Merge pull request #413 from ollama-webui/main

dev

.github/FUNDING.yml

+github: tjbck

.github/ISSUE_TEMPLATE/bug_report.md

@@ -4,7 +4,6 @@ about: Create a report to help us improve
 title: ''
 labels: ''
 assignees: ''
-
 ---
 
 # Bug Report
@@ -31,6 +30,7 @@ assignees: ''
 ## Reproduction Details
 
 **Confirmation:**
+
 - [ ] I have read and followed all the instructions provided in the README.md.
 - [ ] I have reviewed the troubleshooting.md document.
 - [ ] I have included the browser console logs.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -4,7 +4,6 @@ about: Suggest an idea for this project
 title: ''
 labels: ''
 assignees: ''
-
 ---
 
 **Is your feature request related to a problem? Please describe.**

.github/workflows/node.js.yaml → .github/workflows/format-backend.yaml

-name: Node.js CI
+name: Python CI
 on:
   push:
     branches: ['main']
   pull_request:
 jobs:
   build:
-    name: 'Fmt, Lint, & Build'
+    name: 'Format Backend'
     env:
       PUBLIC_API_BASE_URL: ''
     runs-on: ubuntu-latest
@@ -14,14 +14,14 @@ jobs:
         node-version:
           - latest
     steps:
-      - uses: actions/checkout@v3
-      - name: Use Node.js ${{ matrix.node-version }}
-        uses: actions/setup-node@v3
-        with:
-          node-version: ${{ matrix.node-version }}
-      - run: node --version
-      - run: npm clean-install
-      - run: npm run fmt
-        #- run: npm run lint
-        #- run: npm run lint:types
-      - run: npm run build
+      - uses: actions/checkout@v4
+      - name: Use Python
+        uses: actions/setup-python@v4
+      - name: Use Bun
+        uses: oven-sh/setup-bun@v1
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install yapf
+      - name: Format backend
+        run: bun run format:backend

.github/workflows/format-build-frontend.yaml

+name: Bun CI
+on:
+  push:
+    branches: ['main']
+  pull_request:
+jobs:
+  build:
+    name: 'Format & Build Frontend'
+    env:
+      PUBLIC_API_BASE_URL: ''
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Bun
+        uses: oven-sh/setup-bun@v1
+      - run: bun --version
+      - name: Install frontend dependencies
+        run: bun install
+      - name: Format frontend
+        run: bun run format
+      - name: Build frontend
+        run: bun run build

.github/workflows/lint-backend.disabled

+name: Python CI
+on:
+  push:
+    branches: ['main']
+  pull_request:
+jobs:
+  build:
+    name: 'Lint Backend'
+    env:
+      PUBLIC_API_BASE_URL: ''
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        node-version:
+          - latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Python
+        uses: actions/setup-python@v4
+      - name: Use Bun
+        uses: oven-sh/setup-bun@v1
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pylint
+      - name: Lint backend
+        run: bun run lint:backend

.github/workflows/lint-frontend.disabled

+name: Bun CI
+on:
+  push:
+    branches: ['main']
+  pull_request:
+jobs:
+  build:
+    name: 'Lint Frontend'
+    env:
+      PUBLIC_API_BASE_URL: ''
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Use Bun
+        uses: oven-sh/setup-bun@v1
+      - run: bun --version
+      - name: Install frontend dependencies
+        run: bun install --frozen-lockfile
+      - run: bun run lint:frontend
+      - run: bun run lint:types
+        if: success() || failure()
\ No newline at end of file

.gitignore

@@ -8,3 +8,293 @@ node_modules
 !.env.example
 vite.config.js.timestamp-*
 vite.config.ts.timestamp-*
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
\ No newline at end of file

.prettierignore

@@ -11,3 +11,6 @@ node_modules
 pnpm-lock.yaml
 package-lock.json
 yarn.lock
+
+# Ignore kubernetes files
+kubernetes
\ No newline at end of file

