Repository navigation
Fix: Close the gaps Ollama and OpenAI clients hit - #134
Merged
Merged
Conversation
HEAD / now answers 200 for health checks; /api/version returns the real version (1.0.0, above every Ollama 0.x) instead of 0.0.0. Ollama names qwen3, qwen3:latest, qwen3:0.6b and qwen3:0.6b-fp16 map to Qwen3-0.6B, and an unknown name lists the names that exist. The Ollama chat, generate and embed routes fetch the catalogue model on first use, like the app and the OpenAI API, so 'ollama run qwen3' works on a fresh install. think: false (Ollama) and reasoning_effort none/minimal or chat_template_kwargs (OpenAI) reach the chat template as enable_thinking. The READMEs and the server guide show how to point the ollama CLI and OpenAI SDKs at Gemstone.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
#118 (SPEC S1.10, S1.15).
Defect fixed
HEAD /→ 200 (health checks);GET /still serves the web client./api/version(GET/HEAD) →1.0.0fromapi/src/main/version.py(a test keeps it equal topyproject.toml); was0.0.0.qwen3,qwen3:latest,qwen3:0.6b,qwen3:0.6b-fp16,default→Qwen/Qwen3-0.6B(case-insensitive); unknown names → 404 listing the available names and thatOrg/Modelids can be pulled (same text on Ollama and OpenAI)./api/chat,/api/generate,/api/embedfetch the catalogue model on first use.think: false(Ollama),reasoning_effort: none|minimalorchat_template_kwargs(OpenAI) →enable_thinkingin the chat template (Engine.__call__(chat_template_kwargs=), keeps batching).Test added:
api/tests/test_client_compat.py(35; red: 27 failed).Documentation corrected: README + README_ko, guide server page (en + ko):
OLLAMA_HOST=http://127.0.0.1:23100,OPENAI_BASE_URL=…/v1, the API key. SPEC S1.10, S1.15.Rebased onto #133 (import conflict in
ollama_api.pyresolved: bothUnsupportedModelandin_catalogue).Closes #118