# Quickstart

For quickstart, you can rely on the default embedding option. By default we use "**HuggingFaceEmbedding**" This eliminates the need to configure embeddings, making the process effortless.

To utilize the vectordb configuration with the default embedding:

\=> **Vectordb usage with Retriever**

```python
from genai_stack.vectordb.chroma import ChromaDB
from genai_stack.retriever.langchain import LangChainRetriever
vectordb =  ChromaDB.from_kwargs(class_name = "genai-stack")
retriever = LangChainRetriever.from_kwargs(vectordb = vectordb)
retriever.retrieve("<My question>")

# Output 
# <Source documents nearest to you question>
```

**=> Vectordb usage with ETL**

```python
from genai_stack.vectordb.chroma import ChromaDB
from genai_stack.etl.lang_loader import LangLoaderEtl
from genai_stack.etl.utils import get_config_from_source_kwargs

vectordb =  ChromaDB.from_kwargs(class_name = "genai-stack")
etl = LangLoaderEtl.from_kwargs(vectordb = vectordb, get_config_from_source_kwargs("pdf", "/path/to/pdf"))
etl.run()
```

**Important Note:** A vector db is never used alone its used along with either ETL or Retrieval which gives a good usecase to use the vectordb.


---

# 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/v0.1.0/components/vector-database/quickstart.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.