Dockerfile

@@ -2,12 +2,6 @@
 
 FROM node:alpine as build
 
-ARG OLLAMA_API_BASE_URL='/ollama/api'
-RUN echo $OLLAMA_API_BASE_URL
-
-ENV PUBLIC_API_BASE_URL $OLLAMA_API_BASE_URL
-RUN echo $PUBLIC_API_BASE_URL
-
 WORKDIR /app
 
 COPY package.json package-lock.json ./ 
@@ -18,11 +12,13 @@ RUN npm run build
 
 FROM python:3.11-slim-buster as base
 
-ARG OLLAMA_API_BASE_URL='/ollama/api'
-
 ENV ENV=prod
-ENV OLLAMA_API_BASE_URL $OLLAMA_API_BASE_URL
-ENV WEBUI_AUTH ""
+
+ENV OLLAMA_API_BASE_URL "/ollama/api"
+
+ENV OPENAI_API_BASE_URL ""
+ENV OPENAI_API_KEY ""
+
 ENV WEBUI_JWT_SECRET_KEY "SECRET_KEY"
 
 WORKDIR /app

INSTALLATION.md

+### Installing Both Ollama and Ollama Web UI Using Kustomize
+
+For cpu-only pod
+
+```bash
+kubectl apply -f ./kubernetes/manifest/base
+```
+
+For gpu-enabled pod
+
+```bash
+kubectl apply -k ./kubernetes/manifest
+```
+
+### Installing Both Ollama and Ollama Web UI Using Helm
+
+Package Helm file first
+
+```bash
+helm package ./kubernetes/helm/
+```
+
+For cpu-only pod
+
+```bash
+helm install ollama-webui ./ollama-webui-*.tgz
+```
+
+For gpu-enabled pod
+
+```bash
+helm install ollama-webui ./ollama-webui-*.tgz --set ollama.resources.limits.nvidia.com/gpu="1"
+```
+
+Check the `kubernetes/helm/values.yaml` file to know which parameters are available for customization

README.md

@@ -27,12 +27,16 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
 
 - ⚡ **Swift Responsiveness**: Enjoy fast and responsive performance.
 
-- 🚀 **Effortless Setup**: Install seamlessly using Docker for a hassle-free experience.
+- 🚀 **Effortless Setup**: Install seamlessly using Docker or Kubernetes (kubectl, kustomize or helm) for a hassle-free experience.
 
 - 💻 **Code Syntax Highlighting**: Enjoy enhanced code readability with our syntax highlighting feature.
 
 - ✒️🔢 **Full Markdown and LaTeX Support**: Elevate your LLM experience with comprehensive Markdown and LaTeX capabilities for enriched interaction.
 
+- 📜 **Prompt Preset Support**: Instantly access preset prompts using the '/' command in the chat input. Load predefined conversation starters effortlessly and expedite your interactions. Effortlessly import prompts through [OllamaHub](https://ollamahub.com/) integration.
+
+- 👍👎 **RLHF Annotation**: Empower your messages by rating them with thumbs up and thumbs down, facilitating the creation of datasets for Reinforcement Learning from Human Feedback (RLHF). Utilize your messages to train or fine-tune models, all while ensuring the confidentiality of locally saved data.
+
 - 📥🗑️ **Download/Delete Models**: Easily download or remove models directly from the web UI.
 
 - ⬆️ **GGUF File Model Creation**: Effortlessly create Ollama models by uploading GGUF files directly from the web UI. Streamlined process with options to upload from your machine or download GGUF files from Hugging Face.
@@ -79,32 +83,6 @@ Don't forget to explore our sibling project, [OllamaHub](https://ollamahub.com/)
 
 - **Privacy and Data Security:** We prioritize your privacy and data security above all. Please be reassured that all data entered into the Ollama Web UI is stored locally on your device. Our system is designed to be privacy-first, ensuring that no external requests are made, and your data does not leave your local environment. We are committed to maintaining the highest standards of data privacy and security, ensuring that your information remains confidential and under your control.
 
