[Feature] Implement Streaming Responses for Reduced Perceived Latency

[knoxiboy]

Description
RAG pipelines are slow because they involve embedding generation, vector retrieval, and LLM generation. Waiting for the entire response to be generated before displaying it leads to poor UX.

Implementation

1. Update the LLM integration in bots/ (e.g., Langchain or OpenAI SDK) to use streaming mode.
2. Modify the FastAPI backend/ to return a StreamingResponse or Server-Sent Events (SSE).
3. Update the React frontend/ chat component to append incoming chunks to the chat bubble in real-time, creating a typewriter effect.
4. Ensure error handling gracefully manages interrupted streams.

Level: Advanced
Affected Files: backend/api.py, bots/assistant.py, frontend/components/Chat/

[knoxiboy]

/assign gssoc'26
@param20h Please assigne this issue to me.

[github-actions]

Hi @knoxiboy! 👋

Thanks for opening this issue! We are thrilled to have you contribute to PDF-Assistant-RAG for GSSoC 2026.

📌 Before you start:

• Make sure you have read our Contributing Guidelines.
• Wait for a project admin to assign this issue to you before working on it.
• Remember to branch off dev and not main.

Happy Coding! 🚀