Dev #5
Merged
Dev #5
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ain-ai#553) Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Update splash screen to take into account information about whether the playground is enabled/disabled
Swap out to use only langchain_core
…i#549) Add `Setup` instruction to run `langserve` app locally.
…led (langchain-ai#566) This change cleans up the schema surfaced via openapi docs to not include callback event schema if the server does not respond with it.
After this PR most of the scaffolding code is in place to support scoped feedback. After this PR the remaining work to be done: 1. Expose configuration in APIHandler / add_routes 2. Determine how to support with the existing feedback endpoint (or change to a new endpoint) 3. Surface in RemoteRunnable
…langchain-ai#570) * Create an endpoint to accept token based feedback * Update the format of returned feedback (since it's scoped by key)
…n-ai#571) This PR exposes the ability to configure feedback tokens for the APIHandler and add_routes
This PR allows to turn on a configuration that makes the server accept
client provided run ids.
The server needs to be started with
`add_routes(..., config_keys=['run_id'])`
And a client will then be able to make a request with `config={"run_id":
uuid4}`
…bled config (langchain-ai#573) Add test to verify that token_feedback endpoint gets registered correctly
…angchain-ai#577) After this PR a better error message will be surfaced to add_routes if a user passes something that's not a runnable. This currently occurs a lot when using the langchain cli as the lanchain cli creates an empty app with a palceholder value of NotImplemented for the runnable.
* This PR removes dependency on httpx sse * After this PR invalid requests will be returned as having a status code of 422 using a non streaming request
- Fixes langsmith client not being enabled if token feedback was specified - Add unit test for token feedback endpoint - Fix schema for token feedback to accept a str in addition to a UUID - Add metadata even to astream log with token feedback information
rc2 release to test API for feedback token integration
- remove pulumi links which are 404 - fix stream_events mention - run markdown formatter
Code was checking if feedback was enabled rather than token feedback.
See release notes
Migrate to new locations of imports
Prepare for 0.2.x release for core
Forgot to relock
`ChatAnthropic()` raises ValidationError. Also set model for ChatOpenAI where it appears alongside anthropic. Best to be explicit about model, otherwise new defaults will cause unexpected changes. Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Use correct attribute
Just a quickfix for langchain-ai#212. It would be better not to have to install fastapi only for using the client, but in my opinion this is still better then getting errors when importing the `RemoteRunnable` after a `pip install "langserve[client]"`. Otherwise at least the readme should be updated. --------- Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Release merge
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.