infuseai 1.0.0

Python SDK for InfuseAI - Build AI applications with your own knowledge bases

infuseai

The official Python client for InfuseAI. This SDK empowers you to seamlessly integrate your custom RAG apps and Knowledge Bases into any Python application, including Django, Flask, and FastAPI.

Installation

pip install infuseai

Usage

1. Import and Initialize

Initialize the InfuseClient with your application credentials. You can retrieve these from your App's dashboard in InfuseAI.

from infuseai import InfuseClient

client = InfuseClient(
    client_id="YOUR_CLIENT_ID",  # Your User ID
    app_id="YOUR_APP_ID",        # The specific AI App ID
    api_key="YOUR_API_KEY",      # The API Key for this App
)

2. Query Your App

Send prompts to your AI using the query method. The SDK manages context retrieval (RAG) and LLM inference behind the scenes.

def ask_my_assistant():
    try:
        response = client.query("What does the documentation say about deployment?")
        
        print("Answer:", response.response)
        
        # If your app uses a Knowledge Base, you can inspect the sources used:
        if response.sources:
            print("Sources Used:", [s.name for s in response.sources])
            
    except Exception as e:
        print(f"Failed to query InfuseAI: {e}")

ask_my_assistant()

3. Using with Django

# views.py
from django.http import JsonResponse
from infuseai import InfuseClient

client = InfuseClient(
    client_id="YOUR_CLIENT_ID",
    app_id="YOUR_APP_ID",
    api_key="YOUR_API_KEY",
)

def chat_view(request):
    query = request.POST.get("query", "")
    response = client.query(query)
    return JsonResponse({
        "response": response.response,
        "sources": [{"name": s.name, "content": s.content} for s in response.sources]
    })

4. Using with FastAPI

from fastapi import FastAPI
from infuseai import InfuseClient

app = FastAPI()
client = InfuseClient(
    client_id="YOUR_CLIENT_ID",
    app_id="YOUR_APP_ID",
    api_key="YOUR_API_KEY",
)

@app.post("/chat")
async def chat(query: str):
    response = client.query(query)
    return {"response": response.response, "sources_count": len(response.sources)}

5. Context Manager Support

from infuseai import InfuseClient

with InfuseClient(
    client_id="YOUR_CLIENT_ID",
    app_id="YOUR_APP_ID",
    api_key="YOUR_API_KEY",
) as client:
    response = client.query("Tell me about your product")
    print(response.response)

API Reference

InfuseClient

Constructor

InfuseClient(client_id, app_id, api_key, base_url=None)

Parameters:

Parameter	Type	Required	Description
client_id	str	Yes	Your unique user identifier from the dashboard.
app_id	str	Yes	The ID of the specific app you want to interact with.
api_key	str	Yes	The secret API key for authentication.
base_url	str	No	Optional override for the API endpoint (default: Production).

client.query(text)

Sends a prompt to the InfuseAI backend.

Signature

query(text: str) -> QueryResponse

Returns

A QueryResponse dataclass:

@dataclass
class QueryResponse:
    response: str           # The AI's generated answer
    sources: List[Source]   # List of sources used for RAG
    credits_left: float     # Remaining credits
    credits_used: float     # Credits consumed by this query
    raw: Dict[str, Any]     # Raw API response

Error Handling

The SDK provides specific exceptions for different error scenarios:

from infuseai import (
    InfuseClient,
    InfuseAuthError,
    InfuseCreditsError,
    InfuseAPIError,
    InfuseConfigError,
)

try:
    response = client.query("Hello")
except InfuseAuthError as e:
    print(f"Authentication failed: {e.message}")
except InfuseCreditsError as e:
    print(f"Insufficient credits: {e.message}")
except InfuseAPIError as e:
    print(f"API error ({e.status_code}): {e.message}")
except InfuseConfigError as e:
    print(f"Configuration error: {e.message}")

License

ISC