| Name | fastapi-agent JSON |
| Version |
0.1.4
JSON |
| download |
| home_page | None |
| Summary | Add an AI Agent to your FastAPI application. The agent knows how to interact with your endpoints within a chat interface. |
| upload_time | 2025-08-04 10:23:41 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
agent
ai
api
chat
fastapi
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# 🤖 FastAPI Agent
> 💬 **Talk to your FastAPI app like it's a teammate.**
FastAPI Agent integrates an AI Agent into your FastAPI application.
It allows interaction with your API endpoints through a chat interface or directly via the `/agent/query` API route.
## ⚙️ Installation:
To install the package, run:
```bash
pip install fastapi_agent
```
## 🧪 Usage:
To use the FastAPI Agent, initialize it with your FastAPI app and AI model.<br>
You can use the default agent routes or add custom ones to your FastAPI application to interact with the agent via a chat interface or API endpoint.
Here is a simple example of how to use the FastAPI Agent with your FastAPI application:
#### .env
```bash
OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
```
#### app.py
```python
import uvicorn
from dotenv import load_dotenv
from fastapi import FastAPI
from fastapi_agent import FastAPIAgent
# load OPENAI_API_KEY from .env
load_dotenv()
# set your FastAPI app
app = FastAPI(
title="YOUR APP TITLE",
version="0.1.0",
description="some app description",
)
# add routes
@app.get("/")
async def root():
"""Welcome endpoint that returns basic API information"""
return {"message": "Welcome to Test API"}
# add the FastAPI Agent + default routes
FastAPIAgent(
app,
model="openai:gpt-4",
base_url="http://localhost:8000",
include_router=True,
)
uvicorn.run(app, host="0.0.0.0", port=8000)
```
## 🧭 Default Routes
FastAPI Agent provides two default routes:
1. **`/agent/query`** – Ask anything about your API using natural language. 🧠
```bash
curl -k -X POST "http://127.0.0.1:8000/agent/query" \
-H "Content-Type: application/json" \
-d '{"query": "show all endpoints"}'
```
2. **`/agent/chat`** – A simple web-based chat interface to interact with your API. 💬
<br>
> 💡 _You can also add custom routes using agent.chat() methode - [Example](https://github.com/orco82/fastapi-agent/blob/main/examples/3_fastapi_agent_example.py)_
## 🧩 Additional Arguments:
If your application routes use **Depends** (e.g., an API key), you can pass a dictionary of headers.
The agent will use them to call your routes and apply the same dependencies to the `/agent/query` route.
```python
api_key = "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
FastAPIAgent(
app,
model="openai:gpt-4",
base_url="https://localhost:8000",
deps={"api-key": api_key},
include_router=True,
)
```
---
You can also pass the `ignore_routes` argument to prevent the agent from accessing specific routes in your application:
```python
FastAPIAgent(
app,
model="openai:gpt-4",
base_url="https://localhost:8000",
ignore_routes=["/user/delete/{user_id}"],
include_router=True,
)
```
## 📁 Additional Examples:
Check out our examples for [ai_agent](https://github.com/orco82/fastapi-agent/blob/main/examples/1_ai_agent_example.py),
[fastapi_discovery](https://github.com/orco82/fastapi-agent/blob/main/examples/2_fastapi_discovery_example.py),
and [fastapi_agent](https://github.com/orco82/fastapi-agent/blob/main/examples/3_fastapi_agent_example.py).
All examples are available [here](https://github.com/orco82/fastapi-agent/blob/main/examples/).
---
#### If you're using *Depends* in your routes, make sure to pass the required headers when calling the `/agent/query` endpoint like the examples below:
#### python
```python
import requests
res = requests.post(
"http://127.0.0.1:8000/agent/query",
json={"query": "show all endpoints"},
headers={"deps": '{"api-key": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"}'}
)
print(res.json())
```
#### curl
```bash
curl -k -X POST "http://127.0.0.1:8000/agent/query" \
-H 'deps: {"api-key": "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"}' \
-H "Content-Type: application/json" \
-d '{"query": "show all endpoints"}'
```
## 📜 License
This project is licensed under the MIT License.
