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

# 📝 Text

# Integrating Text File Content into Your Chat Agent

Enhancing your chat agent with the inclusion of plain text (.txt) files broadens its knowledge base, enabling it to draw upon a diverse range of textual content. The `txt_chat` method facilitates the seamless integration of text files into your chat agent, making this wealth of information accessible for enhancing conversation quality and relevance.

## Function Overview

The `txt_chat` function is designed to ingest content from text files into your chat agent, employing a variety of parameters to ensure this process is both efficient and effective.

### Parameters

* **input\_dir** (`Optional[str]`): Directory path containing text files to be added. If specified, the function will search this directory for eligible files.
* **input\_files** (`Optional[List]`): A list of paths to specific text files to be added. When provided, `input_dir` is bypassed.
* **exclude\_hidden** (`bool`): If `True`, hidden files or those starting with a dot (.) within `input_dir` are excluded.
* **filename\_as\_id** (`bool`): If `True`, the filename is used as the unique identifier for each text document.
* **recursive** (`bool`): If `True`, the function will also search subdirectories within `input_dir` for text files.
* **required\_exts** (`Optional[List[str]]`): Specifies the file extensions to include. Defaults to text file extensions.
* **system\_prompt** (`str`): An optional prompt to guide the system in processing text file content.
* **query\_wrapper\_prompt** (`str`): An optional prompt that can improve the relevance of search queries by providing context related to the text content.
* **embed\_model** (`Union[str, EmbedType]`): The embedding model used for extracting and embedding text from the files. Defaults to a general-purpose model.
* **llm\_params** (`dict`): Configuration parameters for integrating Large Language Models to enhance content comprehension and query processing.
* **vector\_store\_params** (`dict`): Configuration for vector storage, specifying how and where extracted content embeddings are stored.
* **service\_context\_params** (`dict`): Additional parameters to customize the service context for the text file content.
* **chat\_engine\_params** (`dict`): Customization parameters for the chat engine, influencing how the chat agent utilizes text file content in conversations.
* **retriever\_params** (`dict`): Configuration for the document retriever component, determining how text file content is indexed and retrieved in response to user queries.

## Example Usage

### Adding Text Files from a Directory

```python theme={null}
chat_agent.txt_chat(
    input_dir="/path/to/text/files",
    recursive=True
)
```

This snippet configures the chat agent to ingest text files from the specified directory and its subdirectories.

### Adding Specific Text Files

```python theme={null}
chat_agent.txt_chat(
    input_files=["/path/to/file1.txt", "/path/to/file2.txt"],
)
```

Here, specific text files are directly added to the chat agent, allowing it to leverage their content in conversations.