect
+    # via unstructured
+    # via unstructured-client
+typing-inspect==0.9.0
+    # via dataclasses-json
+    # via unstructured-client
+tzdata==2024.1
+    # via pandas
+tzlocal==5.2
+    # via apscheduler
+unstructured==0.11.8
+    # via open-webui
+unstructured-client==0.22.0
+    # via unstructured
+uritemplate==4.1.1
+    # via google-api-python-client
+urllib3==2.2.1
+    # via botocore
+    # via kubernetes
+    # via requests
+    # via unstructured-client
+uvicorn==0.22.0
+    # via chromadb
+    # via litellm
+    # via open-webui
+uvloop==0.19.0
+    # via uvicorn
+validators==0.28.1
+    # via open-webui
+watchfiles==0.21.0
+    # via uvicorn
+websocket-client==1.8.0
+    # via kubernetes
+websockets==12.0
+    # via uvicorn
+werkzeug==3.0.3
+    # via flask
+wrapt==1.16.0
+    # via deprecated
+    # via langfuse
+    # via opentelemetry-instrumentation
+    # via unstructured
+wsproto==1.2.0
+    # via simple-websocket
+xlrd==2.0.1
+    # via open-webui
+yarl==1.9.4
+    # via aiohttp
+youtube-transcript-api==0.6.2
+    # via open-webui
+zipp==3.18.1
+    # via importlib-metadata

requirements.lock

@@ -0,0 +1,680 @@
+# generated by rye
+# use `rye lock` or `rye sync` to update this lockfile
+#
+# last locked with the following flags:
+#   pre: false
+#   features: []
+#   all-features: false
+#   with-sources: false
+
+-e file:.
+aiohttp==3.9.5
+    # via langchain
+    # via langchain-community
+    # via litellm
+    # via open-webui
+aiosignal==1.3.1
+    # via aiohttp
+annotated-types==0.6.0
+    # via pydantic
+anyio==4.3.0
+    # via httpx
+    # via openai
+    # via starlette
+    # via watchfiles
+apscheduler==3.10.4
+    # via litellm
+    # via open-webui
+argon2-cffi==23.1.0
+    # via open-webui
+argon2-cffi-bindings==21.2.0
+    # via argon2-cffi
+asgiref==3.8.1
+    # via opentelemetry-instrumentation-asgi
+attrs==23.2.0
+    # via aiohttp
+av==11.0.0
+    # via faster-whisper
+backoff==2.2.1
+    # via langfuse
+    # via litellm
+    # via posthog
+    # via unstructured
+bcrypt==4.1.2
+    # via chromadb
+    # via open-webui
+    # via passlib
+beautifulsoup4==4.12.3
+    # via unstructured
+bidict==0.23.1
+    # via python-socketio
+black==24.4.2
+    # via open-webui
+blinker==1.8.2
+    # via flask
+boto3==1.34.95
+    # via open-webui
+botocore==1.34.103
+    # via boto3
+    # via s3transfer
+build==1.2.1
+    # via chromadb
+cachetools==5.3.3
+    # via google-auth
+certifi==2024.2.2
+    # via httpcore
+    # via httpx
+    # via kubernetes
+    # via pulsar-client
+    # via requests
+    # via unstructured-client
+cffi==1.16.0
+    # via argon2-cffi-bindings
+    # via cryptography
+chardet==5.2.0
+    # via unstructured
+charset-normalizer==3.3.2
+    # via requests
+    # via unstructured-client
+chroma-hnswlib==0.7.3
+    # via chromadb
+chromadb==0.4.24
+    # via langchain-chroma
+    # via open-webui
+click==8.1.7
+    # via black
+    # via flask
+    # via litellm
+    # via nltk
+    # via peewee-migrate
+    # via rq
+    # via typer
+    # via uvicorn
+coloredlogs==15.0.1
+    # via onnxruntime
+cryptography==42.0.7
+    # via litellm
+    # via pyjwt
+ctranslate2==4.2.1
+    # via faster-whisper
+dataclasses-json==0.6.6
+    # via langchain
+    # via langchain-community
+    # via unstructured