-### Installing Both Ollama and Ollama Web UI Using Docker Compose
-
-If you don't have Ollama installed yet, you can use the provided Docker Compose file for a hassle-free installation. Simply run the following command:
-
-```bash
-docker compose up -d --build
-```
-
-This command will install both Ollama and Ollama Web UI on your system.
-
-#### Enable GPU
-
-Use the additional Docker Compose file designed to enable GPU support by running the following command:
-
-```bash
-docker compose -f docker-compose.yml -f docker-compose.gpu.yml up -d --build
-```
-
-#### Expose Ollama API outside the container stack
-
-Deploy the service with an additional Docker Compose file designed for API exposure:
-
-```bash
-docker compose -f docker-compose.yml -f docker-compose.api.yml up -d --build
-```
-
 ### Installing Ollama Web UI Only
 
 #### Prerequisites
@@ -149,6 +127,69 @@ docker build -t ollama-webui .
 docker run -d -p 3000:8080 -e OLLAMA_API_BASE_URL=https://example.com/api -v ollama-webui:/app/backend/data --name ollama-webui --restart always ollama-webui
 ```
 
+### Installing Both Ollama and Ollama Web UI
+
+#### Using Docker Compose
+
+If you don't have Ollama installed yet, you can use the provided Docker Compose file for a hassle-free installation. Simply run the following command:
+
+```bash
+docker compose up -d --build
+```
+
+This command will install both Ollama and Ollama Web UI on your system.
+
+##### Enable GPU
+
+Use the additional Docker Compose file designed to enable GPU support by running the following command:
+
+```bash
+docker compose -f docker-compose.yaml -f docker-compose.gpu.yaml up -d --build
+```
+
+##### Expose Ollama API outside the container stack
+
+Deploy the service with an additional Docker Compose file designed for API exposure:
+
+```bash
+docker compose -f docker-compose.yaml -f docker-compose.api.yaml up -d --build
+```
+
+#### Using Provided `run-compose.sh` Script (Linux)
+
+Also available on Windows under any docker-enabled WSL2 linux distro (you have to enable it from Docker Desktop)
+
+Simply run the following command to grant execute permission to script:
+
+```bash
+chmod +x run-compose.sh
+```
+
+##### For CPU only container
+
+```bash
+./run-compose.sh
+```
+
+##### Enable GPU
+
+For GPU enabled container (to enable this you must have your gpu driver for docker, it mostly works with nvidia so this is the official install guide: [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html))
+Warning! A GPU-enabled installation has only been tested using linux and nvidia GPU, full functionalities are not guaranteed under Windows or Macos or using a different GPU
+
+```bash
+./run-compose.sh --enable-gpu
+```
+
+Note that both the above commands will use the latest production docker image in repository, to be able to build the latest local version you'll need to append the `--build` parameter, for example:
+
+```bash
+./run-compose.sh --enable-gpu --build
+```
+
+#### Using Alternative Methods (Kustomize or Helm)
+
+See [INSTALLATION.md](/INSTALLATION.md) for information on how to install and/or join our [Ollama Web UI Discord community](https://discord.gg/5rJgQTnV4s).
+
 ## How to Install Without Docker
 
 While we strongly recommend using our convenient Docker container installation for optimal support, we understand that some situations may require a non-Docker setup, especially for development purposes. Please note that non-Docker installations are not officially supported, and you might need to troubleshoot on your own.
@@ -157,9 +198,15 @@ While we strongly recommend using our convenient Docker container installation f
 
 The Ollama Web UI consists of two primary components: the frontend and the backend (which serves as a reverse proxy, handling static frontend files, and additional features). Both need to be running concurrently for the development environment.
 
-**Warning: Backend Dependency for Proper Functionality**
+> [!IMPORTANT]
+> The backend is required for proper functionality
+
+### Requirements 📦
 
-### TL;DR 🚀
+- 🐰 [Bun](https://bun.sh) >= 1.0.21 or 🐢 [Node.js](https://nodejs.org/en) >= 20.10
+- 🐍 [Python](https://python.org) >= 3.11
+
+### Build and Install 🛠️
 
 Run the following commands to install:
 
@@ -170,13 +217,17 @@ cd ollama-webui/
 # Copying required .env file
 cp -RPp example.env .env
 
-# Building Frontend
+# Building Frontend Using Node
 npm i
 npm run build
 
+# or Building Frontend Using Bun
+# bun install
+# bun run build
+
 # Serving Frontend with the Backend
 cd ./backend
-pip install -r requirements.txt
+pip install -r requirements.txt -U
 sh start.sh
 ```
 

TROUBLESHOOTING.md

@@ -4,7 +4,7 @@
 
 The Ollama WebUI system is designed to streamline interactions between the client (your browser) and the Ollama API. At the heart of this design is a backend reverse proxy, enhancing security and resolving CORS issues.
 
