Add langchain component for Vertex Standalone Ranking API #167
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
lkuligin
approved these changes
Apr 25, 2024
lkuligin
reviewed
Apr 25, 2024
libs/community/pyproject.toml
Outdated
| @@ -17,6 +17,8 @@ langchain-community = ">=0.0.28" | |||
| google-api-core = "^2.17.1" | |||
| google-api-python-client = "^2.122.0" | |||
| grpcio = "^1.62.0" | |||
| google-cloud-discoveryengine = "^0.11.11" | |||
There was a problem hiding this comment.
could it add it as a poetry group, please?
lkuligin
reviewed
Apr 25, 2024
| from google.api_core import exceptions as core_exceptions | ||
| from google.auth.credentials import Credentials | ||
| from google.cloud import discoveryengine_v1alpha | ||
| from langchain.retrievers.document_compressors.base import BaseDocumentCompressor |
There was a problem hiding this comment.
please, import it from langchain_core
lkuligin
reviewed
Apr 25, 2024
libs/community/pyproject.toml
Outdated
| @@ -17,6 +17,8 @@ langchain-community = ">=0.0.28" | |||
| google-api-core = "^2.17.1" | |||
| google-api-python-client = "^2.122.0" | |||
| grpcio = "^1.62.0" | |||
| google-cloud-discoveryengine = "^0.11.11" | |||
| langchain = "^0.1.16" | |||
There was a problem hiding this comment.
we shouldn't depend on langchain
lkuligin
reviewed
Apr 25, 2024
| @@ -103,4 +104,4 @@ markers = [ | |||
| "asyncio: mark tests as requiring asyncio", | |||
| "compile: mark placeholder test used to compile integration tests without running them", | |||
| ] | |||
| asyncio_mode = "auto" | |||
| asyncio_mode = "auto" | |||
lkuligin
reviewed
Apr 25, 2024
| from google.cloud import discoveryengine_v1alpha | ||
|
|
||
|
|
||
| class VertexRankSDKManager: |
There was a problem hiding this comment.
why do we need this as a public class?
lkuligin
reviewed
Apr 25, 2024
| else None | ||
| ) | ||
|
|
||
| def get_rank_service_client(self) -> discoveryengine_v1alpha.RankServiceClient: |
There was a problem hiding this comment.
can we make it a private function instead of a class, please?
lkuligin
reviewed
Apr 25, 2024
| title_field: Optional[str] = Field(default=None) | ||
| credentials: Optional[Credentials] = Field(default=None) | ||
| credentials_path: Optional[str] = Field(default=None) | ||
| sdk_manager: VertexRankSDKManager = Field(default=None) |
There was a problem hiding this comment.
I don't think we need an additional sdk_manager provided. can we just re-use project_id / location_id attributes from this class instead?
lkuligin
reviewed
Apr 25, 2024
| from langchain_google_community.rank._sdk_manager import VertexRankSDKManager | ||
|
|
||
|
|
||
| class VertexAIRank(BaseDocumentCompressor): |
There was a problem hiding this comment.
please, add to the __init__.py on the module's level for an easy import
lkuligin
approved these changes
Apr 25, 2024
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.
Vertex DIY RAG APIs helps to build complex RAG systems and provide more granular control, and are suited for custom use cases.
The ranking API takes in a list of documents and reranks those documents based on how relevant the documents are to a given query. Compared to embeddings that look purely at the semantic similarity of a document and a query, the ranking API can give you a more precise score for how well a document answers a given query.
Reference : https://cloud.google.com/generative-ai-app-builder/docs/ranking
We implement this similar to other ranking APIs that langchain already integrates with - like Cohere Ranker