+    # via unstructured-client
+deepdiff==7.0.1
+    # via unstructured-client
+defusedxml==0.7.1
+    # via fpdf2
+deprecated==1.2.14
+    # via opentelemetry-api
+    # via opentelemetry-exporter-otlp-proto-grpc
+distro==1.9.0
+    # via openai
+dnspython==2.6.1
+    # via email-validator
+docx2txt==0.8
+    # via open-webui
+ecdsa==0.19.0
+    # via python-jose
+email-validator==2.1.1
+    # via pydantic
+emoji==2.11.1
+    # via unstructured
+et-xmlfile==1.1.0
+    # via openpyxl
+fake-useragent==1.5.1
+    # via open-webui
+fastapi==0.109.2
+    # via chromadb
+    # via fastapi-sso
+    # via langchain-chroma
+    # via litellm
+    # via open-webui
+fastapi-sso==0.10.0
+    # via litellm
+faster-whisper==1.0.1
+    # via open-webui
+filelock==3.14.0
+    # via huggingface-hub
+    # via torch
+    # via transformers
+filetype==1.2.0
+    # via unstructured
+flask==3.0.3
+    # via flask-cors
+    # via open-webui
+flask-cors==4.0.0
+    # via open-webui
+flatbuffers==24.3.25
+    # via onnxruntime
+fonttools==4.51.0
+    # via fpdf2
+fpdf2==2.7.8
+    # via open-webui
+frozenlist==1.4.1
+    # via aiohttp
+    # via aiosignal
+fsspec==2024.3.1
+    # via huggingface-hub
+    # via torch
+google-ai-generativelanguage==0.6.2
+    # via google-generativeai
+google-api-core==2.19.0
+    # via google-ai-generativelanguage
+    # via google-api-python-client
+    # via google-generativeai
+google-api-python-client==2.129.0
+    # via google-generativeai
+google-auth==2.29.0
+    # via google-ai-generativelanguage
+    # via google-api-core
+    # via google-api-python-client
+    # via google-auth-httplib2
+    # via google-generativeai
+    # via kubernetes
+google-auth-httplib2==0.2.0
+    # via google-api-python-client
+google-generativeai==0.5.2
+    # via open-webui
+googleapis-common-protos==1.63.0
+    # via google-api-core
+    # via grpcio-status
+    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio==1.63.0
+    # via chromadb
+    # via google-api-core
+    # via grpcio-status
+    # via opentelemetry-exporter-otlp-proto-grpc
+grpcio-status==1.62.2
+    # via google-api-core
+gunicorn==21.2.0
+    # via litellm
+h11==0.14.0
+    # via httpcore
+    # via uvicorn
+    # via wsproto
+httpcore==1.0.5
+    # via httpx
+httplib2==0.22.0
+    # via google-api-python-client
+    # via google-auth-httplib2
+httptools==0.6.1
+    # via uvicorn
+httpx==0.27.0
+    # via fastapi-sso
+    # via langfuse
+    # via openai
+huggingface-hub==0.23.0
+    # via faster-whisper
+    # via sentence-transformers
+    # via tokenizers
+    # via transformers
+humanfriendly==10.0
+    # via coloredlogs
+idna==3.7
+    # via anyio
+    # via email-validator
+    # via httpx
+    # via langfuse
+    # via requests
+    # via unstructured-client
+    # via yarl
+importlib-metadata==7.0.0
+    # via litellm
+    # via opentelemetry-api
+importlib-resources==6.4.0
+    # via chromadb
+itsdangerous==2.2.0
+    # via flask
+jinja2==3.1.4
+    # via flask
+    # via litellm
+    # via torch
+jmespath==1.0.1
+    # via boto3
+    # via botocore
+joblib==1.4.2
+    # via nltk
+    # via scikit-learn
+jsonpatch==1.33
+    # via langchain
+    # via langchain-core
+jsonpath-python==1.0.6
+    # via unstructured-client
+jsonpointer==2.4
+    # via jsonpatch
