Add Ollama local Model support - #197
Open
WaterS-MoYu wants to merge 13 commits into
Open
Conversation
modify Translator.cs, TranslatorFactory.cs; Add LlamaTranslator.cs,LlamaContainer.cs
Add text box UI to use user defined ollama model
readme pic upload
WaterS-MoYu
changed the title
Chaobs
pushed a commit
to Chaobs/Translumo-LLM
that referenced
this pull request
Jul 23, 2026
Add Ollama as a built-in LLM provider so users can run translations against a local Ollama instance without configuring a Custom provider. Unlike the upstream PR ramjke/Translumo#197 (which used the legacy /api/generate endpoint with a hardcoded prompt), this reuses the existing LlmTranslator pipeline (professional system prompt, retry, parsing, encryption) over Ollama's OpenAI-compatible /v1/chat/completions endpoint. - LlmProvider: add Ollama = 10. - LlmProviderPresets: Ollama preset (http://localhost:11434/v1/chat/completions, llama3, OpenAI style). - LlmModelCatalog: 10 common Ollama models (llama3/3.1/3.2, qwen2.5, mistral, gemma2, phi3, deepseek-r1, ...). - LlmConfiguration: add RequiresApiKey (Ollama does not need a key). - LlmTranslator: skip the API key check and the Authorization header for providers that do not require a key. - Tests: https-assertion Ollama http exception, ApiStyle/FirstModel theory additions, RequiresApiKey tests. Also reorder the LLM provider dropdown so Custom is always last and Ollama sits just above it (LanguagesSettingsViewModel.ProviderDisplayOrder). The enum values are intentionally left unchanged to keep saved configs deserializable. Verified: 0 error/0 warning, 58 tests pass.
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
1 participant
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.
Add Ollama local model name support, users must install ollama on their PC and add folder path (which contains ollama.exe) to PATH, then run "ollama run " to install any model. Input in translumo languages setting--OllamaModel and choose translator to "LocalOllama"