codemap-semantic-index

Embedding-based semantic recall plugin for codemap.

Registers an embedding ranker into codemap recall via the codemap.recall_hooks entry-point group (introduced in codemap-core 0.4.1). codemap-aimemory automatically RRF-fuses the embedding ranking with its token ranking and applies freshness decay (P4-2).

Install

pipx inject codemap codemap-semantic-index
# pulls sentence-transformers + torch (~200MB)

# Pick + download a local model (1.2GB default)
codemap embed install                   # interactive picker
codemap embed install BAAI/bge-m3       # direct

# First embed (writes <project>/.ai-memory/_semantic/)
codemap embed

# Now `codemap recall` does double-path (token + embedding) + RRF + freshness
codemap recall '<query>' --with-content

Default model

Qwen/Qwen3-Embedding-0.6B (1024 dim, 32k context, 1.2GB). Same-source training as the Qwen cloud text-embedding-v3, so switching to cloud preserves recall "feel".

Cloud backend (any OpenAI-compatible embedding API)

codemap embed backend set    # interactive picker (qwen / openai / zhipu / voyage / custom)
codemap embed backend show
codemap embed backend reset  # back to local

Four preset providers + custom for self-hosted vLLM / Ollama / TEI. Config persists to ~/.config/codemap/embedding.yaml (chmod 600).

Storage

<project_root>/.ai-memory/_semantic/
├── chunks.json    chunked text + metadata (model-independent)
├── vectors.npy    (n_chunks, 1024) float32 (model-specific)
├── model_id.txt   active backend fingerprint
└── manifest.json  text_hash → chunk_id (drives incremental)

Switching models requires codemap embed --rebuild (different vector spaces are not comparable).

Design doc

Obsidian/Notes/07-Ideas/AI-Enterprise-Delivery-System/2026-06-27-p1-3-codemap-semantic-index-设计方案.md — full spec including chunker / RRF / freshness integration.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

codemap_semantic_index-0.2.3.tar.gz (35.5 kB view details)

Uploaded Aug 17, 2026 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

codemap_semantic_index-0.2.3-py3-none-any.whl (30.5 kB view details)

Uploaded Aug 17, 2026 Python 3

File details

Details for the file codemap_semantic_index-0.2.3.tar.gz.

File metadata

Download URL: codemap_semantic_index-0.2.3.tar.gz
Upload date: Aug 17, 2026
Size: 35.5 kB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for codemap_semantic_index-0.2.3.tar.gz
Algorithm	Hash digest
SHA256	`fd20a4e6a14127b5852e60186937af04b0f233807a44c6507d3a417a2eb47e7d`
MD5	`2471c7b024e0b2aa186dc3021fbdbaca`
BLAKE2b-256	`d458e83a4d108b5c2842438a0b4a55c7edc4cf7ac1b1cb297df8bb09c2885fef`

See more details on using hashes here.

Provenance

The following attestation bundles were made for codemap_semantic_index-0.2.3.tar.gz:

Publisher: publish.yml on qxbyte/codemap

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Statement:
- Statement type: https://in-toto.io/Statement/v1
- Predicate type: https://docs.pypi.org/attestations/publish/v1
- Subject name: codemap_semantic_index-0.2.3.tar.gz
- Subject digest: fd20a4e6a14127b5852e60186937af04b0f233807a44c6507d3a417a2eb47e7d
- Sigstore transparency entry: 2496880221
- Sigstore integration time: Aug 17, 2026
Source repository:
- Permalink: qxbyte/codemap@13709c99dfe26f42eb7185d8b7de695e2df81c37
- Branch / Tag: refs/tags/v0.4.10
- Owner: https://github.com/qxbyte
- Access: public
Publication detail:
- Token Issuer: https://token.actions.githubusercontent.com
- Runner Environment: github-hosted
- Publication workflow: publish.yml@13709c99dfe26f42eb7185d8b7de695e2df81c37
- Trigger Event: push