+kubernetes==29.0.0
+    # via chromadb
+langchain==0.1.16
+    # via open-webui
+langchain-chroma==0.1.0
+    # via open-webui
+langchain-community==0.0.34
+    # via langchain
+    # via open-webui
+langchain-core==0.1.52
+    # via langchain
+    # via langchain-chroma
+    # via langchain-community
+    # via langchain-text-splitters
+langchain-text-splitters==0.0.1
+    # via langchain
+langdetect==1.0.9
+    # via unstructured
+langfuse==2.27.3
+    # via open-webui
+langsmith==0.1.57
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+litellm==1.35.28
+    # via open-webui
+lxml==5.2.2
+    # via unstructured
+markdown==3.6
+    # via open-webui
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.5
+    # via jinja2
+    # via werkzeug
+marshmallow==3.21.2
+    # via dataclasses-json
+    # via unstructured-client
+mdurl==0.1.2
+    # via markdown-it-py
+mmh3==4.1.0
+    # via chromadb
+monotonic==1.6
+    # via posthog
+mpmath==1.3.0
+    # via sympy
+multidict==6.0.5
+    # via aiohttp
+    # via yarl
+mypy-extensions==1.0.0
+    # via black
+    # via typing-inspect
+    # via unstructured-client
+networkx==3.3
+    # via torch
+nltk==3.8.1
+    # via unstructured
+numpy==1.26.4
+    # via chroma-hnswlib
+    # via chromadb
+    # via ctranslate2
+    # via langchain
+    # via langchain-chroma
+    # via langchain-community
+    # via onnxruntime
+    # via opencv-python
+    # via opencv-python-headless
+    # via pandas
+    # via rank-bm25
+    # via rapidocr-onnxruntime
+    # via scikit-learn
+    # via scipy
+    # via sentence-transformers
+    # via shapely
+    # via transformers
+    # via unstructured
+oauthlib==3.2.2
+    # via fastapi-sso
+    # via kubernetes
+    # via requests-oauthlib
+onnxruntime==1.17.3
+    # via chromadb
+    # via faster-whisper
+    # via rapidocr-onnxruntime
+openai==1.28.1
+    # via litellm
+opencv-python==4.9.0.80
+    # via rapidocr-onnxruntime
+opencv-python-headless==4.9.0.80
+    # via open-webui
+openpyxl==3.1.2
+    # via open-webui
+opentelemetry-api==1.24.0
+    # via chromadb
+    # via opentelemetry-exporter-otlp-proto-grpc
+    # via opentelemetry-instrumentation
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+    # via opentelemetry-sdk
+opentelemetry-exporter-otlp-proto-common==1.24.0
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-exporter-otlp-proto-grpc==1.24.0
+    # via chromadb
+opentelemetry-instrumentation==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+opentelemetry-instrumentation-asgi==0.45b0
+    # via opentelemetry-instrumentation-fastapi
+opentelemetry-instrumentation-fastapi==0.45b0
+    # via chromadb
+opentelemetry-proto==1.24.0
+    # via opentelemetry-exporter-otlp-proto-common
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-sdk==1.24.0
+    # via chromadb
+    # via opentelemetry-exporter-otlp-proto-grpc
+opentelemetry-semantic-conventions==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+    # via opentelemetry-sdk
+opentelemetry-util-http==0.45b0
+    # via opentelemetry-instrumentation-asgi
+    # via opentelemetry-instrumentation-fastapi
+ordered-set==4.1.0
+    # via deepdiff
+orjson==3.10.3
+    # via chromadb
+    # via langsmith
+    # via litellm
+overrides==7.7.0
+    # via chromadb
+packaging==23.2
+    # via black
