-
Notifications
You must be signed in to change notification settings - Fork 29
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
Ll/vectara #783
Ll/vectara #783
Conversation
a67f4cd
to
ce3812f
Compare
corpus_key: str | ||
description: str = "Search documents related to {{ corpus_key }}" | ||
vectara_url: str = "https://api.vectara.io/" | ||
body_overrides: dict = Field({}, description="Arguments to use when creating / continuing a chat. See https://docs.vectara.com/docs/rest-api/create-chat for more information.") |
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.
Agent Configuration lives here. Override allow the creation / turn interface to be arbitrarily customized since we don't know how people will want to use This. contract is the same for both endpoints,
|
||
corpus_key: str = Field(description="The corpus key to search in.") | ||
description: str = Field("Search documents related to {corpus_key}.", description="Description of the tool presented to LLM. Will be formatted with corpus_key.") | ||
vectara_url: str = "https://api.vectara.io/" |
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.
Vectara tool for agentic rag. Allows agents to 1. query arbitrary search terms and 2. read full documents as desired (doc id is retrieved from searches)
Add vectara support in Eidolon.
Will add docs in follow-up pr if we like the contract