We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
top_n function returns Vec<(f64, String, T)> where T is converted to a serde_json::Value by the VectorStoreIndexDyn.
top_n
Vec<(f64, String, T)>
T
serde_json::Value
VectorStoreIndexDyn
This becomes a problem because there is no point where the embedding vectors are filtered out of the vector search response.
Then, the agent takes as input this dynamic context and passes all the vectors as part of the context to the provider.
This makes the context window huge = more expensive and way slower.
The text was updated successfully, but these errors were encountered:
No branches or pull requests
top_n
function returnsVec<(f64, String, T)>
whereT
is converted to aserde_json::Value
by theVectorStoreIndexDyn
.This becomes a problem because there is no point where the embedding vectors are filtered out of the vector search response.
Then, the agent takes as input this dynamic context and passes all the vectors as part of the context to the provider.
This makes the context window huge = more expensive and way slower.
The text was updated successfully, but these errors were encountered: