Conversation
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
added new repo info tool with test
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Feature UI
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Feature/graphdb
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…ocs, deleted useless code and added a few tests
Contributor
There was a problem hiding this comment.
Pull request overview
This PR modernizes the project into a chat-first “agent + RAG retrieval” architecture, adds containerization + CI workflows, introduces YAML-based model config, and expands documentation/testing around retrieval, repo info, and UI.
Changes:
- Added CI workflows (HF Space deploy, MkDocs deploy, PR Docker build) plus root Dockerfile/.dockerignore.
- Refactored retrieval/agent tooling (new embedder/reranker modules, pipeline singleton registry, query utils, DeepWiki/repocards repo summary).
- Added extensive MkDocs documentation and several new tests/scripts around tools and retrieval behavior.
Reviewed changes
Copilot reviewed 92 out of 101 changed files in this pull request and generated 14 comments.
Show a summary per file
| File | Description |
|---|---|
| tests/test_repo_summary_async_contract.py | Adds async contract coverage for repo summary tool. |
| tests/test_repo_summary.py | Adds a repo summary “smoke test” script (currently under tests/). |
| tests/test_query_utils.py | Adds unit tests for new query utils helpers. |
| tests/test_pipeline_registry.py | Adds tests for pipeline singleton behavior by index_dir. |
| tests/test_gpt4o_vision.py | Adds a vision test script (currently executes at import). |
| tests/test_epfl_vision.py | Adds an EPFL vision capability test script (currently executes at import). |
| tests/README_test_deepwiki_repo_info.md | Documents DeepWiki repo-info test suite. |
| tests/README_RETRIEVAL_TESTS.md | Documents retrieval pipeline test suite and expectations. |
| src/ai_agent/utils/utils.py | Refactors runnable link picking and adds affirmative + file coercion helpers. |
| src/ai_agent/utils/temp_file_manager.py | Adds process-wide temp file registry + atexit cleanup. |
| src/ai_agent/utils/tags.py | Simplifies supported control tags (EXCLUDE/REFINE only). |
| src/ai_agent/utils/image_io.py | Formatting + safety guard improvements in image loading/unzipping. |
| src/ai_agent/utils/full_processing.py | Renames entrypoint and adds logging output for catalog processing. |
| src/ai_agent/utils/file_validator.py | Formatting + minor validation logic cleanup. |
| src/ai_agent/utils/config.py | Adds YAML-driven model configuration loader. |
| src/ai_agent/utils/image_analyzer.py | Removes legacy OpenAI VLM image analyzer module. |
| src/ai_agent/ui/visualizations.py | Adds Plotly tool-call charts/timeline and disabled-tool summary. |
| src/ai_agent/ui/utils.py | Adds UI helpers for reading model config (agent/default/available). |
| src/ai_agent/ui/state.py | Adds chat state/message models and markdown rendering helpers. |
| src/ai_agent/ui/formatters.py | Adds tool card markdown formatter. |
| src/ai_agent/ui/init.py | Adds UI public exports + lazy imports. |
| src/ai_agent/retriever/text_embedder.py | Adds BGE-M3 embedder wrapper interface. |
| src/ai_agent/retriever/reranker.py | Adds CrossEncoder reranker wrapper. |
| src/ai_agent/queries/get_relevant_software.rq | Adds SPARQL CONSTRUCT query template. |
| src/ai_agent/generator/schema.py | Extends generator schema (Conversation/choices normalization). |
| src/ai_agent/generator/prompts.py | Rewrites selector prompt and adds prompt factory functions. |
| src/ai_agent/generator/generator.py | Removes legacy VLMToolSelector implementation. |
| src/ai_agent/core/pipeline_registry.py | Adds shared pipeline singleton with index_dir-based recreation. |
| src/ai_agent/core/init.py | Exposes core shared services. |
| src/ai_agent/cli.py | Introduces chat/sync CLI + background catalog refresh loop. |
| src/ai_agent/agent/utils.py | Expands AgentState + adds GitHub URL coercion helpers. |
| src/ai_agent/agent/tools/utils.py | Adds lightweight catalog loader + shared pipeline access + clipping/github checks. |
| src/ai_agent/agent/tools/search_tool.py | Updates search tool to use new query utils + automatic reranking + image hints. |
| src/ai_agent/agent/tools/search_alternative_tool.py | Adds alternative query search tool. |
| src/ai_agent/agent/tools/rerank_tool.py | Removes legacy rerank tool (reranking now automatic). |
| src/ai_agent/agent/tools/repo_info_tool.py | Replaces repo_info with async deepwiki-first repo summary + repocards fallback. |
| src/ai_agent/agent/tools/query_utils.py | Adds format normalization/token appending + legacy marker stripping. |
