Simple Kafka-based reliable AI streaming
Project description
Reliable AI Streams
Simple Kafka-based reliable streaming for AI applications. Handles reconnections, replays, and ensures no message loss.
Features
- ✅ Reliable streaming (survives page refreshes)
- ✅ Replay from any point
- ✅ Simple API
- ✅ Production-ready
- ✅ Type-safe
Installation
pip install reliable-ai-streams
Quick Start
from reliable_ai_streams import Publisher, Subscriber, Chunk
# Publish
with Publisher() as pub:
chunk = Chunk(
conversation_id="chat-123",
content="Hello!",
type="text"
)
pub.publish(chunk)
# Subscribe
with Subscriber() as sub:
for chunk in sub.subscribe("chat-123"):
print(chunk.content)
if chunk.type == "finish":
break
Configuration
Set via environment variables:
KAFKA_BOOTSTRAP_SERVERS=localhost:9092
KAFKA_TOPIC_PREFIX=ai-stream
Or pass directly:
from reliable_ai_streams import Config, Publisher
config = Config(bootstrap_servers="kafka:9092")
publisher = Publisher(config)
FastAPI Example
from fastapi import FastAPI
from fastapi.responses import StreamingResponse
from reliable_ai_streams import Publisher, Subscriber
app = FastAPI()
publisher = Publisher()
subscriber = Subscriber()
@app.on_event("startup")
def startup():
publisher.connect()
subscriber.connect()
@app.get("/stream/{conversation_id}")
def stream(conversation_id: str):
def events():
for chunk in subscriber.subscribe(conversation_id):
yield f"data: {chunk.to_json().decode()}\n\n"
return StreamingResponse(events(), media_type="text/event-stream")
License
MIT
## Installation & Usage
```bash
# Development setup
git clone <your-repo>
cd reliable-ai-streams
# Create virtual environment
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# Install
pip install -e .
# Or with dev dependencies
pip install -e ".[dev]"
# Setup environment
cp .env.example .env
# Edit .env with your Kafka settings
# Run example
python examples/basic_example.py
# Run tests (requires Kafka running)
pytest
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file reliable_ai_streams-0.1.0.tar.gz.
File metadata
- Download URL: reliable_ai_streams-0.1.0.tar.gz
- Upload date:
- Size: 6.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
879b91ea303988713ea6b0ec20a5c9e0e04f05785c5fac0cf414fdad6619f32f
|
|
| MD5 |
beb1fbb1467c088919b3fbd32740e225
|
|
| BLAKE2b-256 |
968e69cf99646460f06c9530b470fd70073e2adf6ce5880f99cd575540b2dfa1
|
File details
Details for the file reliable_ai_streams-0.1.0-py3-none-any.whl.
File metadata
- Download URL: reliable_ai_streams-0.1.0-py3-none-any.whl
- Upload date:
- Size: 6.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b0ca40dd6203ddeb84612c7d1df5f7f71f5c54ea48c117805af52d1544f04c00
|
|
| MD5 |
df007afdb918d539623ab57dc7723909
|
|
| BLAKE2b-256 |
db4675a0ffb985d0e5112d59c2e899c1f6ea175c6a09b917d6e0fcaeebec9f5f
|