> For the complete documentation index, see [llms.txt](https://genaistack.aiplanet.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://genaistack.aiplanet.com/components/embedding/langchain.md).

# Langchain

## General Configuration Structure

The Embedding configuration is of two main parameters in `source` "name" and "fields".

#### Source Configuration

```json
config = {
    "name": "source_component_name",
    "fields": {
        "parameter_name": "parameter_value",
        ...
    }
}
```

In this section:

* `"name"`: Specifies the name of the embedding component to be used.
* `"fields"`: Contains key-value pairs representing the specific parameters required by the embedding component.

### Usage

```python
from genai_stack.embedding.langchain import LangchainEmbedding
from genai_stack.embedding.utils import get_default_embeddings
```

### Using Python Dictionary Configuration

You can represent your configuration as a Python dictionary and pass it directly to the `LangchainEmbedding.from_kwargs()` method. This provides a more programmatic and dynamic way of configuring your ETL process.

#### Example Python Dictionary Configuration

Below is an example of how you can define your ETL configuration as a Python dictionary:

```
python
```

```python
config = {
    "name": "HuggingFaceEmbeddings",
    "fields": {
        "model_name": "sentence-transformers/all-mpnet-base-v2",
        "model_kwargs": {"device": "cpu"},
        "encode_kwargs": {"normalize_embeddings": False},
    }
}
```

#### Using Python Dictionary Configuration

Once you have defined your configuration as a Python dictionary, you can use it with the `LangchainEmbedding.from_kwargs()` method:

```python
embeddings = LangchainETL.from_kwargs(**config)
embdding.embed_text("Text to embed")
```

### Loading Configuration from JSON File

If you have your configuration defined in a JSON file, you can use the `Langchain.from_config()` method to load it. Here's how:

```python
json_file_path = "path/to/your/config.json"
embeddings = LangchainETL.from_kwargs(**config)
embdding.embed_text("Text to embed")
```

### Benefits of Using Python Dictionary Configuration

* **Dynamic Configuration**: Python dictionaries allow you to dynamically generate configurations based on variables and logic.
* **Integration with Code**: You can easily integrate the configuration within your code, making it easier to manage and maintain.

***

And now, here's the example JSON configuration you provided integrated into the documentation:

```json
{
    "name": "HuggingFaceEmbeddings",
    "fields": {
        "model_name": "sentence-transformers/all-mpnet-base-v2",
        "model_kwargs": {"device": "cpu"},
        "encode_kwargs": {"normalize_embeddings": False},
    }
}
```

Please note that the actual details and parameters within the JSON configuration might vary based on the specific components and vector database being used. Adjust the documentation accordingly to match the functionalities and attributes of those components.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://genaistack.aiplanet.com/components/embedding/langchain.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.