Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[PR #3129] [MERGED] Enable num_ctx to match defined chunk length in ollama embedder #4218

New Issue
Closed
opened 2026-02-22 18:35:23 -05:00 by yindo · 0 comments
yindo commented 2026-02-22 18:35:23 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/Mintplex-Labs/anything-llm/pull/3129
Author: @timothycarambat
Created: 2/5/2025
Status: ✅ Merged
Merged: 2/5/2025
Merged by: @timothycarambat

Base: master ← Head: 3122-ollama-embedder-num_ctx

📝 Commits (2)

  • ea4d8bb Enable num_ctx to match defined chunk length in ollama embedder
  • 80f917b remove console

📊 Changes

1 file changed (+27 additions, -12 deletions)

View changed files

📝 server/utils/EmbeddingEngines/ollama/index.js (+27 -12)

📄 Description

Pull Request Type

  • ✨ feat
  • 🐛 fix
  • ♻️ refactor
  • 💄 style
  • 🔨 chore
  • 📝 docs

Relevant Issues

resolves #3122

What is in this change?

  • Ollama embedder will not always use the user defined max embedding length so that chunks are always fully formed and processed. This can be reduced by the user specify a value under the max length to conserve resources.

Assumed defaults for keep_alive so the model can persist in memory for follow-on embeddings and requests.

Additional Information

  • Moved client to use Ollama SDK instead of fetch

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality
  • Docker build succeeds locally

🔄 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/Mintplex-Labs/anything-llm/pull/3129 **Author:** [@timothycarambat](https://github.com/timothycarambat) **Created:** 2/5/2025 **Status:** ✅ Merged **Merged:** 2/5/2025 **Merged by:** [@timothycarambat](https://github.com/timothycarambat) **Base:** `master` ← **Head:** `3122-ollama-embedder-num_ctx` --- ### 📝 Commits (2) - [`ea4d8bb`](https://github.com/Mintplex-Labs/anything-llm/commit/ea4d8bba4a6690189509943b9deb16f9f1bd921d) Enable `num_ctx` to match defined chunk length in ollama embedder - [`80f917b`](https://github.com/Mintplex-Labs/anything-llm/commit/80f917bcb7a8627faaba56150d704534ea01e8cb) remove console ### 📊 Changes **1 file changed** (+27 additions, -12 deletions) <details> <summary>View changed files</summary> 📝 `server/utils/EmbeddingEngines/ollama/index.js` (+27 -12) </details> ### 📄 Description ### Pull Request Type <!-- For change type, change [ ] to [x]. --> - [x] ✨ feat - [ ] 🐛 fix - [ ] ♻️ refactor - [ ] 💄 style - [ ] 🔨 chore - [ ] 📝 docs ### Relevant Issues <!-- Use "resolves #xxx" to auto resolve on merge. Otherwise, please use "connect #xxx" --> resolves #3122 ### What is in this change? - Ollama embedder will not always use the user defined `max embedding length` so that chunks are always fully formed and processed. This can be reduced by the user specify a value _under_ the max length to conserve resources. Assumed defaults for keep_alive so the model can persist in memory for follow-on embeddings and requests. <!-- Describe the changes in this PR that are impactful to the repo. --> ### Additional Information - Moved client to use `Ollama` SDK instead of `fetch` <!-- Add any other context about the Pull Request here that was not captured above. --> ### Developer Validations <!-- All of the applicable items should be checked. --> - [ ] I ran `yarn lint` from the root of the repo & committed changes - [ ] Relevant documentation has been updated - [ ] I have tested my code functionality - [ ] Docker build succeeds locally --- <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 2026-02-22 18:35:23 -05:00
yindo closed this issue 2026-02-22 18:35:23 -05:00
yindo changed title from [PR #3129] Enable `num_ctx` to match defined chunk length in ollama embedder to [PR #3129] [MERGED] Enable `num_ctx` to match defined chunk length in ollama embedder 2026-06-05 15:17:27 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
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: Mintplex-Labs/anything-llm#4218
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?