run-llama/semtools
1
0
Fork 0
mirror of https://github.com/run-llama/semtools.git synced 2026-07-21 11:15:24 -04:00
Code Issues 4 Packages Projects Releases 10 Wiki Activity

[PR #25] [MERGED] remove beta document-level approach, persist purely line embeddings as a new beta approach #35

New Issue
Closed
opened 2026-02-16 04:15:17 -05:00 by yindo · 0 comments
yindo commented 2026-02-16 04:15:17 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/run-llama/semtools/pull/25
Author: @logan-markewich
Created: 9/14/2025
Status: ✅ Merged
Merged: 9/14/2025
Merged by: @logan-markewich

Base: main ← Head: logan/workspace_v2

📝 Commits (4)

📊 Changes

5 files changed (+360 additions, -304 deletions)

View changed files

📝 Cargo.lock (+1 -1)
📝 Cargo.toml (+1 -1)
📝 package.json (+1 -1)
📝 src/bin/search.rs (+81 -95)
📝 src/workspace/store.rs (+276 -206)

📄 Description

So, document-level filtering might be too big-brained.

Trying a beta.2 approach where instead we purely persist line embeddings

I also considered swapping lancedb with sqlite, but with line-level embeddings we will quickly blow past the scaling limits of sqlite

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/run-llama/semtools/pull/25 **Author:** [@logan-markewich](https://github.com/logan-markewich) **Created:** 9/14/2025 **Status:** ✅ Merged **Merged:** 9/14/2025 **Merged by:** [@logan-markewich](https://github.com/logan-markewich) **Base:** `main` ← **Head:** `logan/workspace_v2` --- ### 📝 Commits (4) - [`6479bfe`](https://github.com/run-llama/semtools/commit/6479bfe8d0830ae236ad7eb27c2937f5adeb3e0a) remove document-level approach, persist purely line embeddings - [`4e3a533`](https://github.com/run-llama/semtools/commit/4e3a533009ef4b39a0561703305539af03f7a6a0) linting - [`fce4973`](https://github.com/run-llama/semtools/commit/fce49730f41930293394c7a7f2c55820c797da56) linting - [`915adaf`](https://github.com/run-llama/semtools/commit/915adaff30b97ceffe18869c9eddf4988c124e4d) fix ### 📊 Changes **5 files changed** (+360 additions, -304 deletions) <details> <summary>View changed files</summary> 📝 `Cargo.lock` (+1 -1) 📝 `Cargo.toml` (+1 -1) 📝 `package.json` (+1 -1) 📝 `src/bin/search.rs` (+81 -95) 📝 `src/workspace/store.rs` (+276 -206) </details> ### 📄 Description So, document-level filtering might be too big-brained. Trying a beta.2 approach where instead we purely persist line embeddings I also considered swapping lancedb with sqlite, but with line-level embeddings we will quickly blow past the scaling limits of sqlite --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-02-16 04:15:17 -05:00
yindo closed this issue 2026-02-16 04:15:17 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
enhancement
pull-request
Mirrored from GitHub Pull Request
No Label pull-request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/semtools#35
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?