[good first issue-platform adapt-Ellama] Add Memory adapter for Ellama (Emacs) - #1159
Open
LeonSGP43 wants to merge 1 commit into
Open
[good first issue-platform adapt-Ellama] Add Memory adapter for Ellama (Emacs)#1159LeonSGP43 wants to merge 1 commit into
LeonSGP43 wants to merge 1 commit into
Conversation
…m package) Docs-only adapter connecting s-kostyaev/ellama (Emacs LLM assistant) to the memory proxy through the llm package's built-in OpenAI-compatible provider: :url is the trailing-slash base (/codebuddy/<spaceId>/v1/), llm appends chat/completions; :key (inherited from llm-openai) sends the sk-mem-... business user key as Bearer. EN/CN README with setup, configuration reference, troubleshooting, and an auth-source alternative, following the gptel adapter format. Signed-off-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Collaborator
|
Thank you so much for your attention and contribution! We will arrange an internal review for this PR shortly, and all feedback will be shared right here in the discussion. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds a docs-only adapter for Ellama (s-kostyaev/ellama, the Emacs LLM assistant), connecting it to the TencentDB Agent Memory proxy through the llm package's built-in OpenAI-compatible provider — the same editor-adapter line as the gptel adapter.
adapters/ellama/README.md+README_CN.md(EN/CN, same structure as the gptel docs-only adapter)How it connects (verified against official sources)
ellama-select-modellists "OpenAI-compatible" as a built-in provider choice with URL editing.llmpackage docs (§3.2) definemake-llm-openai-compatiblewith:url— the base URL leading up to the command (chat/completions), e.g.https://api.openai.com/v1/with trailing slash — plus:chat-model/:embedding-model.:keyslot was verified in the llm-openai.el source:llm-openai-compatibleincludesllm-openai, so the key is accepted and sent asAuthorization: Bearer(key checking is a no-op for compatible providers since some don't require one — ours does).:urlathttp://127.0.0.1:8096/codebuddy/<spaceId>/v1/lands on the proxy's canonical route.Contents
sk-mem-...user key)ellama-provider→ align model withPROXY_UPSTREAM_MODEL→ verify viaM-x ellama-chatand the session pickerellama-select-modelroute,auth-sourcealternative for the key, data-flow statementPart of the platform-adapt batch tracked in #926.