arm.com disclaimer, performix docs, and new parser for developer.arm.com#83
Open
JoeStech wants to merge 3 commits into
Open
arm.com disclaimer, performix docs, and new parser for developer.arm.com#83JoeStech wants to merge 3 commits into
JoeStech wants to merge 3 commits into
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds Arm.com-specific response disclaimers to the MCP knowledge-base search output, expands the embedding corpus to include Arm Performix documentation, and introduces a new ingestion/parser path for developer.arm.com/documentation/... by fetching and decoding the Arm Documentation Service JSON payloads.
Changes:
- Add an Arm.com-domain disclaimer field to KB search results returned by the MCP server.
- Add Arm Performix as a new vector DB source and corresponding retrieval evaluation questions.
- Implement a new
developer.arm.comdocumentation fetch/parse flow (service URL mapping + base64 HTML decode + chunking).
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| mcp-local/utils/kb_response.py | New helper to detect Arm domains and inject a standard disclaimer into search results. |
| mcp-local/server.py | Applies the disclaimer injection to knowledge_base_search() results. |
| embedding-generation/vector-db-sources.csv | Adds Arm Performix documentation as a new source URL. |
| embedding-generation/tests/test_generate_chunks.py | Removes the existing embedding-generation unit test suite. |
| embedding-generation/generate-chunks.py | Adds Arm documentation chunk generation via the Arm documentation-service JSON API. |
| embedding-generation/eval_questions.json | Adds new evaluation questions targeting Arm Performix pages. |
| embedding-generation/document_chunking.py | Adds Arm developer/service URL mapping + JSON/base64 parsing for Arm documentation API responses. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+409
to
+423
| data = json.loads(response_content.decode("utf-8", errors="ignore")) | ||
| topic = data.get("topic", data) | ||
| content = topic.get("content", "") | ||
| if not content: | ||
| return ParsedDocument( | ||
| source_url=source_url, | ||
| resolved_url=resolved_url, | ||
| display_title=fallback_title, | ||
| content_type="html", | ||
| sections=[], | ||
| ) | ||
|
|
||
| html = base64.b64decode(content).decode("utf-8", errors="ignore") | ||
| title = data.get("title") or fallback_title | ||
| return parse_html(html, source_url, resolved_url, title) |
Comment on lines
+939
to
+942
| root_data = json.loads(root_response.content.decode("utf-8", errors="ignore")) | ||
| keywords = _arm_metadata_keywords(root_data, keywords_value, source_name) | ||
| document_title = root_data.get("title") or source_name | ||
| topic_links = _arm_topic_links(root_data.get("topic", {})) |
Comment on lines
879
to
884
| def create_chunks_for_source(source_url, source_name, doc_type, keywords_value): | ||
| if doc_type == "Ecosystem Dashboard": | ||
| return create_ecosystem_dashboard_chunk(source_url, source_name, keywords_value) | ||
| if is_arm_developer_documentation_url(source_url): | ||
| return create_arm_documentation_chunks(source_url, source_name, doc_type, keywords_value) | ||
|
|
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.
No description provided.