This release is a pre-release and may not be stable for production use.
Django AI SDK
A Django SDK for building AI-powered applications with support for multiple LLM providers, RAG (Retrieval-Augmented Generation), and streaming responses.
Project Status: Read This First
This is an early preview. We're actively iterating on the API and learning from real usage. Here's what that means for you:
- Expect breaking changes: APIs will shift as we find better patterns.
- Migrations might be reset: Don't rely on database schema stability between versions.
- Not for production: Use this for experimentation, prototypes, and side projects. Keep critical workloads elsewhere.
- Watch the repo: Things change quickly. Star & watch to stay in the loop.
- Your feedback shapes the SDK: Break things, open issues, tell us what hurts.
We'd love to have you along for the ride, just keep your seatbelt on.
Install
pip install django-ai-sdk
Or with uv:
uv add django-ai-sdk
Quick Start
1. Add to INSTALLED_APPS
# settings.py
INSTALLED_APPS = [
...
"django_ai_sdk",
]
Then run python manage.py migrate.
2. Define your assistant
# assistants.py
from django_ai_sdk import Assistant
class HelpDeskAssistant(Assistant):
name = "Help Desk"
model = "gpt-4o"
instructions = "You are a helpful support assistant."
3. Return a streaming response
# views.py
from .assistants import HelpDeskAssistant
assistant = HelpDeskAssistant()
@router.post("/chat")
async def chat(request, payload: ChatRequest):
return await assistant.as_view(
payload.messages,
thread_id=payload.thread_id,
)
Features
- RAG Pipelines: BM25, ChromaDB, and Qdrant hybrid search with query expansion.
- Streaming Responses: Built-in SSE streaming. Works with Vercel AI SDK protocol.
- Conversation Storage: Automatic message persistence. Thread-based history out of the box.
- Tool Calling: MCP, memory, and custom tools — all managed by your Assistant.
- Reindexing: Hot-reload documents. Cached embeddings with simple refresh API.
Documentation
Full documentation and examples: github.com/django-ai-sdk/django-ai-sdk
1 maintainer
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 django_ai_sdk-0.1.1a11.tar.gz.
File metadata
- Download URL: django_ai_sdk-0.1.1a11.tar.gz
- Upload date:
- Size: 127.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.6.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
86935a33f6b2a807e172135fcad4615054ec0b347596ae227d404154c8ca7397
|
|
| MD5 |
d6c786ec6e77ce9eae6ac72642eba6aa
|
|
| BLAKE2b-256 |
4ad57b92cd43381e87ef7b0284ef495eb772771143c78e02fcbe24f1aaff79ef
|
File details
Details for the file django_ai_sdk-0.1.1a11-py3-none-any.whl.
File metadata
- Download URL: django_ai_sdk-0.1.1a11-py3-none-any.whl
- Upload date:
- Size: 164.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.6.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0a3657c8f008f84afd216b755bf3dc7022d29cdd62390f212f87bf3284f5cec7
|
|
| MD5 |
0b1c133eb681658e4546c44a63b68946
|
|
| BLAKE2b-256 |
e78ad9b7c5e7414b89de0799ed03ed613ae6e4a016eb2d299be9530b5ad59c00
|
