[Feature] Implement Conversation History Persistence and Context Window Management

[knoxiboy]

Description
To maintain a natural chat flow, the LLM needs to remember previous questions and answers. However, blindly appending the whole history to the prompt will quickly exceed the context window and increase API costs.

Implementation

1. Store chat sessions in a relational database (e.g., PostgreSQL).
2. Implement a context management strategy in bots/:
   • Keep the last N messages verbatim.
   • Use a background LLM call to summarize older parts of the conversation.
3. Pass the combination of summary + recent history + retrieved document chunks to the LLM.

Level: Advanced
Affected Files: backend/history.py, bots/memory.py, migrations/

[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! 🚀