It's really hard to evaluate LLM applications The most direct way is to do so is to gather feedback from the end user Here's an in depth walkthrough of using LangSmith to do that. Feedback is associated with traces, so you can easily debug bad results https://
github.com/langchain-ai/l
angsmith-cookbook/tree/main/feedback-examples/streamlit
…
@hwchase17
-
Evaluating LLM Applications with LangSmith Feedback
By
–
-
LangSmith Real-World Examples: From LLM Prototype to Production
By
–
More generally we're going to putting together a lot of real world, end-to-end examples of using LangSmith to bring LLM applications from prototype to production Any particular examples you'd like to see?
-
Text-to-SQL Deep Dive: Steps and Implementation Guide
By
–
A great deep dive by @manuelsoria_ and @RLanceMartin on text-to-SQL and all the steps involved!
-
AI Companion Apps: Mimicking Humans Through Component Breakdown
By
–
This is where all the “ai companion” apps/projects are valuable: mimicking a person
— Harrison Chase (@hwchase17) 8 août 2023
Really like to see the breakdown of different components that Greg has https://t.co/m4hVzTOdbLThis is where all the “ai companion” apps/projects are valuable: mimicking a person Really like to see the breakdown of different components that Greg has
-
Metaphor Search Integration Enables Web Exploring AI Agents
By
–
Congrats to @metaphorsystems on this launch! We've updated our integration page to show how you can use Metaphor to create an agent capable of exploring the web Docs: https://
python.langchain.com/docs/integrati
ons/tools/metaphor_search
… Example agent trace: https://
smith.langchain.com/public/dc0c264
4-9150-4fa0-8eea-dc653dafffeb/r
… -
Waitlist access rolling out at scale
By
–
are you on the waitlist? we're letting ~1000 off a day so hopefully shouldn't be that much longer
-
Expression Language Composability Over Callbacks in Components
By
–
because the expression language is more composable, callbacks may not be necessary as it may be easier just to run each component as its own for example, in the example above i took a stab at it and got: https://
gist.github.com/hwchase17/f93f
3043a5c9fe2b69e19e2674f80d19
… is this helpful? -
LangChain Streamlit apps speedup tool evaluation
By
–
Gonna check this out this afternoon Been spending a lot of time creating langchain x @streamlit apps – if this can speed that up would be great!
-
LCEL Examples and Documentation for LangChain Development
By
–
@waydegilliam added an example here – in general very happy to add/provide examples of LCEL https://
github.com/langchain-ai/l
angchain/pull/8830/files
… just ask! def takes a bit of work to grok but starts to get fun after a bit -
Self-Query: Splitting User Queries for Semantic Search
By
–
Self-Query The idea of splitting a user query into a semantic search term as well as a metadata filter One of the more clever retrieval methods in @langchain
, courtesy of @veryboldbagel Excited to talk about it in our webinar next week! https://
crowdcast.io/c/kqz7nl8nps42