-- **How it Works**: When you make a request (like `/ollama/api/tags`) from the Ollama WebUI, it doesn’t go directly to the Ollama API. Instead, it first reaches the Ollama WebUI backend. The backend then forwards this request to the Ollama API via the route you define in the `OLLAMA_API_BASE_URL` environment variable. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend.
+- **How it Works**: The Ollama WebUI is designed to interact with the Ollama API through a specific route. When a request is made from the WebUI to Ollama, it is not directly sent to the Ollama API. Initially, the request is sent to the Ollama WebUI backend via `/ollama/api` route. From there, the backend is responsible for forwarding the request to the Ollama API. This forwarding is accomplished by using the route specified in the `OLLAMA_API_BASE_URL` environment variable. Therefore, a request made to `/ollama/api` in the WebUI is effectively the same as making a request to `OLLAMA_API_BASE_URL` in the backend. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend.
 
 - **Security Benefits**: This design prevents direct exposure of the Ollama API to the frontend, safeguarding against potential CORS (Cross-Origin Resource Sharing) issues and unauthorized access. Requiring authentication to access the Ollama API further enhances this security layer.
 
@@ -27,6 +27,6 @@ docker run -d --network=host -v ollama-webui:/app/backend/data -e OLLAMA_API_BAS
 1. **Verify Ollama URL Format**:
    - When running the Web UI container, ensure the `OLLAMA_API_BASE_URL` is correctly set, including the `/api` suffix. (e.g., `http://192.168.1.1:11434/api` for different host setups).
    - In the Ollama WebUI, navigate to "Settings" > "General".
-   - Confirm that the Ollama Server URL is correctly set to `/ollama/api`, including the `/api` suffix.
+   - Confirm that the Ollama Server URL is correctly set to `[OLLAMA URL]/api` (e.g., `http://localhost:11434/api`), including the `/api` suffix.
 
 By following these enhanced troubleshooting steps, connection issues should be effectively resolved. For further assistance or queries, feel free to reach out to us on our community Discord.

backend/.gitignore

@@ -5,3 +5,4 @@ uploads
 .ipynb_checkpoints
 *.db
 _test
+Pipfile
\ No newline at end of file

backend/apps/ollama/main.py

-from flask import Flask, request, Response, jsonify
-from flask_cors import CORS
-
+from fastapi import FastAPI, Request, Response, HTTPException, Depends
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import StreamingResponse
+from fastapi.concurrency import run_in_threadpool
 
 import requests
 import json
-
+from pydantic import BaseModel
 
 from apps.web.models.users import Users
 from constants import ERROR_MESSAGES
-from utils.utils import extract_token_from_auth_header
+from utils.utils import decode_token, get_current_user
 from config import OLLAMA_API_BASE_URL, WEBUI_AUTH
 
-app = Flask(__name__)
-CORS(
-    app
-)  # Enable Cross-Origin Resource Sharing (CORS) to allow requests from different domains
+app = FastAPI()
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.state.OLLAMA_API_BASE_URL = OLLAMA_API_BASE_URL
+
+# TARGET_SERVER_URL = OLLAMA_API_BASE_URL
 
-# Define the target server URL
-TARGET_SERVER_URL = OLLAMA_API_BASE_URL
+
+@app.get("/url")
+async def get_ollama_api_url(user=Depends(get_current_user)):
+    if user and user.role == "admin":
+        return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
+    else:
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
 
