Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

[LogosDB] Track and expose memory IDs in search results

Open
#10 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
48/100
Issue type
Feature
Clarity
Mostly clear
Activity status
Quiet
Tech stack
cpp
Domain
search

Research direction

Start with tools/cli/cli.cpp lines 1377-1411 and trace the search result handling, including logosdb_result_id() and logosdb_put(). Review the memory chunk path and build_llm_compressed_hint, then update the debug output and search results to carry IDs. Done means the acceptance criteria are met, including documenting ID usage in SPECS.md; LogosDB v0.2.0 is required first.

Written by the indexing model from the issue text.

Description

stale

Update search result handling to expose memory IDs returned by LogosDB v0.2.0.

Background

LogosDB v0.2.0 adds logosdb_result_id() to get row IDs from search results. Currently funes.cpp ignores these IDs.

Proposed Changes

  1. Store IDs when teaching

    • Keep track of (text_hash -> id) mapping
    • Or use sidecar metadata file for ID persistence
  2. Include ID in debug output

    • When LLAMA_SEMANTIC_MEMORY_DEBUG is set, show:
      [semantic-memory] search hit: id=42 score=0.95 text="..."
  3. Use IDs for memory provenance

    • Track which memories were used in a response
    • Enable feedback: "that memory was helpful / not helpful"

Implementation

  • Add id field to memory chunk structure
  • Update build_llm_compressed_hint to receive IDs
  • Update debug logging in search code path

Acceptance Criteria

  • Capture and store IDs from logosdb_put()
  • Expose IDs in LLAMA_SEMANTIC_MEMORY_DEBUG output
  • Include IDs in search results passed to compressor
  • Document ID usage in SPECS.md

Dependencies

  • Requires LogosDB v0.2.0 (issue #8)

Related Code

  • tools/cli/cli.cpp lines 1377-1411 (search result handling)
Dominant language
C++
Stars
1
Forks
0
PR merge metrics
No merged PRs in 30d

Getting set up

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from jose-compu/funes.cpp

All issues in jose-compu/funes.cpp

Similar issues

More C++ issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.