+    # via build
+    # via gunicorn
+    # via huggingface-hub
+    # via langchain-core
+    # via langfuse
+    # via marshmallow
+    # via onnxruntime
+    # via transformers
+    # via unstructured-client
+pandas==2.2.2
+    # via open-webui
+passlib==1.7.4
+    # via open-webui
+pathspec==0.12.1
+    # via black
+peewee==3.17.3
+    # via open-webui
+    # via peewee-migrate
+peewee-migrate==1.12.2
+    # via open-webui
+pillow==10.3.0
+    # via fpdf2
+    # via rapidocr-onnxruntime
+    # via sentence-transformers
+platformdirs==4.2.1
+    # via black
+posthog==3.5.0
+    # via chromadb
+proto-plus==1.23.0
+    # via google-ai-generativelanguage
+    # via google-api-core
+protobuf==4.25.3
+    # via google-ai-generativelanguage
+    # via google-api-core
+    # via google-generativeai
+    # via googleapis-common-protos
+    # via grpcio-status
+    # via onnxruntime
+    # via opentelemetry-proto
+    # via proto-plus
+psycopg2-binary==2.9.9
+    # via open-webui
+pulsar-client==3.5.0
+    # via chromadb
+pyasn1==0.6.0
+    # via pyasn1-modules
+    # via python-jose
+    # via rsa
+pyasn1-modules==0.4.0
+    # via google-auth
+pyclipper==1.3.0.post5
+    # via rapidocr-onnxruntime
+pycparser==2.22
+    # via cffi
+pydantic==2.7.1
+    # via chromadb
+    # via fastapi
+    # via fastapi-sso
+    # via google-generativeai
+    # via langchain
+    # via langchain-core
+    # via langfuse
+    # via langsmith
+    # via open-webui
+    # via openai
+pydantic-core==2.18.2
+    # via pydantic
+pygments==2.18.0
+    # via rich
+pyjwt==2.8.0
+    # via litellm
+    # via open-webui
+pymysql==1.1.0
+    # via open-webui
+pypandoc==1.13
+    # via open-webui
+pyparsing==3.1.2
+    # via httplib2
+pypdf==4.2.0
+    # via open-webui
+    # via unstructured-client
+pypika==0.48.9
+    # via chromadb
+pyproject-hooks==1.1.0
+    # via build
+python-dateutil==2.9.0.post0
+    # via botocore
+    # via kubernetes
+    # via pandas
+    # via posthog
+    # via unstructured-client
+python-dotenv==1.0.1
+    # via litellm
+    # via uvicorn
+python-engineio==4.9.0
+    # via python-socketio
+python-iso639==2024.4.27
+    # via unstructured
+python-jose==3.3.0
+    # via open-webui
+python-magic==0.4.27
+    # via unstructured
+python-multipart==0.0.9
+    # via litellm
+    # via open-webui
+python-socketio==5.11.2
+    # via open-webui
+pytube==15.0.0
+    # via open-webui
+pytz==2024.1
+    # via apscheduler
+    # via pandas
+pyxlsb==1.0.10
+    # via open-webui
+pyyaml==6.0.1
+    # via chromadb
+    # via ctranslate2
+    # via huggingface-hub
+    # via kubernetes
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+    # via litellm
+    # via rapidocr-onnxruntime
+    # via transformers
+    # via uvicorn
+rank-bm25==0.2.2
+    # via open-webui
+rapidfuzz==3.9.0
+    # via unstructured
+rapidocr-onnxruntime==1.2.3
+    # via open-webui
+redis==5.0.4
+    # via rq
+regex==2024.5.10
+    # via nltk
+    # via tiktoken
+    # via transformers
+requests==2.31.0
+    # via chromadb
+    # via google-api-core
+    # via huggingface-hub
+    # via kubernetes
+    # via langchain
+    # via langchain-community
+    # via langsmith
+    # via litellm
+    # via open-webui
+    # via posthog
+    # via requests-oauthlib
+    # via tiktoken
