Add version for Llamaindex with FastApi and Auth0

Author: AdamW

py-llamaindex/README.md

@@ -1,3 +1,94 @@
-# Assistant0: An AI Personal Assistant Secured with Auth0 - LlamaIndex Python Version
+# Assistant0: An AI Personal Assistant Secured with Auth0 - Llamaindex Python/FastAPI Version
+
+Assistant0 an AI personal assistant that consolidates your digital life by dynamically accessing multiple tools to help you stay organized and efficient.
+
+## About the template
+
+This template scaffolds an Auth0 + LlamaIndex.js + Next.js starter app. It mainly uses the following libraries:
+
+- [LlamaIndex's Python framework](https://docs.llamaindex.ai/en/stable/#introduction)
+- The [Auth0 AI SDK](https://github.com/auth0-lab/auth0-ai-python) and [Auth0 FastAPI SDK](https://github.com/auth0/auth0-fastapi) to secure the application and call third-party APIs.
+- [Auth0 FGA](https://auth0.com/fine-grained-authorization) to define fine-grained access control policies for your tools and RAG pipelines.
+
+## 🚀 Getting Started
+
+First, clone this repo and download it locally.
+
+```bash
+git clone https://github.com/auth0-samples/auth0-assistant0.git
+cd auth0-assistant0/py-llamaindex
+```
+
+The project is divided into two parts:
+
+- `backend/` contains the backend code for the Web app and API written in Python using FastAPI.
+- `frontend/` contains the frontend code for the Web app written in React as a Vite SPA.
+
+### Setup the backend
+
+```bash
+cd backend
+```
+
+Next, you'll need to set up environment variables in your repo's `.env` file. Copy the `.env.example` file to `.env`.
+
+To start with the basic examples, you'll just need to add your OpenAI API key and Auth0 credentials.
+
+- To start with the examples, you'll just need to add your OpenAI API key and Auth0 credentials for the Web app.
+  - You can setup a new Auth0 tenant with an Auth0 Web App and Token Vault following the Prerequisites instructions [here](https://auth0.com/ai/docs/call-others-apis-on-users-behalf).
+  - An Auth0 FGA account, you can create one [here](https://dashboard.fga.dev). Add the FGA store ID, client ID, client secret, and API URL to the `.env` file.
+
+Next, install the required packages using your preferred package manager, e.g. uv:
+
+```bash
+uv sync
+```
+
+Now you're ready to start the database:
+
+```bash
+# start the postgres database
+docker compose up -d
+```
+
+Initialize FGA store:
+
+```bash
+source .venv/bin/activate
+python -m app.core.fga_init
+```
+
+Now you're ready to run the development server:
+
+```bash
+source .venv/bin/activate
+uv run uvicorn app.main:app --reload
+```
+
+### Start the frontend server
+
+Rename `.env.example` file to `.env` in the `frontend` directory.
+
+Finally, you can start the frontend server in another terminal:
+
+```bash
+cd frontend
+cp .env.example .env # Copy the `.env.example` file to `.env`.
+npm install
+npm run dev
+```
+
+This will start a React vite server on port 5173.
+
+![A streaming conversation between the user and the AI](./public/images/home-page.png)
+
+Agent configuration lives in `backend/app/agents/assistant0.ts`. From here, you can change the prompt and model, or add other tools and logic.
+
+## License
+
+This project is open-sourced under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Author
+
+This project is built by [Adam W.](https://github.com/AdamWozniewski).
 
-Coming soon

py-llamaindex/backend/.env.example

@@ -0,0 +1,24 @@
+APP_BASE_URL='http://localhost:8000'
+API_PREFIX=/api
+
+AUTH0_SECRET='use [openssl rand -hex 32] to generate a 32 bytes value'
+AUTH0_DOMAIN=''
+AUTH0_CLIENT_ID=''
+AUTH0_CLIENT_SECRET=''
+
+OPENAI_API_KEY=''
+PROVIDER=openai
+
+# Database
+DATABASE_URL="postgresql+psycopg://postgres:postgres@localhost:5432/ai_documents_db"
+
+# Auth0 FGA
+FGA_STORE_ID=<your-fga-store-id>
+FGA_CLIENT_ID=<your-fga-store-client-id>
+FGA_CLIENT_SECRET=<your-fga-store-client-secret>
+FGA_API_URL=https://api.xxx.fga.dev
+FGA_API_AUDIENCE=https://api.xxx.fga.dev/
+
+# Shop API URL (Optional)
+# SHOP_API_URL="http://localhost:3001/api/shop"
+# SHOP_API_AUDIENCE="https://api.shop-online-demo.com"

