hinthornw
Follow
Pinned
2,880 contributions in the last year
Contribution activity
September 2023
Created 2 repositories
- hinthornw/langchain-tutorials Jupyter Notebook
- hinthornw/lilac Python
Created a pull request in langchain-ai/chat-langchain that received 5 comments
Rm Trace LInk
When the write queue goes in, the run IDs will no longer be immediately available. Hide the link function until we bypass this.
+57
−70
•
5
comments
Opened 76 other pull requests in 7 repositories
langchain-ai/langsmith-sdk
23
merged
- Update
- Update client rod
- 0.0.39
- lint
- Support ref dataset ID assignment
- Make Metadata/tags Inheritable
- 0.0.37
- Int Test
- Write Queue Compatible
- Wraps
- Add option to return source run id
- 0.0.35
- 0.0.34
- Add config
- Wfh/reorder
- reorder
- mailto
- Add issue templates
- Add support for hiding inputs/outputs via env var
- Add other env info
- 0.0.33
- 0.0.32
- Add fields
langchain-ai/langchain
14
merged
1
closed
4
open
- Criteria Parser Improvements
- poc
- Merge metadata + tags in config
- Update LangSmith Version
- Make eval output parsers more robust
- Catch Base Exception
- Update LangSmith Walkthrough
- Add support for showing IO to chain group
- add avg feedback
- Update lambda typing
- Support multiple errors
- Add json evaluators
- Add progress bar + runner fixes
- Reduce default num retries
- Add LCEL cookbook examples
- Allow config propagation, Add default lambda name, Improve ergonomics of config passed in
- Better ls info
- Fix url loader
- Update redirects meta tags
langchain-ai/langsmith-cookbook
17
merged
2
open
- Wfh/lilac finetune
- Add example downloading feedback an druns from test project
- Wfh/trubrics feedback update
- Query for retriever runs by feedback
- Share run trace
- Update img links
- Add collab link
- Add linkcheck
- Exporting runs and feedback guide
- Update some feedback calls
- Add collab link
- Add readmes
- Fix links
- Wfh/eda/lilac
- Custom Run Naming
- Split QA Example
- Add Runnable Example
- Hub Example
- Algorithmic Feedback Example
langchain-ai/langsmith-docs
11
merged
1
open
langchain-ai/chat-langchain
1
open
gkamradt/langchain-tutorials
1
merged
lilacai/lilac
1
merged
Reviewed 26 pull requests in 6 repositories
langchain-ai/langchain
10 pull requests
langchain-ai/langsmith-cookbook
5 pull requests
langchain-ai/langsmith-sdk
5 pull requests
langchain-ai/langchainjs
3 pull requests
langchain-ai/langsmith-docs
2 pull requests
conda-forge/langsmith-feedstock
1 pull request
Opened 66 issues in 1 repository
langchain-ai/langsmith-cookbook
14
open
52
closed
- How to better handle rate limits when evaluating using run_on_dataset
- String Matching Evaluator Examples
- Example showing how to evaluate a conversational bot
- Evaluating a Router Example
- Querying for retriever runs with bad/good user feedback
- Augmenting a Q&A Dataset
- how to read a nested run
- How to generate an eval report from the feedback
- How to test/assign feedback to multiple steps in a trace
- Add blog post /more opinionated findings for RAG evals
- FAQ for "my serialized object isn't supported"
- Add option to add custom criteria in new test run page
- Permit hub loading of prompt for criteria evaluator
- Update tracing faq TS example to recommend runcollector
- Using the feedback results from run_on_dataset flows
- Scope out playground -> eval flow
- Scope out OTel collector options
- re-contextualize context QA eval flow
- Augmenting an Extraction Dataset
- Few-shot preferences with criteria evaluator using prod data
- Agent Evals Examples
- Better few-shot example selection
- QA Doc Nits
- Testing CLI
- Evaluating a retriever example
- Some issues not shown.
29
contributions
in private repositories
Sep 5 – Sep 19