-
Notifications
You must be signed in to change notification settings - Fork 282
[N-2] 09-VectorStore / 10-Weaviate #389
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
Conversation
- Introduced a new Jupyter notebook for integrating Weaviate with LangChain, covering setup, connection, and usage. - Added multiple images to illustrate the Weaviate Cloud Services setup process. - Included sections on environment setup, querying, and using Weaviate with LangChain for enhanced question answering and retrieval-augmented generation.
…ing features - Updated execution counts for code cells to reflect the latest changes. - Modified the index creation process to include new properties: 'chapter', 'index', and 'total_docs'. - Changed the index name from 'Langchain_test_index7' to 'Langchain_test_index8'. - Improved the output formatting for search results, including region-specific queries and limiting results with the 'k' parameter. - Added new examples demonstrating the retrieval of monuments by region, enhancing the notebook's educational value.
…content - Added a "Credentials" section for setting up Weaviate Cloud Services. - Introduced new subsections on initialization, including listing, creating, and deleting indexes, as well as selecting embeddings and data preprocessing. - Updated the "Manage vector store" section with detailed steps for adding and deleting items. - Enhanced the "Finding Objects by Similarity" section with additional steps for data preparation and result quantification. - Improved overall structure and clarity of the notebook to facilitate better understanding and usage of Weaviate with LangChain.
… and output refinements - Adjusted execution counts for code cells to maintain consistency. - Updated output messages for index creation and document uploads to reflect accurate status. - Enhanced output formatting for search results, ensuring clarity in data retrieval. - Improved overall structure and readability of the notebook for better user experience.
… output adjustments - Set execution counts to null for specific code cells to reset state. - Cleared output messages for index creation and deletion to enhance clarity. - Updated index name from 'Langchain_test_index8' to 'Langchain_test_index' for consistency. - Improved output formatting for search results, ensuring accurate representation of data. - Enhanced overall readability and structure of the notebook for better user experience.
…features - Introduced functions for creating and deleting collections in Weaviate, improving data organization. - Updated the notebook structure to include detailed markdown explanations for each new feature. - Enhanced the collection creation process with customizable properties and vectorizer configurations. - Improved output messages for collection operations to provide clearer feedback on actions taken. - Adjusted execution counts for code cells to maintain consistency and reflect the latest changes.
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.
[Review Checklist]
-
Review OS: Linux
- Windows / Mac / Linux (해당 OS를 기재해주세요)
-
Template Rule 준수 여부:
- Template Rule 가이드를 준수하였는가? (Check 표기)
-
Table of Contents 링크 확인:
- Table of Contents의 링크가 원활하게 동작하는지 확인하였는가? (Check 표기)
-
이미지 파일명 검토:
- 이미지가 포함되어 있다면, 이미지의 파일명이 가이드를 준수하였는가? (Check 표기)
-
최신 import 방식 사용 여부:
- import 구문이 예전 legacy 방식이 아닌 최신 버전을 따르는가? (Check 표기)
-
코드 동작 확인:
- 모든 코드가 오류 없이 동작하는가? (Check 표기)
- Warning 발생 시 코멘트에 적어주세요.
-
제출 파일 확인:
- 꼭 필요한 파일들만 제출되었는가?
- 튜토리얼 외 설정 파일이나 다른 분이 작업한 파일이 포함되었는지 Files Changed에서 확인 부탁드립니다. (Check 표기)
- 꼭 필요한 파일들만 제출되었는가?
-
기타 의견:
- 처음 사용해보는데, 이미지를 활용하여 잘 작성해주셔서 큰 문제 없이 따라할 수 있었습니다. 👍
- 직접 실행해보는 경우에는 문제가 없었는데, 에러 결과가 현재 파일에 포함되어 있습니다. 확인 부탁드립니다.
- 이미지 파일 확인 부탁드립니다.
09-VectorStore/assets/09-Weaviate-Credentials-01.png
>09-VectorStore/assets/10-weaviate-credentials-01.png
09-VectorStore/assets/09-Weaviate-Credentials-02.png
>09-VectorStore/assets/10-weaviate-credentials-02.png
09-VectorStore/assets/09-Weaviate-Credentials-03.png
>09-VectorStore/assets/10-weaviate-credentials-03.png
09-VectorStore/assets/09-Weaviate-Credentials-04-1.png
>09-VectorStore/assets/10-weaviate-credentials-04-01.png
- 추가로
04-01
도 다른 파일들과 함께04
로 통일하는 것은 어떨지 제안드립니다.
- 그 외에 확인 수정 요청사항은 별도 comment 남겼습니다.
- 중간에 에러가 발생하여서 이후 리뷰는 진행하지 못하였는데, 수정 후에 리뷰를 재 요청해주시면 추가 검토하도록 하겠습니다. 감사합니다.
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.