py-llamaindex/backend/.gitignore

@@ -0,0 +1,10 @@
+__pycache__
+app.egg-info
+*.pyc
+.mypy_cache
+.coverage
+htmlcov
+.cache
+.venv
+.env
+

py-llamaindex/backend/.python-version

@@ -0,0 +1 @@
+3.13

py-llamaindex/backend/README.md

@@ -0,0 +1,40 @@
+# Setup the backend
+
+```bash
+cd backend
+```
+
+You'll need to set up environment variables in your repo's `.env` file. Copy the `.env.example` file to `.env`.
+
+To start with the basic examples, you'll just need to add your OpenAI API key and Auth0 credentials.
+
+- To start with the examples, you'll just need to add your OpenAI API key and Auth0 credentials for the Web app.
+  - You can setup a new Auth0 tenant with an Auth0 Web App and Token Vault following the Prerequisites instructions [here](https://auth0.com/ai/docs/call-others-apis-on-users-behalf).
+  - An Auth0 FGA account, you can create one [here](https://dashboard.fga.dev). Add the FGA store ID, client ID, client secret, and API URL to the `.env` file.
+
+Next, install the required packages using your preferred package manager, e.g. uv:
+
+```bash
+uv sync
+```
+
+Now you're ready to start and migrate the database:
+
+```bash
+# start the postgres database
+docker compose up -d
+```
+
+Initialize FGA store:
+
+```bash
+source .venv/bin/activate
+python -m app.core.fga_init
+```
+
+Now you're ready to run the development server:
+
+```bash
+source .venv/bin/activate
+uv run uvicorn app.main:app --reload
+```

py-llamaindex/backend/app/__init__.py

@@ -0,0 +1,28 @@
+from __future__ import annotations
+from llama_index.core.agent import ReActAgentWorker
+from llama_index.llms.openai import OpenAI
+
+from app.agents.tools.user_info_li import get_user_info_li
+from app.agents.tools.google_calendar_li import list_upcoming_events_li
+from app.agents.tools.shop_online_li import shop_online_li
+from app.agents.tools.context_docs_li import get_context_docs_li
+
+llm = OpenAI(model="gpt-4.1-mini", temperature=0.2)
+
+tools = [
+    get_user_info_li,
+    list_upcoming_events_li,
+    shop_online_li,
+    get_context_docs_li,
+]
+
+agent = ReActAgentWorker.from_tools(
+    tools=tools,
+    llm=llm,
+    verbose=True,
+    system_prompt=(
+        "You are a personal assistant named Assistant0. "
+        "Use tools when helpful; prefer get_context_docs for knowledge base queries. "
+        "Render email-like bodies as markdown (no code fences)."
+    ),
+).as_agent()

py-llamaindex/backend/app/agents/__init__.py

@@ -0,0 +1,38 @@
+from __future__ import annotations
+from typing import List
+
+from llama_index.core.tools import FunctionTool
+from pydantic import BaseModel
+
+from app.core.rag_li import retrieve_nodes
+from app.core.fga import authorization_manager
+
+
+class GetContextDocsSchema(BaseModel):
+    question: str
+
+async def get_context_docs_li_fn(question: str, user_email: str) -> str:
+    nodes = retrieve_nodes(question, top_k=12)
+
+    allowed: List[str] = []
+    for n in nodes:
+        doc_id = n.metadata.get("document_id")
+        if not doc_id:
+            continue
+
+        can_view = await authorization_manager.check_relation(
+            user=user_email, doc_id=doc_id, relation="can_view"
+        )
+        if can_view:
+            allowed.append(n.get_content(metadata_mode="none"))
+
+    if not allowed:
+        return "I couldn't find any documents you are allowed to view."
+    return "\n\n".join(allowed)
+
+
+get_context_docs_li = FunctionTool.from_defaults(
+    name="get_context_docs",
+    description="Retrieve documents from the knowledge base (LlamaIndex + FGA).",
+    fn=get_context_docs_li_fn,
+)