 
-@app.route("/", defaults={"path": ""}, methods=["GET", "POST", "PUT", "DELETE"])
-@app.route("/<path:path>", methods=["GET", "POST", "PUT", "DELETE"])
-def proxy(path):
-    # Combine the base URL of the target server with the requested path
-    target_url = f"{TARGET_SERVER_URL}/{path}"
-    print(target_url)
+class UrlUpdateForm(BaseModel):
+    url: str
 
-    # Get data from the original request
-    data = request.get_data()
+
+@app.post("/url/update")
+async def update_ollama_api_url(
+    form_data: UrlUpdateForm, user=Depends(get_current_user)
+):
+    if user and user.role == "admin":
+        app.state.OLLAMA_API_BASE_URL = form_data.url
+        return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
+    else:
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+
+
+@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
+async def proxy(path: str, request: Request, user=Depends(get_current_user)):
+    target_url = f"{app.state.OLLAMA_API_BASE_URL}/{path}"
+
+    body = await request.body()
     headers = dict(request.headers)
 
-    # Basic RBAC support
-    if WEBUI_AUTH:
-        if "Authorization" in headers:
-            token = extract_token_from_auth_header(headers["Authorization"])
-            user = Users.get_user_by_token(token)
-            if user:
-                # Only user and admin roles can access
     if user.role in ["user", "admin"]:
         if path in ["pull", "delete", "push", "copy", "create"]:
-                        # Only admin role can perform actions above
-                        if user.role == "admin":
-                            pass
-                        else:
-                            return (
-                                jsonify({"detail": ERROR_MESSAGES.ACCESS_PROHIBITED}),
-                                401,
+            if user.role != "admin":
+                raise HTTPException(
+                    status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
                 )
     else:
-                        pass
-                else:
-                    return jsonify({"detail": ERROR_MESSAGES.ACCESS_PROHIBITED}), 401
-            else:
-                return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401
-        else:
-            return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401
-    else:
-        pass
-
-    r = None
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
 
     headers.pop("Host", None)
     headers.pop("Authorization", None)
     headers.pop("Origin", None)
     headers.pop("Referer", None)
 
+    r = None
+
+    def get_request():
+        nonlocal r
         try:
-        # Make a request to the target server
             r = requests.request(
                 method=request.method,
                 url=target_url,
-            data=data,
+                data=body,
                 headers=headers,
-            stream=True,  # Enable streaming for server-sent events
+                stream=True,
             )
 
             r.raise_for_status()
 
-        # Proxy the target server's response to the client
-        def generate():
-            for chunk in r.iter_content(chunk_size=8192):
-                yield chunk
-
-        response = Response(generate(), status=r.status_code)
-
-        # Copy headers from the target server's response to the client's response
-        for key, value in r.headers.items():
-            response.headers[key] = value
+            return StreamingResponse(
+                r.iter_content(chunk_size=8192),
+                status_code=r.status_code,
+                headers=dict(r.headers),
+            )
+        except Exception as e:
+            raise e
 
-        return response
+    try:
+        return await run_in_threadpool(get_request)
     except Exception as e:
-        print(e)
         error_detail = "Ollama WebUI: Server Connection Error"
-        if r != None:
-            print(r.text)
+        if r is not None:
+            try:
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            print(res)
-
-        return (
-            jsonify(
-                {
-                    "detail": error_detail,
-                    "message": str(e),
-                }
-            ),
-            400,
-        )
-
+            except:
+                error_detail = f"Ollama: {e}"
 
-if __name__ == "__main__":
-    app.run(debug=True)
+        raise HTTPException(
+            status_code=r.status_code if r else 500,
+            detail=error_detail,
+        )