| src/ai_agent/agent/tools/mcp/registry.py | Adds tool registry/config abstraction for MCP tools. |
| src/ai_agent/agent/tools/mcp/base.py | Adds base input/output models for tool standardization. |
| src/ai_agent/agent/tools/mcp/init.py | Exposes MCP registry/base models + registration trigger. |
| src/ai_agent/agent/tools/gradio_space_tool.py | Reworks demo runner, adds preview/origin materialization. |
| src/ai_agent/agent/tools/deepwiki_tool.py | Adds DeepWiki MCP integration for repo docs. |
| src/ai_agent/agent/tools/init.py | Exposes tool registration API and imports tool set for registration. |
| src/ai_agent/agent/models.py | Adds usage stats + richer tool-run logging for agent results. |
| scripts/process_fields.py | Removes legacy dataset field filtering script. |
| pyproject.toml | Pins dependencies and adds new runtime deps (plotly, repocards, yaml, RDF). |
| mkdocs.yml | Adds MkDocs Material site configuration and navigation. |
| docs/index.md | Adds docs landing page. |
| docs/getting-started/installation.md | Adds installation guide (includes Docker instructions). |
| docs/getting-started/configuration.md | Adds env/config.yaml setup guide. |
| docs/getting-started/quickstart.md | Adds quickstart walkthrough. |
| docs/user-guide/chat-interface.md | Adds chat UI usage guide and advanced tags. |
| docs/user-guide/file-formats.md | Adds supported formats and preview/metadata explanation. |
| docs/user-guide/recommendations.md | Explains ranking/scoring pipeline and interpretation. |
| docs/user-guide/running-demos.md | Documents demo execution workflow. |
| docs/reference/environment.md | Documents environment variables and model config. |
| docs/reference/cli.md | Documents CLI commands. |
| docs/reference/changelog.md | Adds docs-friendly changelog page. |
| docs/development/contributing.md | Adds contribution guide. |
| config.yaml | Adds default model configuration and UI model list. |
| LICENSE | Adds Apache-2.0 license file. |
| Dockerfile | Adds root Dockerfile for containerized deployment. |
| .dockerignore | Excludes git/env/tests from Docker build context. |
| .env.dist | Expands environment template with new variables and guidance. |
| .github/workflows/docker-build-pr.yml | Adds PR Docker build workflow. |
| .github/workflows/deploy_docs.yml | Adds GitHub Pages deploy via MkDocs workflow. |
| .github/workflows/deploy-develop-to-hf.yml | Adds Hugging Face Spaces deploy workflow. |
| .github/copilot-instructions.md | Updates internal architecture guidance and command names. |
You can also share your feedback on Copilot code review. Take the survey.
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Feature/speeding
caviri
approved these changes
Apr 29, 2026
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.
This pull request introduces major improvements to the project’s infrastructure, configuration, and documentation, as well as a significant expansion of features and architectural changes. Key highlights include new CI workflows for deployment and Docker builds, a revamped
.env.distfor environment configuration, a new Dockerfile for containerization, and a comprehensive update to the changelog detailing new chat-based features, tool registry systems, and UI enhancements.Infrastructure and CI/CD:
deploy-develop-to-hf.yml), building documentation with MkDocs (deploy_docs.yml), and building Docker images for pull requests (docker-build-pr.yml). [1] [2] [3]Dockerfilefor containerized deployment, including a non-root user, dependency installation, and startup command for the chat agent..dockerignoreto exclude unnecessary files from Docker builds, improving build efficiency and security.Configuration and Environment:
.env.distwith documentation and fields for API keys, model configuration, GraphDB, output paths, and support for a newconfig.yamlsystem. [1] [2]Documentation and Project Structure:
CHANGELOG.mdwith detailed descriptions of new features, architectural changes, and bug fixes, including the new chat interface, tool registry, UI redesign, and improved retrieval pipeline. [1] [2]copilot-instructions.mdto reflect new retriever modules and improved retrieval pipeline structure.Summary of the most important changes:
Infrastructure & Deployment:
Dockerfileand.dockerignorefor containerization and efficient Docker builds. [1] [2]Configuration:
.env.distwith new fields for API keys, model configuration, GraphDB, and support forconfig.yaml, improving environment setup and flexibility. [1] [2]Features & Architecture:
Bug Fixes & Maintenance:
CHANGELOG.md.These changes collectively modernize the project’s deployment, configuration, and documentation, while introducing a robust new feature set and architectural improvements.