> ## Documentation Index
> Fetch the complete documentation index at: https://docs.moorcheh.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# LangChain Integration

> Lightning-fast semantic search engine and vector store using Maximally Informative Binarization (MIB) and Information-Theoretic Score (ITS)

## What is Moorcheh?

[Moorcheh](https://www.moorcheh.ai/) is a lightning-fast semantic search engine and vector store. Instead of using simple distance metrics like L2 or Cosine, Moorcheh uses Maximally Informative Binarization (MIB) and Information-Theoretic Score (ITS) to retrieve accurate document chunks.

The following tutorial will allow you to use Moorcheh and LangChain to upload and store text documents and vector embeddings as well as retrieve relevant chunks for all of your queries.

## Key Features

<CardGroup cols={2}>
  <Card title="MIB Technology" icon="brain">
    Uses Maximally Informative Binarization for superior search accuracy
  </Card>

  <Card title="ITS Scoring" icon="chart-line">
    Information-Theoretic Score provides better relevance ranking
  </Card>

  <Card title="LangChain Integration" icon="link">
    Seamless integration with LangChain ecosystem
  </Card>

  <Card title="Lightning Fast" icon="bolt">
    Optimized for speed and performance
  </Card>
</CardGroup>

## Setup

First, install the necessary package:

```bash theme={null}
pip install langchain-moorcheh
```

## Initialization

Get started with Moorcheh

<Steps>
  <Step title="Sign Up">
    Sign up or log in at the [Moorcheh Console](https://console.moorcheh.ai/)
  </Step>

  <Step title="Generate API Key">
    Go to the "API Keys" tab and generate an API key
  </Step>

  <Step title="Set Environment Variable">
    Save the key as an environment variable named `MOORCHEH_API_KEY`
  </Step>

  <Step title="Create Namespace">
    In the Console, open the "Namespaces" tab and click "Create namespace"; or initialize it programmatically
  </Step>

  <Step title="Start Using">
    Use your API key to create namespaces, upload documents, and retrieve answers
  </Step>
</Steps>

<Info>
  For more information about the Moorcheh SDK functions, see the [GitHub repository](https://github.com/moorcheh-ai/moorcheh-python-sdk).
</Info>

## Importing Packages

Import the required packages:

```python theme={null}
from langchain_moorcheh import MoorchehVectorStore
from moorcheh_sdk import MoorchehClient

import logging
import os
from uuid import uuid4
import asyncio
from typing import Any, List, Optional, Literal, Tuple, Type, TypeVar, Sequence
from langchain_core.documents import Document
from langchain_core.embeddings import Embeddings
from langchain_core.vectorstores import VectorStore
from google.colab import userdata
```

## Code Setup

Set your Moorcheh API Key in your environment variables:

```python theme={null}
MOORCHEH_API_KEY = os.environ['MOORCHEH_API_KEY']
```

Set up your namespace name, type, and create the vector store:

```python theme={null}
namespace = "your_namespace_name"
namespace_type = "text" # or vector
store = MoorchehVectorStore(
            api_key=MOORCHEH_API_KEY,
            namespace=namespace,
            namespace_type=namespace_type
        )
```

## Adding Documents

Create and add documents to your vector store:

```python theme={null}
document_1 = Document(
    page_content="Brewed a fresh cup of Ethiopian coffee and paired it with a warm croissant.",
    metadata={"source": "blog"},
)

document_2 = Document(
    page_content="Tomorrow's weather will be sunny with light winds, reaching a high of 78°F.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Experimenting with LangChain for an AI-powered note-taking assistant!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Local bakery donates 500 loaves of bread to the community food bank.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="That concert last night was absolutely unforgettable—what a performance!",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Check out our latest article: 5 ways to boost productivity while working from home.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The ultimate guide to mastering homemade pizza dough.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph just made multi-agent workflows way easier—seriously impressive!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="Oil prices rose 3% today after unexpected supply cuts from major exporters.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I really hope this post doesn't vanish into the digital void…",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]

uuids = [str(uuid4()) for _ in range(len(documents))]

store.add_documents(documents=documents, ids=uuids)
```

## Delete Documents

Remove documents from your vector store:

```python theme={null}
store.delete(ids=["chunk_id_here"])
```

## Query Engine

Once your namespace has been created and you have uploaded documents into it, you can ask queries about the documents directly through the vector store. Set the query and LLM you would like to answer your query.

```python theme={null}
query = "Give me a brief summary of the provided documents"
answer = store.generative_answer(query, ai_model = "anthropic.claude-sonnet-4-6")
print(answer)
```

<Info>
  For more information on supported LLMs, please visit our [Github page](https://github.com/moorcheh-ai/moorcheh-python-sdk).
</Info>

