-
Notifications
You must be signed in to change notification settings - Fork 894
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
fix(agents-api): init nlp pipeline text-search #1045
base: dev
Are you sure you want to change the base?
Conversation
CI Failure Feedback 🧐(Checks updated until commit 6a07a54)
✨ CI feedback usage guide:The CI feedback tool (
In addition to being automatically triggered, the tool can also be invoked manually by commenting on a PR:
where |
PR Reviewer Guide 🔍Here are some key observations to aid the review process:
|
PR Code Suggestions ✨Explore these optional code suggestions:
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
👍 Looks good to me! Reviewed everything up to cb86135 in 1 minute and 22 seconds
More details
- Looked at
543
lines of code in5
files - Skipped
0
files when reviewing. - Skipped posting
1
drafted comments based on config settings.
1. agents-api/agents_api/queries/docs/search_docs_by_text.py:64
- Draft comment:
Thetext_to_tsvector_query
function is commented out. If this is intentional, consider removing it. Otherwise, uncomment it to ensure the text query is processed correctly. - Reason this comment was not posted:
Confidence changes required:50%
Thetext_to_tsvector_query
function is commented out in thesearch_docs_by_text
function, which might be an oversight since the PR is about initializing the NLP pipeline for text search.
Workflow ID: wflow_TVBvQPCSjdXPF22A
You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
❌ Changes requested. Incremental review on 27ed1f4 in 35 seconds
More details
- Looked at
42
lines of code in1
files - Skipped
0
files when reviewing. - Skipped posting
0
drafted comments based on config settings.
Workflow ID: wflow_DnFTLZ3o4XbKJR8j
Want Ellipsis to fix these issues? Tag @ellipsis-dev
in a comment. You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet
mode, and more.
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
PR Type
Enhancement, Tests
Description
Enhanced NLP pipeline for text search with improved keyword extraction.
Refactored query-building logic for efficiency and clarity.
Added tests for embedding generation and text-to-query conversion.
Introduced utility for generating vectors with specific cosine similarity.
Changes walkthrough 📝
nlp.py
Enhanced NLP pipeline and query-building logic
agents-api/agents_api/common/nlp.py
search_docs_by_text.py
Preprocess raw text queries for search
agents-api/agents_api/queries/docs/search_docs_by_text.py
utils.py
Added vector generation utility for testing
agents-api/tests/utils.py
similarity.
fixtures.py
Added test embeddings with confidence levels
agents-api/tests/fixtures.py
test_docs_queries.py
Added tests for document search and text-to-query utility
agents-api/tests/test_docs_queries.py
Important
Enhances NLP pipeline for text search, refactors query logic, and adds tests for embedding and text-to-query conversion.
nlp.py
with better stopword filtering and optimized query-building logic.search_docs_by_text.py
.utils.py
for generating vectors with specific cosine similarity.test_docs_queries.py
for document search and text-to-query conversion.fixtures.py
for testing.nlp.py
for efficiency and clarity.nlp.py
.This description was created by for 27ed1f4. It will automatically update as commits are pushed.