backend/apps/ollama/old_main.py

+from fastapi import FastAPI, Request, Response, HTTPException, Depends
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import StreamingResponse
+
+import requests
+import json
+from pydantic import BaseModel
+
+from apps.web.models.users import Users
+from constants import ERROR_MESSAGES
+from utils.utils import decode_token, get_current_user
+from config import OLLAMA_API_BASE_URL, WEBUI_AUTH
+
+import aiohttp
+
+app = FastAPI()
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.state.OLLAMA_API_BASE_URL = OLLAMA_API_BASE_URL
+
+# TARGET_SERVER_URL = OLLAMA_API_BASE_URL
+
+
+@app.get("/url")
+async def get_ollama_api_url(user=Depends(get_current_user)):
+    if user and user.role == "admin":
+        return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
+    else:
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+
+
+class UrlUpdateForm(BaseModel):
+    url: str
+
+
+@app.post("/url/update")
+async def update_ollama_api_url(
+    form_data: UrlUpdateForm, user=Depends(get_current_user)
+):
+    if user and user.role == "admin":
+        app.state.OLLAMA_API_BASE_URL = form_data.url
+        return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
+    else:
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+
+
+# async def fetch_sse(method, target_url, body, headers):
+#     async with aiohttp.ClientSession() as session:
+#         try:
+#             async with session.request(
+#                 method, target_url, data=body, headers=headers
+#             ) as response:
+#                 print(response.status)
+#                 async for line in response.content:
+#                     yield line
+#         except Exception as e:
+#             print(e)
+#             error_detail = "Ollama WebUI: Server Connection Error"
+#             yield json.dumps({"error": error_detail, "message": str(e)}).encode()
+
+
+@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
+async def proxy(path: str, request: Request, user=Depends(get_current_user)):
+    target_url = f"{app.state.OLLAMA_API_BASE_URL}/{path}"
+    print(target_url)
+
+    body = await request.body()
+    headers = dict(request.headers)
+
+    if user.role in ["user", "admin"]:
+        if path in ["pull", "delete", "push", "copy", "create"]:
+            if user.role != "admin":
+                raise HTTPException(
+                    status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
+                )
+    else:
+        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+
+    headers.pop("Host", None)
+    headers.pop("Authorization", None)
+    headers.pop("Origin", None)
+    headers.pop("Referer", None)
+
+    session = aiohttp.ClientSession()
+    response = None
+    try:
+        response = await session.request(
+            request.method, target_url, data=body, headers=headers
+        )
+
+        print(response)
+        if not response.ok:
+            data = await response.json()
+            print(data)
+            response.raise_for_status()
+
+        async def generate():
+            async for line in response.content:
+                print(line)
+                yield line
+            await session.close()
+
+        return StreamingResponse(generate(), response.status)
+
+    except Exception as e:
+        print(e)
+        error_detail = "Ollama WebUI: Server Connection Error"
+
+        if response is not None:
+            try:
+                res = await response.json()
+                if "error" in res:
+                    error_detail = f"Ollama: {res['error']}"
+            except:
+                error_detail = f"Ollama: {e}"
+
+        await session.close()
+        raise HTTPException(
+            status_code=response.status if response else 500,
+            detail=error_detail,
+        )

