> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Agentic RAG with PgVector

> Agentic RAG with PgVector, storing and searching embeddings with hybrid search.

Implement Agentic RAG using PgVector (PostgreSQL with vector extensions) to store and search embeddings with hybrid search.

## Code

```python agentic_rag_pgvector.py theme={null}
"""
1. Run: `./cookbook/scripts/run_pgvector.sh` to start a postgres container with pgvector
2. Run: `pip install openai sqlalchemy psycopg pgvector pypdf agno` to install the dependencies
3. Run: `python agentic_rag_pgvector.py` to run the agent
"""

from agno.agent import Agent
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIResponses
from agno.vectordb.pgvector import PgVector, SearchType

db_url = "postgresql+psycopg://ai:ai@localhost:5532/ai"
knowledge = Knowledge(
    # Use PgVector as the vector database and store embeddings in the `ai.recipes` table
    vector_db=PgVector(
        table_name="recipes",
        db_url=db_url,
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)

knowledge.insert(
    url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
)

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    knowledge=knowledge,
    # Add a tool to search the knowledge base which enables agentic RAG.
    # This is enabled by default when `knowledge` is provided to the Agent.
    search_knowledge=True,
    markdown=True,
)
agent.print_response(
    "How do I make chicken and galangal in coconut milk soup", stream=True
)
# agent.print_response(
#     "Hi, i want to make a 3 course meal. Can you recommend some recipes. "
#     "I'd like to start with a soup, then im thinking a thai curry for the main course and finish with a dessert",
#     stream=True,
# )
```

## Usage

<Snippet file="create-venv-step.mdx" />

**1. Install dependencies**

```bash theme={null}
uv pip install -U agno openai sqlalchemy psycopg pgvector pypdf
```

<Snippet file="run-pgvector-step.mdx" />

**2. Export your OpenAI API key**

```bash theme={null}
export OPENAI_API_KEY=your_openai_api_key_here
```

**3. Run Agent**

```bash theme={null}
python agentic_rag_pgvector.py
```

## Next Steps

| Task | Guide |
| - | - |
| Retrieve before the first model call instead | [Traditional RAG with PgVector](https://agno-v2.mintlify.site/knowledge/agents/traditional-rag-pgvector.md) |
| Tune hybrid ranking | [Hybrid Search](https://agno-v2.mintlify.site/knowledge/concepts/search-and-retrieval/hybrid-search.md) |
| Apply metadata filters | [Filtering](https://agno-v2.mintlify.site/knowledge/concepts/filters/overview.md) |


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.