+    # via transformers
+    # via unstructured
+    # via unstructured-client
+    # via youtube-transcript-api
+requests-oauthlib==2.0.0
+    # via kubernetes
+rich==13.7.1
+    # via typer
+rq==1.16.2
+    # via litellm
+rsa==4.9
+    # via google-auth
+    # via python-jose
+s3transfer==0.10.1
+    # via boto3
+safetensors==0.4.3
+    # via transformers
+scikit-learn==1.4.2
+    # via sentence-transformers
+scipy==1.13.0
+    # via scikit-learn
+    # via sentence-transformers
+sentence-transformers==2.7.0
+    # via open-webui
+setuptools==69.5.1
+    # via ctranslate2
+    # via opentelemetry-instrumentation
+shapely==2.0.4
+    # via rapidocr-onnxruntime
+shellingham==1.5.4
+    # via typer
+simple-websocket==1.0.0
+    # via python-engineio
+six==1.16.0
+    # via apscheduler
+    # via ecdsa
+    # via kubernetes
+    # via langdetect
+    # via posthog
+    # via python-dateutil
+    # via rapidocr-onnxruntime
+    # via unstructured-client
+sniffio==1.3.1
+    # via anyio
+    # via httpx
+    # via openai
+soupsieve==2.5
+    # via beautifulsoup4
+sqlalchemy==2.0.30
+    # via langchain
+    # via langchain-community
+starlette==0.36.3
+    # via fastapi
+sympy==1.12
+    # via onnxruntime
+    # via torch
+tabulate==0.9.0
+    # via unstructured
+tenacity==8.3.0
+    # via chromadb
+    # via langchain
+    # via langchain-community
+    # via langchain-core
+threadpoolctl==3.5.0
+    # via scikit-learn
+tiktoken==0.6.0
+    # via litellm
+tokenizers==0.15.2
+    # via chromadb
+    # via faster-whisper
+    # via litellm
+    # via transformers
+torch==2.3.0
+    # via sentence-transformers
+tqdm==4.66.4
+    # via chromadb
+    # via google-generativeai
+    # via huggingface-hub
+    # via nltk
+    # via openai
+    # via sentence-transformers
+    # via transformers
+transformers==4.39.3
+    # via sentence-transformers
+typer==0.12.3
+    # via chromadb
+typing-extensions==4.11.0
+    # via chromadb
+    # via fastapi
+    # via google-generativeai
+    # via huggingface-hub
+    # via openai
+    # via opentelemetry-sdk
+    # via pydantic
+    # via pydantic-core
+    # via sqlalchemy
+    # via torch
+    # via typer
+    # via typing-inspect
+    # via unstructured
+    # via unstructured-client
+typing-inspect==0.9.0
+    # via dataclasses-json
+    # via unstructured-client
+tzdata==2024.1
+    # via pandas
+tzlocal==5.2
+    # via apscheduler
+unstructured==0.11.8
+    # via open-webui
+unstructured-client==0.22.0
+    # via unstructured
+uritemplate==4.1.1
+    # via google-api-python-client
+urllib3==2.2.1
+    # via botocore
+    # via kubernetes
+    # via requests
+    # via unstructured-client
+uvicorn==0.22.0
+    # via chromadb
+    # via litellm
+    # via open-webui
+uvloop==0.19.0
+    # via uvicorn
+validators==0.28.1
+    # via open-webui
+watchfiles==0.21.0
+    # via uvicorn
+websocket-client==1.8.0
+    # via kubernetes
+websockets==12.0
+    # via uvicorn
+werkzeug==3.0.3
+    # via flask
+wrapt==1.16.0
+    # via deprecated
+    # via langfuse
+    # via opentelemetry-instrumentation
+    # via unstructured
+wsproto==1.2.0
+    # via simple-websocket
+xlrd==2.0.1
+    # via open-webui
+yarl==1.9.4
+    # via aiohttp
+youtube-transcript-api==0.6.2
+    # via open-webui
+zipp==3.18.1
+    # via importlib-metadata