backend/apps/openai/main.py

+from fastapi import FastAPI, Request, Response, HTTPException, Depends
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import StreamingResponse, JSONResponse
+
+import requests
+import json
+from pydantic import BaseModel
+
+from apps.web.models.users import Users
+from constants import ERROR_MESSAGES
+from utils.utils import decode_token, get_current_user
+from config import OPENAI_API_BASE_URL, OPENAI_API_KEY
+
+app = FastAPI()
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.state.OPENAI_API_BASE_URL = OPENAI_API_BASE_URL
+app.state.OPENAI_API_KEY = OPENAI_API_KEY
+
+
+class UrlUpdateForm(BaseModel):
+    url: str
+
+
+class KeyUpdateForm(BaseModel):
+    key: str
+
+
+@app.get("/url")
+async def get_openai_url(user=Depends(get_current_user)):
+    if user and user.role == "admin":
+        return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL}
+    else:
+        raise HTTPException(status_code=401,
+                            detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+
+
+@app.post("/url/update")
+async def update_openai_url(form_data: UrlUpdateForm,
+                            user=Depends(get_current_user)):
+    if user and user.role == "admin":
+        app.state.OPENAI_API_BASE_URL = form_data.url
+        return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL}
+    else:
+        raise HTTPException(status_code=401,
+                            detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+
+
+@app.get("/key")
+async def get_openai_key(user=Depends(get_current_user)):
+    if user and user.role == "admin":
+        return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
+    else:
+        raise HTTPException(status_code=401,
+                            detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+
+
+@app.post("/key/update")
+async def update_openai_key(form_data: KeyUpdateForm,
+                            user=Depends(get_current_user)):
+    if user and user.role == "admin":
+        app.state.OPENAI_API_KEY = form_data.key
+        return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY}
+    else:
+        raise HTTPException(status_code=401,
+                            detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+
+
+@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
+async def proxy(path: str, request: Request, user=Depends(get_current_user)):
+    target_url = f"{app.state.OPENAI_API_BASE_URL}/{path}"
+    print(target_url, app.state.OPENAI_API_KEY)
+
+    if user.role not in ["user", "admin"]:
+        raise HTTPException(status_code=401,
+                            detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+    if app.state.OPENAI_API_KEY == "":
+        raise HTTPException(status_code=401,
+                            detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
+
+    body = await request.body()
+    # headers = dict(request.headers)
+    # print(headers)
+
+    headers = {}
+    headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}"
+    headers["Content-Type"] = "application/json"
+
+    try:
+        r = requests.request(
+            method=request.method,
+            url=target_url,
+            data=body,
+            headers=headers,
+            stream=True,
+        )
+
+        r.raise_for_status()
+
+        # Check if response is SSE
+        if "text/event-stream" in r.headers.get("Content-Type", ""):
+            return StreamingResponse(
+                r.iter_content(chunk_size=8192),
+                status_code=r.status_code,
+                headers=dict(r.headers),
+            )
+        else:
+            # For non-SSE, read the response and return it
+            # response_data = (
+            #     r.json()
+            #     if r.headers.get("Content-Type", "")
+            #     == "application/json"
+            #     else r.text
+            # )
+
+            response_data = r.json()
+
+            print(type(response_data))
+
+            if "openai" in app.state.OPENAI_API_BASE_URL and path == "models":
+                response_data["data"] = list(
+                    filter(lambda model: "gpt" in model["id"],
+                           response_data["data"]))
+
+            return response_data
+    except Exception as e:
+        print(e)
+        error_detail = "Ollama WebUI: Server Connection Error"
+        if r is not None:
+            try:
+                res = r.json()
+                if "error" in res:
+                    error_detail = f"External: {res['error']}"
+            except:
+                error_detail = f"External: {e}"
+
+        raise HTTPException(status_code=r.status_code, detail=error_detail)

backend/apps/web/main.py

-from fastapi import FastAPI, Request, Depends, HTTPException
+from fastapi import FastAPI, Depends
+from fastapi.routing import APIRoute
 from fastapi.middleware.cors import CORSMiddleware
-
-from apps.web.routers import auths, users, chats, modelfiles, utils
+from apps.web.routers import auths, users, chats, modelfiles, prompts, configs, utils
 from config import WEBUI_VERSION, WEBUI_AUTH
 
 app = FastAPI()
 
 origins = ["*"]
 
+app.state.ENABLE_SIGNUP = True
+app.state.DEFAULT_MODELS = None
+
 app.add_middleware(
     CORSMiddleware,
     allow_origins=origins,
@@ -16,16 +19,23 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-
 app.include_router(auths.router, prefix="/auths", tags=["auths"])
 app.include_router(users.router, prefix="/users", tags=["users"])
 app.include_router(chats.router, prefix="/chats", tags=["chats"])
-app.include_router(modelfiles.router, prefix="/modelfiles", tags=["modelfiles"])
-
+app.include_router(modelfiles.router,
+                   prefix="/modelfiles",
+                   tags=["modelfiles"])
+app.include_router(prompts.router, prefix="/prompts", tags=["prompts"])
 
+app.include_router(configs.router, prefix="/configs", tags=["configs"])
 app.include_router(utils.router, prefix="/utils", tags=["utils"])
 
