-
Notifications
You must be signed in to change notification settings - Fork 282
[E-2] 16-Evaluations / 07-LangSmith-Custom-LLM-Evaluation #359
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
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.
🖥️ OS: Linux
✅ Checklist
- Template: Tutorials follows the required template.
- Table of Contents(TOC) Links: All Table of Contents links work. (Yes/No)
- Image: Image filenames follow guidelines.
- Imports: All import statements use the latest versions. Ensure "langchain-teddynote" is not used.
- Code Execution: Code runs without errors.
- Comments: {Write freely, 한국어 기술 가능}
- 전반적으로 깔끔하게 작성해주셔서 좋았습니다. 감사합니다.
- add `pymupdf`, `faiss-cpu` - update clean text format
- Change package installation method
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.
🖥️ OS: Win
✅ Checklist
- Template: Tutorials follows the required template.
- Table of Contents(TOC) Links: All Table of Contents links work. (Yes/No)
- Image: Image filenames follow guidelines.
- Imports: All import statements use the latest versions. Ensure "langchain-teddynote" is not used.
- Code Execution: Code runs without errors.
- Comments: 문서 작성해주시느라 너무 고생 많으셨습니다. 백틱 수정내용 말고 문제없이 모두 동작합니다!
"\n", | ||
"## Overview\n", | ||
"\n", | ||
"`LangSmith Custom LLM Evaluation` is a customizable evaluation framework in LangChain that enables users to assess LLM application outputs based on their specific requirements.\n", |
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.
backtick은 변수, 함수, 모듈명에 사용하는 것으로 알고 있습니다! 볼드체로 변경해주심이 어떨까 싶습니다!
"\n", | ||
"We'll build a basic **RAG** (Retrieval-Augmented Generation) system to test Custom Evaluators. This implementation creates a question-answering system based on PDF documents, which will serve as our foundation for evaluation purposes.\n", | ||
"\n", | ||
"This **RAG** system will be used to evaluate answer quality and accuracy through `Custom Evaluators` in later sections.\n", |
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.
이 부분 backtick도 함께 수정되면 좋을 것 같습니다! 'Custom Evaluators' > 볼드체
"\n", | ||
"**Random Score Evaluator Implementation**\n", | ||
"- Takes `Run` and `Example` objects as input parameters\n", | ||
"- Returns a dictionary in the format: `{\"key\": \"score_name\", \"score\": score}`\n", |
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.
{\"key\": \"score_name\", \"score\": score}
> 이부분도 수정해주시면 좋을 것 같습니다! (볼드체)
- update style to standardize markdown formatting
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.
🖥️ OS: Win/Mac/Linux
✅ Checklist
- Template: Tutorials follows the required template.
- Table of Contents(TOC) Links: All Table of Contents links work. (Yes/No)
- Image: Image filenames follow guidelines.
- Imports: All import statements use the latest versions. Ensure "langchain-teddynote" is not used.
- Code Execution: Code runs without errors.
- Comments: {Write freely, 한국어 기술 가능}
"from langchain_core.runnables import RunnablePassthrough, Runnable\n", | ||
"\n", | ||
"\n", | ||
"class PDFRAG:\n", |
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.
최신 main 브랜치에 myrag.py가 추가되었습니다.
개인적으로 LLM 평가 주제에 PDFRAG
를 설명하는 부분이 너무 많게 느껴져서 새로 추가된 모듈로 대체하는 것이 좋을 것 같습니다.
어떻게 생각하시나요?
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.
해당 부분에 대해서 myrag.py 로 대체하겠습니다.
감사합니다.
" - `split_documents()`: Splits documents into appropriate sizes using RecursiveCharacterTextSplitter\n", | ||
"\n", | ||
"2. **Vector Store Creation**\n", | ||
" - `create_vectorstore()`: Creates vector DB using OpenAI Embeddings and FAISS\n", |
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.
" - `create_vectorstore()`: Creates vector DB using OpenAI Embeddings and FAISS\n", | |
" - `create_vectorstore()`: Creates vector DB using `OpenAIEmbeddings` and `FAISS`\n", |
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.
@kofsitho87 OpenAIEmbeddings
로 빈칸 없이 수정해주세요.
@rlatjcj 님 리뷰내용 감사드립니다. 요청하신 내용 반영하여 다시 커밋하였습니다. |
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.
확인했습니다! 이상 없는 것 같습니다. 고생 많으셨습니다🤗
" - `split_documents()`: Splits documents into appropriate sizes using RecursiveCharacterTextSplitter\n", | ||
"\n", | ||
"2. **Vector Store Creation**\n", | ||
" - `create_vectorstore()`: Creates vector DB using OpenAI Embeddings and FAISS\n", |
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.
@kofsitho87 OpenAIEmbeddings
로 빈칸 없이 수정해주세요.
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.
🖥️ OS: Win/Mac/Linux
✅ Checklist
- Template: Tutorials follows the required template.
- Table of Contents(TOC) Links: All Table of Contents links work. (Yes/No)
- Image: Image filenames follow guidelines.
- Imports: All import statements use the latest versions. Ensure "langchain-teddynote" is not used.
- Code Execution: Code runs without errors.
- Comments: {Write freely, 한국어 기술 가능}
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.
수정 반영 감사합니다! 고생많으셨습니다!
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.
🖥️ OS: Linux
✅ Checklist
- Template: Tutorials follows the required template.
- Table of Contents(TOC) Links: All Table of Contents links work. (Yes/No)
- Image: Image filenames follow guidelines.
- Imports: All import statements use the latest versions. Ensure "langchain-teddynote" is not used.
- Code Execution: Code runs without errors.
- Comments: {Write freely, 한국어 기술 가능}
- 고생많으셨습니다!
dba139d
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