Skip to main content

​
Welcome to context-window

Building AI applications that answer questions from your documents shouldn’t be complicated. context-window provides a simple, elegant API that handles the entire RAG (Retrieval-Augmented Generation) pipeline.

​
Why context-window?

context-window eliminates the complexity of building RAG systems by providing a complete solution:

📄 Ingest Documents

Support for .txt, .md, and .pdf files with automatic text extraction

✂️ Smart Chunking

Intelligent text chunking with configurable overlap to preserve context

🧮 OpenAI Embeddings

Powered by OpenAI’s text-embedding-3-small model for high-quality vector representations

🗄️ Pinecone Storage

Scalable vector storage with Pinecone’s serverless infrastructure

🔍 Semantic Search

Fast similarity search to retrieve relevant context for any question

💬 Accurate Answers

LLM-powered answers with source citations and strict RAG guardrails

​
Key Features

​
Strict RAG - No Hallucinations

Unlike general chat models, context-window only answers from YOUR documents. If the answer isn’t found, it says “I don’t know based on the uploaded files.”

​
Idempotent Ingestion

Re-running ingestion with the same files won’t create duplicates. Chunk IDs are content-based and stable, making updates safe and predictable.

​
Source Citations

Every answer includes references to the source documents used, making it easy to verify information and maintain trust.

​
Installation

1

Install the package

Install context-window using npm or your preferred package manager:
npm install context-window
2

Create a Pinecone Index

First-time setup requires creating a Pinecone index:
  1. Go to Pinecone Console
  2. Click Create Index
  3. Configure your index:
    • Name: context-window (or any name you prefer)
    • Dimensions: 1536 (required for OpenAI embeddings)
    • Metric: cosine (recommended)
    • Cloud: AWS or GCP (AWS us-east-1 for free tier)
  4. Click Create Index
The free tier includes 1 serverless index with 100K vectors, perfect for testing and small projects.
3

Get your API keys

You’ll need API keys from both OpenAI and Pinecone:
  1. Visit OpenAI API Keys
  2. Click Create new secret key
  3. Copy the key (starts with sk-...)
  4. Store it securely - you won’t be able to see it again
  1. Visit Pinecone Console
  2. Go to API Keys in the left sidebar
  3. Copy your API key
  4. Note your environment/region (e.g., us-east-1)
4

Configure environment variables

Create a .env file in your project root:
# OpenAI Configuration
OPENAI_API_KEY=sk-...

# Pinecone Configuration
PINECONE_API_KEY=...
PINECONE_INDEX=context-window
PINECONE_ENVIRONMENT=us-east-1
Never commit your .env file to version control. Add it to .gitignore.

​
Quick Start

Create your first RAG application in minutes: 
import { createCtxWindow, getCtxWindow } from "context-window";

// Create a context window with your documents
await createCtxWindow({
  namespace: "my-docs",
  data: ["./documents"],
  ai: { provider: "openai", model: "gpt-4o-mini" },
  vectorStore: { provider: "pinecone" }
});

// Retrieve and use it
const cw = getCtxWindow("my-docs");

// Ask a question
const { text, sources } = await cw.ask("What is the main topic?");
console.log(text);     // AI-generated answer
console.log(sources);  // ["document1.pdf", "notes.md"]
You can pass a single file, multiple files, or entire directories to the data parameter. Supported formats: .txt, .md, .pdf

​
What Happens Behind the Scenes

When you create a context window, here’s what happens:
  1. Ingests your documents by reading all .txt, .md, and .pdf files
  2. Chunks the text into overlapping segments (default: 1000 chars)
  3. Embeds each chunk using OpenAI’s text-embedding-3-small
  4. Stores vectors in your Pinecone index
  5. Retrieves relevant chunks when you ask a question
  6. Generates an answer using GPT-4o-mini with strict RAG instructions

​
Common Customizations

​
Using Different Models

await createCtxWindow({
  namespace: "my-docs",
  data: ["./docs"],
  ai: {
    provider: "openai",
    model: "gpt-4o"  // Use GPT-4 for better accuracy
  },
  vectorStore: { provider: "pinecone" }
});

const cw = getCtxWindow("my-docs");

​
Adjusting Chunk Size

await createCtxWindow({
  namespace: "my-docs",
  data: ["./docs"],
  chunk: {
    size: 1500,    // Larger chunks for more context
    overlap: 200   // More overlap to preserve continuity
  },
  ai: { provider: "openai" },
  vectorStore: { provider: "pinecone" }
});

const cw = getCtxWindow("my-docs");

​
Fine-tuning Retrieval

await createCtxWindow({
  namespace: "my-docs",
  data: ["./docs"],
  limits: {
    topK: 5,               // Retrieve top 5 most relevant chunks
    scoreThreshold: 0.7,   // Only use high-confidence matches
    maxContextChars: 6000  // Limit context size
  },
  ai: { provider: "openai" },
  vectorStore: { provider: "pinecone" }
});

const cw = getCtxWindow("my-docs");

​
Troubleshooting

Make sure:
  • Your Pinecone index exists in the console
  • PINECONE_INDEX in .env matches your index name
  • You’re using the correct environment/region
Your Pinecone index must have 1536 dimensions. If you created it with wrong dimensions:
  1. Delete the old index in Pinecone Console
  2. Create a new one with 1536 dimensions
  3. Re-run your ingestion
Verify your API keys:
  • OpenAI key starts with sk-
  • Keys are correctly set in .env
  • No extra spaces or quotes around the keys
Try:
  • Lowering scoreThreshold or removing it entirely
  • Increasing topK to retrieve more chunks
  • Rephrasing your question to match document content
  • Verifying documents were ingested successfully

​
Next Steps

Use Cases

Explore real-world applications and examples

API Reference

Complete API documentation and configuration options

Best Practices

Tips for optimizing performance and accuracy

Examples

Browse complete code examples for common scenarios
Need more help? Check out the Troubleshooting guide or open an issue on GitHub.