Raw data
{
"_id": null,
"home_page": null,
"name": "fastapi-agent",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "agent, ai, api, chat, fastapi",
"author": null,
"author_email": "Or Cohen <orco82@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/b3/e6/fa06632404978196f3164fbcfa8608dd9b62df1795e1b800185ea97c3da2/fastapi_agent-0.1.4.tar.gz",
"platform": null,
"description": "# \ud83e\udd16 FastAPI Agent\n\n> \ud83d\udcac **Talk to your FastAPI app like it's a teammate.**\n\nFastAPI Agent integrates an AI Agent into your FastAPI application. \nIt allows interaction with your API endpoints through a chat interface or directly via the `/agent/query` API route.\n\n## \u2699\ufe0f Installation:\n\nTo install the package, run:\n```bash\npip install fastapi_agent\n```\n\n\n## \ud83e\uddea Usage:\n\nTo use the FastAPI Agent, initialize it with your FastAPI app and AI model.<br>\nYou can use the default agent routes or add custom ones to your FastAPI application to interact with the agent via a chat interface or API endpoint.\n\nHere is a simple example of how to use the FastAPI Agent with your FastAPI application:\n\n#### .env\n```bash\nOPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx\n```\n\n#### app.py\n```python\nimport uvicorn\nfrom dotenv import load_dotenv\n\nfrom fastapi import FastAPI\nfrom fastapi_agent import FastAPIAgent\n\n# load OPENAI_API_KEY from .env\nload_dotenv()\n\n# set your FastAPI app\napp = FastAPI(\n title=\"YOUR APP TITLE\",\n version=\"0.1.0\",\n description=\"some app description\",\n)\n\n# add routes\n@app.get(\"/\")\nasync def root():\n \"\"\"Welcome endpoint that returns basic API information\"\"\"\n return {\"message\": \"Welcome to Test API\"}\n\n# add the FastAPI Agent + default routes\nFastAPIAgent(\n app,\n model=\"openai:gpt-4\",\n base_url=\"http://localhost:8000\",\n include_router=True,\n)\n\nuvicorn.run(app, host=\"0.0.0.0\", port=8000)\n```\n\n\n## \ud83e\udded Default Routes\n\nFastAPI Agent provides two default routes:\n\n1. **`/agent/query`** \u2013 Ask anything about your API using natural language. \ud83e\udde0\n\n ```bash\ncurl -k -X POST \"http://127.0.0.1:8000/agent/query\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"query\": \"show all endpoints\"}'\n```\n\n2. **`/agent/chat`** \u2013 A simple web-based chat interface to interact with your API. \ud83d\udcac\n\n<br>\n\n> \ud83d\udca1 _You can also add custom routes using agent.chat() methode - [Example](https://github.com/orco82/fastapi-agent/blob/main/examples/3_fastapi_agent_example.py)_\n \n\n## \ud83e\udde9 Additional Arguments:\nIf your application routes use **Depends** (e.g., an API key), you can pass a dictionary of headers. \nThe agent will use them to call your routes and apply the same dependencies to the `/agent/query` route.\n\n```python\napi_key = \"xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx\"\n\nFastAPIAgent(\n app,\n model=\"openai:gpt-4\",\n base_url=\"https://localhost:8000\",\n deps={\"api-key\": api_key},\n include_router=True,\n)\n```\n\n---\n\nYou can also pass the `ignore_routes` argument to prevent the agent from accessing specific routes in your application:\n\n```python\n\nFastAPIAgent(\n app,\n model=\"openai:gpt-4\",\n base_url=\"https://localhost:8000\",\n ignore_routes=[\"/user/delete/{user_id}\"],\n include_router=True,\n)\n\n```\n\n## \ud83d\udcc1 Additional Examples:\n\nCheck out our examples for [ai_agent](https://github.com/orco82/fastapi-agent/blob/main/examples/1_ai_agent_example.py), \n[fastapi_discovery](https://github.com/orco82/fastapi-agent/blob/main/examples/2_fastapi_discovery_example.py), \nand [fastapi_agent](https://github.com/orco82/fastapi-agent/blob/main/examples/3_fastapi_agent_example.py). \nAll examples are available [here](https://github.com/orco82/fastapi-agent/blob/main/examples/).\n\n---\n\n#### If you're using *Depends* in your routes, make sure to pass the required headers when calling the `/agent/query` endpoint like the examples below:\n\n#### python\n```python\nimport requests\n\nres = requests.post(\n \"http://127.0.0.1:8000/agent/query\", \n json={\"query\": \"show all endpoints\"},\n headers={\"deps\": '{\"api-key\": \"xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx\"}'}\n)\nprint(res.json())\n```\n\n#### curl\n```bash\ncurl -k -X POST \"http://127.0.0.1:8000/agent/query\" \\\n -H 'deps: {\"api-key\": \"xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx\"}' \\\n -H \"Content-Type: application/json\" \\\n -d '{\"query\": \"show all endpoints\"}'\n```\n\n## \ud83d\udcdc License\n\nThis project is licensed under the MIT License.",
"bugtrack_url": null,
"license": "MIT",
"summary": "Add an AI Agent to your FastAPI application. The agent knows how to interact with your endpoints within a chat interface.",
"version": "0.1.4",
"project_urls": {
"Bug Tracker": "https://github.com/orco82/fastapi-agent/issues",
"Documentation": "https://github.com/orco82/fastapi-agent#readme",
"Homepage": "https://github.com/orco82/fastapi-agent",
"Repository": "https://github.com/orco82/fastapi-agent"
},
"split_keywords": [
"agent",
" ai",
" api",
" chat",
" fastapi"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f75b2fe757342d089aa663e8d46b0e54049ded623094d7a6b36190126160738e",
"md5": "16a767d0664090df3fb1f891cd48c36e",
"sha256": "893bc4639901eb2a66e71d1b54107f9e89922c24c597abad17b45ba40a39d493"
},
"downloads": -1,
"filename": "fastapi_agent-0.1.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "16a767d0664090df3fb1f891cd48c36e",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 25998,
"upload_time": "2025-08-04T10:23:39",
"upload_time_iso_8601": "2025-08-04T10:23:39.635484Z",
"url": "https://files.pythonhosted.org/packages/f7/5b/2fe757342d089aa663e8d46b0e54049ded623094d7a6b36190126160738e/fastapi_agent-0.1.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "b3e6fa06632404978196f3164fbcfa8608dd9b62df1795e1b800185ea97c3da2",
"md5": "8f2d46955f46dc254c7da107f753a6bb",
"sha256": "df69883d5b279b374244f3ea84b064f984ac7d0dc9f82ad71846fe76aabc9b17"
},
"downloads": -1,
"filename": "fastapi_agent-0.1.4.tar.gz",
"has_sig": false,
"md5_digest": "8f2d46955f46dc254c7da107f753a6bb",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 121446,
"upload_time": "2025-08-04T10:23:41",
"upload_time_iso_8601": "2025-08-04T10:23:41.255356Z",
"url": "https://files.pythonhosted.org/packages/b3/e6/fa06632404978196f3164fbcfa8608dd9b62df1795e1b800185ea97c3da2/fastapi_agent-0.1.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-04 10:23:41",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "orco82",
"github_project": "fastapi-agent",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "fastapi-agent"
}
