> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# autogen.retrieve_utils.create_vector_db_from_dir

<code class="doc-symbol doc-symbol-heading doc-symbol-function" />

#### create\_vector\_db\_from\_dir

```python theme={null}
create_vector_db_from_dir(
    dir_path: str | list[str],
    max_tokens: int = 4000,
    client: API = None,
    db_path: str = 'tmp/chromadb.db',
    collection_name: str = 'all-my-documents',
    get_or_create: bool = False,
    chunk_mode: str = 'multi_lines',
    must_break_at_empty_line: bool = True,
    embedding_model: str = 'all-MiniLM-L6-v2',
    embedding_function: Callable = None,
    custom_text_split_function: Callable = None,
    custom_text_types: list[str] = ['txt', 'json', 'csv', 'tsv', 'md', 'html', 'htm', 'rtf', 'rst', 'jsonl', 'log', 'xml', 'yaml', 'yml', 'pdf', 'mdx'],
    recursive: bool = True,
    extra_docs: bool = False
) -> API
```

Create a vector db from all the files in a given directory, the directory can also be a single file or a url to
a single file. We support chromadb compatible APIs to create the vector db, this function is not required if
you prepared your own vector db.<br />

<b>Parameters:</b>

| Name                         | Description                                                                                                                                                                                                                                                                                                                                                            |
| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `dir_path`                   | the path to the directory, file, url or a list of them.<br /><br />**Type:** str \| list\[str]                                                                                                                                                                                                                                                                         |
| `max_tokens`                 | the maximum number of tokens per chunk.<br /><br />Default is 4000.<br /><br />**Type:** int<br /><br />**Default:** 4000                                                                                                                                                                                                                                              |
| `client`                     | the chromadb client.<br /><br />Default is None.<br /><br />**Type:** API<br /><br />**Default:** None                                                                                                                                                                                                                                                                 |
| `db_path`                    | the path to the chromadb.<br /><br />Default is "tmp/chromadb.db".<br /><br />The default was `/tmp/chromadb.db` for version `=0.2.24`.<br /><br />**Type:** str<br /><br />**Default:** 'tmp/chromadb.db'                                                                                                                                                             |
| `collection_name`            | the name of the collection.<br /><br />Default is "all-my-documents".<br /><br />**Type:** str<br /><br />**Default:** 'all-my-documents'                                                                                                                                                                                                                              |
| `get_or_create`              | Whether to get or create the collection.<br /><br />Default is False.<br /><br />If True, the collection will be returned if it already exists.<br /><br />Will raise ValueError if the collection already exists and get\_or\_create is False.<br /><br />**Type:** bool<br /><br />**Default:** False                                                                |
| `chunk_mode`                 | the chunk mode.<br /><br />Default is "multi\_lines".<br /><br />**Type:** str<br /><br />**Default:** 'multi\_lines'                                                                                                                                                                                                                                                  |
| `must_break_at_empty_line`   | Whether to break at empty line.<br /><br />Default is True.<br /><br />**Type:** bool<br /><br />**Default:** True                                                                                                                                                                                                                                                     |
| `embedding_model`            | the embedding model to use.<br /><br />Default is "all-MiniLM-L6-v2".<br /><br />Will be ignored if embedding\_function is not None.<br /><br />**Type:** str<br /><br />**Default:** 'all-MiniLM-L6-v2'                                                                                                                                                               |
| `embedding_function`         | the embedding function to use.<br /><br />Default is None, SentenceTransformer with the given `embedding_model` will be used.<br /><br />If you want to use OpenAI, Cohere, HuggingFace or other embedding functions, you can pass it here, follow the examples in `https://docs.trychroma.com/embeddings`.<br /><br />**Type:** Callable<br /><br />**Default:** None |
| `custom_text_split_function` | a custom function to split a string into a list of strings.<br /><br />Default is None, will use the default function in `autogen.retrieve_utils.split_text_to_chunks`.<br /><br />**Type:** Callable<br /><br />**Default:** None                                                                                                                                     |
| `custom_text_types`          | a list of file types to be processed.<br /><br />Default is TEXT\_FORMATS.<br /><br />**Type:** list\[str]<br /><br />**Default:** \['txt', 'json', 'csv', 'tsv', 'md', 'html', 'htm', 'rtf', 'rst', 'jsonl', 'log', 'xml', 'yaml', 'yml', 'pdf', 'mdx']                                                                                                               |
| `recursive`                  | whether to search documents recursively in the dir\_path.<br /><br />Default is True.<br /><br />**Type:** bool<br /><br />**Default:** True                                                                                                                                                                                                                           |
| `extra_docs`                 | whether to add more documents in the collection.<br /><br />Default is False<br /><br />**Type:** bool<br /><br />**Default:** False                                                                                                                                                                                                                                   |

<b>Returns:</b>

| Type | Description          |
| ---- | -------------------- |
| API  | The chromadb client. |

<br />