# Chromadb

### Chromadb

This database can give you a quick headstart with the persist option. If you dont specify any arguments a default persistent storage will be used.

**Supported Arguments:**

```
host: Optional[str] = None
port: Optional[int] = None
persist_path: Optional[str] = None
search_method: Optional[SearchMethod] = SearchMethod.SIMILARITY_SEARCH
search_options: Optional[dict] = Field(default_factory=dict)
```

**Supported Search Methods:**

* similarity\_search
  * Search Options:
    * **k** : The top k elements for searching
* max\_marginal\_relevance\_search
  * Search Options
    * **k**: Number of Documents to return. Defaults to 4.
    * **fetch\_k**: Number of Documents to fetch to pass to MMR algorithm.
    * **lambda\_mult**: Number between 0 and 1 that determines the degree of diversity among the results with 0 corresponding to maximum diversity and 1 to minimum diversity. Defaults to 0.5.

### Usage

A Vectordb definitely needs a embedding function and you connect these two components through a stack.

```python
from langchain.docstore.document import Document as LangDocument

from genai_stack.vectordb.chromadb import ChromaDB
from genai_stack.vectordb.weaviate_db import Weaviate
from genai_stack.embedding.utils import get_default_embedding
from genai_stack.stack.stack import Stack


embedding = get_default_embedding()
# Will use default persistent settings for a quick start
chromadb = ChromaDB.from_kwargs()
chroma_stack = Stack(model=None, embedding=embedding, vectordb=chromadb)

# Add your documents
chroma_stack.vectordb.add_documents(
    documents=[
        LangDocument(
            page_content="Some page content explaining something", metadata={"some_metadata": "some_metadata"}
        )
    ]
)
        
# Search for content in your vectordb
chroma_stack.vectordb.search("page")
```

You can also use different search\_methods and search options when trying out more complicated usecases

```python
chromadb = ChromaDB.from_kwargs(
    search_method="max_marginal_relevance_search", 
    search_options={"k": 2, "fetch_k": 10, "lambda_mult": 0.3}
)
```


---

# Agent Instructions: 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:

```
GET https://genaistack.aiplanet.com/components/vector-database/chromadb.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.