Implement semantic cache persistence to disk

[aviralgarg05]

Description

The current semantic cache implementation stores cached queries only in memory. Implement persistence to disk so cached embeddings and results survive application restarts.

Proposed Solution

• Save cache entries to a JSON or pickle file periodically
• Load cached entries on SemanticCache initialization
• Add configurable cache file path via environment variable
• Implement cache expiration/TTL mechanism

Acceptance Criteria

• Cache persists across application restarts
• Configurable cache file location
• Automatic loading of existing cache on startup
• Optional TTL-based cache expiration
• Unit tests for persistence functionality

Technical Notes

• Similar pattern to Q-table persistence in rl_agent.py
• Consider using joblib for efficient numpy array serialization
• Add cache size limits to prevent unbounded growth

[coderabbitai]

📝 CodeRabbit Plan Mode

Generate an implementation plan and prompts that you can use with your favorite coding agent.

• Create Plan

Examples

• Example 1
• Example 2

---

🔗 Similar Issues

Related Issues

• Add RL agent training metrics dashboard #53

👤 Suggested Assignees

• aviralgarg05

---

🧪 Issue enrichment is currently in open beta.

You can configure auto-planning by selecting labels in the issue_enrichment configuration.

To disable automatic issue enrichment, add the following to your .coderabbit.yaml:

issue_enrichment:
  auto_enrich:
    enabled: false

💬 Have feedback or questions? Drop into our discord or schedule a call!

[sshekhar563]

Can i work on this issue ?