에러 발생으로 인해 Finding Objects by Similarity 부분부터는 확인을 못했습니다. 수정해주시면 추가로 리뷰 진행하도록 하겠습니다.
- Expanded the tutorial to include detailed explanations on setting up and managing Weaviate collections, including creation, deletion, and advanced configuration options. - Improved markdown content for better clarity and user guidance, covering essential operations like document indexing, querying, and batch processing. - Added new sections on data preprocessing and document ingestion methods, emphasizing best practices for efficient vector storage. - Updated code cells with consistent execution counts and refined output messages for improved feedback during operations. - Enhanced search functionalities with new methods for similarity, hybrid, and keyword searches, along with structured results presentation. - Overall improvements to the notebook's structure and readability to facilitate a better learning experience for users integrating Weaviate with LangChain.
…and search functionalities - Updated filter handling methods to improve readability and usability, replacing filter_dict with filter_query for consistency across search functions. - Enhanced the WeaviateSearch class with a new _format_filter method for better filter representation in output messages. - Improved search methods (similarity, MMR, hybrid, semantic, and keyword) to utilize the updated filter handling. - Adjusted execution counts and output messages for clarity and consistency throughout the notebook. - Added examples demonstrating the use of filters in search queries, enhancing the educational value of the notebook.
…ent and improved markdown content - Replaced index management sections with detailed explanations on creating, deleting, and listing collections in Weaviate. - Added new subsections for document preprocessing and a function for document preprocessing. - Improved markdown structure for better clarity and user guidance throughout the notebook. - Enhanced overall readability and organization to facilitate a better learning experience for users integrating Weaviate with LangChain.
… enhanced content - Renamed Weaviate Cloud Services (WCS) to Weaviate Cloud (WCD) for consistency. - Added new images for credential setup and updated existing image references. - Improved markdown content for clarity in setting up Weaviate Cloud. - Adjusted execution counts and cleared outputs for better state management. - Enhanced overall readability and organization to facilitate a better learning experience for users integrating Weaviate with LangChain.
…and new credential image - Renamed image files for consistency in naming conventions. - Added a new credential image to enhance the documentation. - Improved markdown content for clarity in the Weaviate setup process.
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.
[Review Checklist]
-
Review OS: Linux
- Windows / Mac / Linux (해당 OS를 기재해주세요)
-
Template Rule 준수 여부:
- Template Rule 가이드를 준수하였는가? (Check 표기)
-
Table of Contents 링크 확인:
- Table of Contents의 링크가 원활하게 동작하는지 확인하였는가? (Check 표기)
-
이미지 파일명 검토:
- 이미지가 포함되어 있다면, 이미지의 파일명이 가이드를 준수하였는가? (Check 표기)
-
최신 import 방식 사용 여부:
- import 구문이 예전 legacy 방식이 아닌 최신 버전을 따르는가? (Check 표기)
-
코드 동작 확인:
- 모든 코드가 오류 없이 동작하는가? (Check 표기)
- Warning 발생 시 코멘트에 적어주세요.
-
제출 파일 확인:
- 꼭 필요한 파일들만 제출되었는가?
- 튜토리얼 외 설정 파일이나 다른 분이 작업한 파일이 포함되었는지 Files Changed에서 확인 부탁드립니다. (Check 표기)
- 꼭 필요한 파일들만 제출되었는가?
-
기타 의견:
- 빠르게 피드백 적용해주셔서 감사합니다. LGTM 💯
이미지 파일이 모두 잘 나옵니다. |
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.
[Review Checklist]
-
Review OS: Max
-
Template Rule 준수 여부
-
Table of Contents 링크 확인
-
이미지 파일명 검토
-
최신 import 방식 사용 여부
-
코드 동작 확인
-
제출 파일 확인
-
코드 동작 확인
-
기타 의견: 수정된 사항 확인하였습니다. 빠르게 작업해주셔서 감사드리고, 고생 많으셨습니다!
b28a302
into
LangChain-OpenTutorial:main
{PR Message - Write freely, remove this bracket if unnecessary}
Author Checklist
PR Title Format: I have confirmed that the PR title follows the correct format. (e.g., [N-2] 07-Text Splitter / 07-RecursiveCharacterTextSplitter)
Committed Files: I have ensured that no unnecessary files (e.g., .bin, .gitignore, poetry.lock, pyproject.toml) are included. These files are not allowed.
(Optional) Related Issue: If this PR is linked to an issue, I have referenced the issue number in the PR message. (e.g., Fixes Update 01-PromptTemplate.ipynb #123)
❌ Do not include unnecessary files (e.g., .bin, .gitignore, poetry.lock, pyproject.toml) or other people's code. If included, close the PR and create a new PR.
Review Template (Intial PR)
If no one reviews your PR within a few days, please @-mention one of teddylee777, musangk, BAEM1N