Add llmman integration page - #592
Open
ericcurtin wants to merge 1 commit into
Open
ericcurtin wants to merge 1 commit into
ericcurtin wants to merge 1 commit into
Conversation
|
@ericcurtin is attempting to deploy a commit to the deepset Team on Vercel. A member of the Team first needs to authorize it. |
llmman (https://github.com/llmmanorg/llmman) is a local model runner that serves the Ollama API, alongside OpenAI- and Anthropic-compatible ones, on port 17434. The existing ollama-haystack components work against it unchanged once pointed at http://localhost:17434, so the page mirrors integrations/ollama.md rather than adding a new package.
Contributor
There was a problem hiding this comment.
馃煛 Changes recommended
The installation section introduces curl | sh / irm | iex patterns that should be adjusted to safer, inspectable install steps before publishing.
Get a fresh assessment by requesting another Copilot review.
Pull request overview
- Purpose: Add a new integration documentation page for
llmman(local model runner exposing the Ollama API plus OpenAI-/Anthropic-compatible endpoints) to the Haystack integrations docs.
Changes:
- Add
integrations/llmman.mddocumenting how to useollama-haystackcomponents againsthttp://localhost:17434. - Include examples for chat generation, tool calling, embedding, and using the OpenAI-compatible
/v1endpoints.
File summaries
| File | Description |
|---|---|
integrations/llmman.md |
New integration page documenting llmman usage with existing Haystack components (Ollama + OpenAI-compatible). |
Review details
Suppressed comments (2)
integrations/llmman.md:43
- The Windows install command pipes a remote script directly into PowerShell ("irm | iex"), which can be risky and prevents easy inspection of the script contents. Prefer downloading the script first and then executing it.
irm https://raw.githubusercontent.com/llmmanorg/llmman/main/install.ps1 | iex
integrations/llmman.md:169
- Consider adding a dedicated
### Licensesection after the final code sample (and link it from the Table of Contents) so readers can quickly see the usage terms for llmman; upstreamllmmanis Apache-2.0.
### Using the OpenAI-compatible API
llmman also exposes `/v1/chat/completions`, `/v1/completions`, `/v1/models` and `/v1/responses`, so you can use [`OpenAIChatGenerator`](https://docs.haystack.deepset.ai/docs/openaichatgenerator) instead of `OllamaChatGenerator` if you prefer to depend only on `haystack-ai`:
- Files reviewed: 1/1 changed files
- Comments generated: 2
- Review effort level: Lite
馃挕 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
Comment on lines
+20
to
+24
| - [Usage](#usage) | ||
| - [Chat Generation](#chat-generation) | ||
| - [Tool Calling](#tool-calling) | ||
| - [Embedders](#embedders) | ||
| - [Using the OpenAI-compatible API](#using-the-openai-compatible-api) |
Comment on lines
+39
to
+40
| # Linux / macOS | ||
| curl -fsSL https://raw.githubusercontent.com/llmmanorg/llmman/main/install.sh | sh |
Contributor
There was a problem hiding this comment.
馃煛 Changes recommended
The installation URLs are invalid, and the setup commands prevent the model pull from executing.
Get a fresh assessment by requesting another Copilot review.
Review details
- Files reviewed: 1/1 changed files
- Comments generated: 3
- Review effort level: Balanced
Comment on lines
+40
to
+43
| curl -fsSL https://raw.githubusercontent.com/llmmanorg/llmman/main/install.sh | sh | ||
|
|
||
| # Windows (PowerShell) | ||
| irm https://raw.githubusercontent.com/llmmanorg/llmman/main/install.ps1 | iex |
Comment on lines
+49
to
+50
| llmman serve | ||
| llmman pull gemma4 |
| - [Chat Generation](#chat-generation) | ||
| - [Tool Calling](#tool-calling) | ||
| - [Embedders](#embedders) | ||
| - [Using the OpenAI-compatible API](#using-the-openai-compatible-api) |
kacperlukawski
requested changes
Sep 17, 2026
kacperlukawski
left a comment
kacperlukawski
left a comment
Member
There was a problem hiding this comment.
Thank you, @ericcurtin Happy to merge once all the Copilot's comments are addressed
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
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.
Adds llmman, a local model runner that serves the Ollama API (alongside OpenAI- and Anthropic-compatible ones) on port 17434.
integrations/llmman.mdonly, modelled onintegrations/ollama.md. No code changes:OllamaChatGenerator,OllamaTextEmbedderandOllamaDocumentEmbedderfromollama-haystackwork unchanged withurl="http://localhost:17434", so the page documents that rather than introducing a new package.pypiis omitted since llmman is not a PyPI package (reposatisfies the "at least one of" rule). Nologorather than reusing another provider's.OpenAIChatGeneratoragainsthttp://localhost:17434/v1for users who prefer to depend only onhaystack-ai.Testing: frontmatter parsed as YAML with required keys present; all 4 Python blocks
ast.parsed; in a fresh venv withollama-haystack6.8.0 confirmed the constructor kwargs used exist and the Ollama components construct without error. Not run against a live llmman server.