## Advanced Usage

### Custom Embeddings

You can use custom embeddings with Moorcheh:

```python theme={null}
from langchain.embeddings import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()
store = MoorchehVectorStore(
    api_key=MOORCHEH_API_KEY,
    namespace=namespace,
    namespace_type=namespace_type,
    embedding=embeddings
)
```

### Search with Similarity

Search for similar documents:

```python theme={null}
# Search for similar documents
results = store.similarity_search("coffee and breakfast", k=3)
for doc in results:
    print(doc.page_content)
    print(doc.metadata)
    print("---")
```

### Search with Score

Get similarity scores along with results:

```python theme={null}
# Search with scores
results = store.similarity_search_with_score("weather forecast", k=3)
for doc, score in results:
    print(f"Score: {score}")
    print(f"Content: {doc.page_content}")
    print("---")
```

## Configuration Options

### Namespace Types

Moorcheh supports two namespace types:

<CardGroup cols={2}>
  <Card title="Text Namespace" icon="file-text">
    Store and search text documents with automatic embedding generation
  </Card>

  <Card title="Vector Namespace" icon="vector-square">
    Store pre-computed vector embeddings for custom use cases
  </Card>
</CardGroup>

### AI Models

Supported AI models for generative answers:

* `anthropic.claude-sonnet-4-6` - Claude Sonnet 4.6
* `anthropic.claude-opus-4-6-v1` - Claude Opus 4.6
* `meta.llama4-maverick-17b-instruct-v1:0` - Llama 4 Maverick 17B
* `amazon.nova-pro-v1:0` - Amazon Nova Pro
* `deepseek.r1-v1:0` - DeepSeek R1
* `deepseek.v3.2` - DeepSeek V3.2
* `openai.gpt-oss-120b-1:0` - OpenAI GPT OSS 120B
* `qwen.qwen3-32b-v1:0` - Qwen 3 32B
* `qwen.qwen3-next-80b-a3b` - Qwen3 Next 80B A3B

## Best Practices

### Document Preparation

<Steps>
  <Step title="Clean Your Data">
    Remove unnecessary whitespace and format text consistently
  </Step>

  <Step title="Add Metadata">
    Include relevant metadata for better filtering and organization
  </Step>

  <Step title="Chunk Appropriately">
    Split large documents into meaningful chunks
  </Step>

  <Step title="Use Unique IDs">
    Generate unique identifiers for each document
  </Step>
</Steps>

### Performance Optimization

* Use appropriate chunk sizes (typically 500-1000 characters)
* Batch document uploads for better performance
* Monitor your API usage and rate limits
* Use caching for frequently accessed data

### Error Handling

```python theme={null}
try:
    store.add_documents(documents=documents, ids=uuids)
    print("Documents added successfully")
except Exception as e:
    print(f"Error adding documents: {e}")
```

## Troubleshooting

### Common Issues

<AccordionGroup>
  <Accordion title="API Key Issues">
    * Ensure your API key is correctly set in environment variables
    * Check that the API key has the necessary permissions
    * Verify the API key is not expired
  </Accordion>

  <Accordion title="Namespace Problems">
    * Make sure the namespace exists before adding documents
    * Check that the namespace type matches your use case
    * Verify you have access to the namespace
  </Accordion>

  <Accordion title="Document Upload Errors">
    * Check document format and content
    * Ensure all required fields are present
    * Verify document IDs are unique
  </Accordion>
</AccordionGroup>

### Debug Mode

Enable debug logging to troubleshoot issues:

```python theme={null}
import logging
logging.basicConfig(level=logging.DEBUG)
```

## Further Resources

For more information about Moorcheh, explore these resources:

<CardGroup cols={2}>
  <Card title="GitHub Repository" icon="github" href="https://github.com/moorcheh-ai/moorcheh-python-sdk">
    Source code and detailed documentation
  </Card>

  <Card title="Examples Repository" icon="code" href="https://github.com/moorcheh-ai/moorcheh-examples">
    Practical examples and tutorials
  </Card>

  <Card title="Official Website" icon="globe" href="https://www.moorcheh.ai/">
    Learn more about Moorcheh's capabilities
  </Card>

  <Card title="Documentation" icon="book" href="https://console.moorcheh.ai/docs">
    Complete API documentation
  </Card>

  <Card title="YouTube Channel" icon="youtube" href="https://www.youtube.com/@moorchehai">
    Video tutorials and demos
  </Card>

  <Card title="Follow on X" icon="x-twitter" href="https://x.com/moorcheh_ai">
    Stay updated with latest news
  </Card>
</CardGroup>

## Support

Need help with the LangChain integration?

<Card title="Get Support" icon="question-mark-circle" href="mailto:support@moorcheh.ai">
  Contact our support team for assistance
</Card>