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 #4977] [MERGED] chore: bump ollama SDK from 0.5.10 to 0.6.3 #4848

New Issue
Closed
opened 2026-02-22 18:36:39 -05:00 by yindo · 0 comments
yindo commented 2026-02-22 18:36:39 -05:00
Owner
Copy Link
Copy Source

📋 Pull Request Information

Original PR: https://github.com/Mintplex-Labs/anything-llm/pull/4977
Author: @angelplusultra
Created: 2/9/2026
Status: ✅ Merged
Merged: 2/9/2026
Merged by: @timothycarambat

Base: master ← Head: bump-ollama-to-latest-feb2026

📝 Commits (1)

  • d3f8033 upgrade ollama in server to latest (0.6.3)

📊 Changes

2 files changed (+9 additions, -2 deletions)

View changed files

📝 server/package.json (+1 -1)
📝 server/yarn.lock (+8 -1)

📄 Description

Pull Request Type

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

Relevant Issues

resolves #4978

What is in this change?

Bumps the ollama npm package in /server from ^0.5.10 to ^0.6.3.

This SDK sits in the critical path for all Ollama LLM and embedding functionality. The upgrade was tested extensively to ensure no regressions across all SDK usage surfaces in the codebase.

Testing / Verification

All Ollama SDK integration points were audited and tested against the new version:

LLM Chat (client.chat())

  • Streaming chat completion
  • Non-streaming chat completion
  • Thinking — GLM-4.7-flash
  • Vision / image input — Qwen3-Vision
  • Tool use / function calling — Qwen3 (Web Search, Web Scraping, Agent Flows)
  • RAG (retrieval-augmented generation) — Qwen3
  • Thread attachments — GLM-4.7-flash

Embeddings (client.embed())

  • Ollama as embedding engine — verified res.embeddings response shape

Model Discovery (client.list() + client.show())

  • Context window caching on boot — verified models are listed, capabilities and model_info[*.context_length] fields are intact, and correct context windows are cached

Agent Provider (server/utils/agents/aibitat/providers/ollama.js)

  • Agent streaming path — separate client instantiation and stream iteration verified

Configuration

  • Keep-alive (keep_alive parameter passthrough)
  • Custom fetch timeout (OLLAMA_RESPONSE_TIMEOUT with undici.Agent dispatcher)

Additional Information

The Ollama SDK is used in 3 files:

  • server/utils/AiProviders/ollama/index.js — main LLM provider (chat, context window caching)
  • server/utils/agents/aibitat/providers/ollama.js — agent provider (tool calls, agent streaming)
  • server/utils/EmbeddingEngines/ollama/index.js — embedding engine

No code changes were required — this is a drop-in version bump. The SDK methods used (.chat(), .embed(), .list(), .show()) all retain the same call signatures and response shapes in 0.6.3.

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/4977 **Author:** [@angelplusultra](https://github.com/angelplusultra) **Created:** 2/9/2026 **Status:** ✅ Merged **Merged:** 2/9/2026 **Merged by:** [@timothycarambat](https://github.com/timothycarambat) **Base:** `master` ← **Head:** `bump-ollama-to-latest-feb2026` --- ### 📝 Commits (1) - [`d3f8033`](https://github.com/Mintplex-Labs/anything-llm/commit/d3f8033aacef51d0c61ff7368dbc29f6e0c67f2f) upgrade ollama in server to latest (0.6.3) ### 📊 Changes **2 files changed** (+9 additions, -2 deletions) <details> <summary>View changed files</summary> 📝 `server/package.json` (+1 -1) 📝 `server/yarn.lock` (+8 -1) </details> ### 📄 Description ### Pull Request Type <!-- For change type, change [ ] to [x]. --> - [ ] ✨ feat - [ ] 🐛 fix - [ ] ♻️ refactor - [ ] 💄 style - [x] 🔨 chore - [ ] 📝 docs ### Relevant Issues <!-- Use "resolves #xxx" to auto resolve on merge. Otherwise, please use "connect #xxx" --> resolves #4978 ### What is in this change? Bumps the `ollama` npm package in `/server` from `^0.5.10` to `^0.6.3`. This SDK sits in the critical path for all Ollama LLM and embedding functionality. The upgrade was tested extensively to ensure no regressions across all SDK usage surfaces in the codebase. ### Testing / Verification All Ollama SDK integration points were audited and tested against the new version: **LLM Chat (`client.chat()`)** - [x] Streaming chat completion - [x] Non-streaming chat completion - [x] Thinking — GLM-4.7-flash - [x] Vision / image input — Qwen3-Vision - [x] Tool use / function calling — Qwen3 (Web Search, Web Scraping, Agent Flows) - [x] RAG (retrieval-augmented generation) — Qwen3 - [x] Thread attachments — GLM-4.7-flash **Embeddings (`client.embed()`)** - [x] Ollama as embedding engine — verified `res.embeddings` response shape **Model Discovery (`client.list()` + `client.show()`)** - [x] Context window caching on boot — verified models are listed, `capabilities` and `model_info[*.context_length]` fields are intact, and correct context windows are cached **Agent Provider (`server/utils/agents/aibitat/providers/ollama.js`)** - [x] Agent streaming path — separate client instantiation and stream iteration verified **Configuration** - [x] Keep-alive (`keep_alive` parameter passthrough) - [x] Custom fetch timeout (`OLLAMA_RESPONSE_TIMEOUT` with `undici.Agent` dispatcher) ### Additional Information The Ollama SDK is used in 3 files: - `server/utils/AiProviders/ollama/index.js` — main LLM provider (chat, context window caching) - `server/utils/agents/aibitat/providers/ollama.js` — agent provider (tool calls, agent streaming) - `server/utils/EmbeddingEngines/ollama/index.js` — embedding engine No code changes were required — this is a drop-in version bump. The SDK methods used (`.chat()`, `.embed()`, `.list()`, `.show()`) all retain the same call signatures and response shapes in 0.6.3. ### Developer Validations <!-- All of the applicable items should be checked. --> - [ ] I ran `yarn lint` from the root of the repo & committed changes - [x] Relevant documentation has been updated - [x] 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 18:36:39 -05:00
yindo closed this issue 2026-02-22 18:36:39 -05:00
yindo changed title from [PR #4977] chore: bump ollama SDK from 0.5.10 to 0.6.3 to [PR #4977] [MERGED] chore: bump ollama SDK from 0.5.10 to 0.6.3 2026-06-05 15:20:41 -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#4848
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?