How to Integrate Unfil AI with Your App

Unfil AI provides production-ready APIs for building RAG (Retrieval-Augmented Generation) applications, vector search, and LLM orchestration. Handle 500M+ requests with sub-200ms latency.

Step 1: Get API Access

Step 2: Generate an API Key

Navigate to API Keys in your dashboard and create a new key. Store it securely in your environment variables.

export UNFIL_API_KEY="your-api-key"

Step 3: Install the SDK

# Python
pip install unfil-ai

# Node.js
npm install @unfil-ai/sdk

Step 4: Make Your First Request

from unfil_ai import UnfilClient

client = UnfilClient(api_key="your-api-key")

# Generate embeddings
response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Your text to embed"
)

print(response.data[0].embedding)

# Vector search (RAG)
results = client.vector.search(
    collection_id="your-collection",
    query="Search query",
    top_k=5,
    filters={"category": "docs"}
)

for result in results:
    print(f"{result.score}: {result.text}")

Key Features of Unfil AI

Vector Search: High-performance semantic search with 95%+ recall across millions of vectors
Embedding Generation: Support for OpenAI, Cohere, and custom embedding models
RAG Pipeline: Complete retrieval-augmented generation with context injection
Multi-Region: Edge deployment in 300+ locations for global low latency
Auto-Scaling: Handle traffic spikes from 10 to 10,000 requests per second

Best Use Cases

Knowledge Base Search: Build semantic search across documentation, wikis, and FAQs
Chatbots & Assistants: RAG-powered AI assistants with accurate, context-aware responses
Recommendation Engines: Content and product recommendations using vector similarity
Document Analysis: Semantic search and clustering for large document collections

For more information, visit Unfil AI Documentation.

Unfil AI