 
 @app.get("/")
 async def get_status():
-    return {"status": True, "version": WEBUI_VERSION, "auth": WEBUI_AUTH}
+    return {
+        "status": True,
+        "version": WEBUI_VERSION,
+        "auth": WEBUI_AUTH,
+        "default_models": app.state.DEFAULT_MODELS,
+    }

backend/apps/web/models/auths.py

@@ -4,7 +4,6 @@ import time
 import uuid
 from peewee import *
 
-
 from apps.web.models.users import UserModel, Users
 from utils.utils import (
     verify_password,
@@ -123,6 +122,15 @@ class AuthsTable:
         except:
             return False
 
+    def update_email_by_id(self, id: str, email: str) -> bool:
+        try:
+            query = Auth.update(email=email).where(Auth.id == id)
+            result = query.execute()
+
+            return True if result == 1 else False
+        except:
+            return False
+
     def delete_auth_by_id(self, id: str) -> bool:
         try:
             # Delete User

backend/apps/web/models/chats.py

@@ -3,14 +3,12 @@ from typing import List, Union, Optional
 from peewee import *
 from playhouse.shortcuts import model_to_dict
 
-
 import json
 import uuid
 import time
 
 from apps.web.internal.db import DB
 
-
 ####################
 # Chat DB Schema
 ####################
@@ -62,23 +60,23 @@ class ChatTitleIdResponse(BaseModel):
 
 
 class ChatTable:
+
     def __init__(self, db):
         self.db = db
         db.create_tables([Chat])
 
-    def insert_new_chat(self, user_id: str, form_data: ChatForm) -> Optional[ChatModel]:
+    def insert_new_chat(self, user_id: str,
+                        form_data: ChatForm) -> Optional[ChatModel]:
         id = str(uuid.uuid4())
         chat = ChatModel(
             **{
                 "id": id,
                 "user_id": user_id,
-                "title": form_data.chat["title"]
-                if "title" in form_data.chat
-                else "New Chat",
+                "title": form_data.chat["title"] if "title" in
+                form_data.chat else "New Chat",
                 "chat": json.dumps(form_data.chat),
                 "timestamp": int(time.time()),
-            }
-        )
+            })
 
         result = Chat.create(**chat.model_dump())
         return chat if result else None
@@ -111,27 +109,25 @@ class ChatTable:
         except:
             return None
 
-    def get_chat_lists_by_user_id(
-        self, user_id: str, skip: int = 0, limit: int = 50
-    ) -> List[ChatModel]:
+    def get_chat_lists_by_user_id(self,
+                                  user_id: str,
+                                  skip: int = 0,
+                                  limit: int = 50) -> List[ChatModel]:
         return [
-            ChatModel(**model_to_dict(chat))
-            for chat in Chat.select()
-            .where(Chat.user_id == user_id)
-            .order_by(Chat.timestamp.desc())
+            ChatModel(**model_to_dict(chat)) for chat in Chat.select().where(
+                Chat.user_id == user_id).order_by(Chat.timestamp.desc())
             # .limit(limit)
             # .offset(skip)
         ]
 
     def get_all_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
         return [
-            ChatModel(**model_to_dict(chat))
-            for chat in Chat.select()
-            .where(Chat.user_id == user_id)
-            .order_by(Chat.timestamp.desc())
+            ChatModel(**model_to_dict(chat)) for chat in Chat.select().where(
+                Chat.user_id == user_id).order_by(Chat.timestamp.desc())
         ]
 
-    def get_chat_by_id_and_user_id(self, id: str, user_id: str) -> Optional[ChatModel]:
+    def get_chat_by_id_and_user_id(self, id: str,
+                                   user_id: str) -> Optional[ChatModel]:
         try:
             chat = Chat.get(Chat.id == id, Chat.user_id == user_id)
             return ChatModel(**model_to_dict(chat))
@@ -146,7 +142,8 @@ class ChatTable:
 
     def delete_chat_by_id_and_user_id(self, id: str, user_id: str) -> bool:
         try:
-            query = Chat.delete().where((Chat.id == id) & (Chat.user_id == user_id))
+            query = Chat.delete().where((Chat.id == id)
+                                        & (Chat.user_id == user_id))
             query.execute()  # Remove the rows, return number of rows removed.
 
             return True