feat: add Ollama support for local AI models#31
Open
poiley wants to merge 4 commits into
Open
Conversation
Contributor
Author
|
I recommended merging the following PRs, rebasing this branch, and moving documentation to |
poiley
force-pushed
the
feat/ollama-support
branch
3 times, most recently
from
September 2, 2025 21:51
202c853 to
d1775a4
Compare
- Add --model and --server CLI flags for Ollama configuration - Implement AdaptiveClient with fallback strategy (Ollama → Claude) - Add comprehensive Ollama connectivity validation and error handling - Support all popular Ollama models (llama3, qwen2, mistral, phi3, gemma) - Add robust error messages and troubleshooting guidance - Include cross-platform support (Windows, macOS, Linux) - Update all BAML functions to use AdaptiveClient - Add comprehensive documentation in OLLAMA_SUPPORT.md - Update README.md with Ollama usage examples Resolves #28 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
When using the --model flag with Ollama, skip API key prompts entirely and use OllamaOnlyClient for purely local analysis without cloud fallback. Changes: - Add OllamaOnlyClient to BAML configuration for local-only analysis - Modify ensure_api_keys() to skip prompts when use_ollama=True - Update RepoAnalyzer to accept ollama_only parameter - Add aiohttp dependency for Ollama connectivity - Use appropriate client (OllamaOnlyClient vs AdaptiveClient) based on mode 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add 54 tests covering all Ollama integration features - Test connection validation, environment setup, CLI flags - Test BAML client configuration and fallback behavior - Test API key handling and error scenarios - Include test runners and documentation - All tests pass with proper async mocking 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
poiley
force-pushed
the
feat/ollama-support
branch
from
September 3, 2025 01:45
9d6c65e to
acd0547
Compare
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.
Summary
--modeland--serverCLI flags for Ollama configurationFeatures
--modelflag for model selection,--serverflag for server configurationUsage Examples
Technical Implementation
Documentation
Benefits
🤖 Generated with Claude Code
Co-Authored-By: Claude noreply@anthropic.com