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

# Installation

> Install the Basalt Python SDK for v1.

<Warning>
  **The TypeScript SDK is not yet available for v1.** If you're using TypeScript/JavaScript, please continue to follow the v0 docs: [v0/installation](/v0/installation).
</Warning>

## Installation (Python)

```bash theme={null}
pip install basalt-sdk
```

## Requirements

* Python 3.10 or later
* Basalt API key ([get one here](https://app.getbasalt.ai))

## Optional Dependencies

The SDK includes optional extras for auto-instrumentation of specific LLM providers, vector databases, and frameworks. You only need to install these if you plan to use auto-instrumentation.

### LLM Providers

```bash theme={null}
# Individual providers
pip install basalt-sdk[openai]
pip install basalt-sdk[anthropic]
pip install basalt-sdk[google_generativeai]
pip install basalt-sdk[bedrock]

# All LLM providers
pip install basalt-sdk[llm-all]
```

### Vector Databases

```bash theme={null}
# Individual providers
pip install basalt-sdk[chromadb]
pip install basalt-sdk[pinecone]
pip install basalt-sdk[qdrant]

# All vector DB providers
pip install basalt-sdk[vector-all]
```

### Frameworks

```bash theme={null}
# Individual frameworks
pip install basalt-sdk[langchain]
pip install basalt-sdk[llamaindex]
pip install basalt-sdk[haystack]

# All frameworks
pip install basalt-sdk[framework-all]
```

### Everything

```bash theme={null}
# Install all optional dependencies
pip install basalt-sdk[all]
```

**Note:** Optional dependencies are not required for basic usage (prompts, datasets, experiments APIs). See the [auto-instrumentation guide](/v1/observabilite/python/auto-instrumentation) for more details.

## Next Steps

* [Quickstart](./quickstart)
* [Prompts](/v1/prompts/python/overview)
* [Datasets](/v1/datasets/python/overview)
* [Observability](/v1/observabilite/python/get-started)