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

# 1.9 DSPy Question Answering Agent

> Simple Q&A agent powered by DSPy framework

Simple Q\&A agent powered by DSPy framework.

## Code

```python theme={null}
"""DSPy Agent Example — Bindu Integration
=======================================
WHAT EXISTED BEFORE:
    Only Agno, CrewAI, LangChain examples existed.
    No DSPy integration existed anywhere in the repo.

WHAT IS NEW:
    - First DSPy example in the Bindu ecosystem
    - Uses DSPy Signatures for structured, typed prompting
    - Supports multi-turn conversation history
    - Works with any OpenAI-compatible model
"""

import dspy
from bindu.penguin.bindufy import bindufy

# Configure DSPy with your preferred LLM
lm = dspy.LM("openai/gpt-4o-mini")
dspy.configure(lm=lm)

# Define a DSPy Signature (typed prompt template)
class QASignature(dspy.Signature):
    """Answer the user's question clearly and concisely."""

    question: str = dspy.InputField(desc="The user's question")
    answer: str = dspy.OutputField(desc="A clear and concise answer")

# Build the DSPy program
qa_program = dspy.Predict(QASignature)

config = {
    "author": "varshayadav1722@gmail.com",
    "name": "dspy_agent",
    "description": "A DSPy-powered question answering agent",
    "deployment": {
        "url": "http://localhost:3773",
        "expose": True,
        "cors_origins": ["http://localhost:5173"]
    },
    
}

def handler(messages: list[dict]) -> list[dict]:
    last_message = messages[-1]["content"]
    result = qa_program(question=last_message)
    return [{"role": "assistant", "content": result.answer}]

if __name__ == "__main__":
    bindufy(config, handler)
```

## How It Works

**Instructions**

* Defines agent through DSPy Signature class
* Provides clear and concise answers to questions
* Uses structured prompting for consistent responses
* Maintains helpful and informative tone

**Tools**

* `dspy.Signature`: Typed prompt template for Q\&A
* `dspy.Predict`: Program execution framework
* `dspy.LM`: Language model configuration

**Model**

* `gpt-4o-mini`: Cost-effective model for Q\&A
* Via OpenAI-compatible API integration
* Configurable through DSPy LM configuration

## Dependencies

```bash theme={null}
uv init
uv add bindu dspy-ai
```

## Environment Setup

Create `.env` file:

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

## Run

```bash theme={null}
uv run dspy-agent.py
```

**Examples:**

* "What are the main benefits of using DSPy for prompting?"
* "How do I create a DSPy signature for my function?"
* "What are the key components of DSPy?"

## Example API Calls

<AccordionGroup>
  <Accordion title="Message Send Request">
    ```json theme={null}
    {
      "jsonrpc": "2.0",
      "method": "message/send",
      "params": {
        "message": {
          "role": "user",
          "kind": "message",
          "messageId": "9f11c870-5616-49ad-b187-d93cbb100001",
          "contextId": "9f11c870-5616-49ad-b187-d93cbb100002",
          "taskId": "9f11c870-5616-49ad-b187-d93cbb100003",
          "parts": [
            {
              "kind": "text",
              "text": "What are the main benefits of using DSPy for prompting?"
            }
          ]
        },
        "configuration": {
          "acceptedOutputModes": ["application/json"]
        }
      },
      "id": "9f11c870-5616-49ad-b187-d93cbb100003"
    }
    ```
  </Accordion>

  <Accordion title="Task get Request">
    ```json theme={null}
    {
      "jsonrpc": "2.0",
      "method": "tasks/get",
      "params": {
        "taskId": "9f11c870-5616-49ad-b187-d93cbb100003"
      },
      "id": "9f11c870-5616-49ad-b187-d93cbb100004"
    }
    ```
  </Accordion>
</AccordionGroup>

## Frontend Setup

```bash theme={null}
# Clone the Bindu repository
git clone https://github.com/GetBindu/Bindu

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

# Start frontend development server
npm run dev
```

Open [http://localhost:5173](http://localhost:5173) and try to chat with the DSPy agent