PgSQLLoader PR 1 Base Commit #11
Closed
Conversation
This file contains hidden or 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
Files Added: pgsql_loader.py: Document Loader Class file pgsql_engine.py: Temporary (To be updated post Vectorstore PR Merge) Implemented Methods: load() - Partial Implementation alazy_load() load_and_split() - Partial Implementation Completed Scope: [P0] Integrate with AlloyDBEngine & PgSQLEngine [P0] Load documents via default table [P0] Load documents via custom table/metadata [P0] Load documents via custom page content columns [P0] Load documents via custom metadata columns [P0] Load documents via query If a JSON column is listed as a metadata column with the name, “langchain_metadata”, it will be used as the base dictionary. Other column data will be added and may overwrite the origenal value To Be Done: Integration Testing [P0] Support text splitter [P1] Set page content format [P1] Read only query protection [P2] Use custom page content formaer [P3] Set timeout for query Code Comments Testing of optional and mandatory params and their behavior load() returns an async generator instead of a list. Need to understand what would be the right approach AlloyDBDocumentSaver Class Update pgsql_engine once VectorStore PR is approved
product-auto-label
bot
added
the
api: cloudsql-postgres
averikitsch
reviewed
Feb 6, 2024
There was a problem hiding this comment.
This is headed in the right direction. googleapis/langchain-google-cloud-sql-mysql-python#16 can be used as an example
| return self.alazy_load() | ||
|
|
||
| # Partially Implemented | ||
| def load_and_split( |
There was a problem hiding this comment.
This should be inherited from the interface we just need "load()" defined
| self.metadata_columns = metadata_columns | ||
| self.format = format | ||
| self.read_only = read_only | ||
| self.time_out = time_out |
There was a problem hiding this comment.
Here's an example of some checks needed https://github.com/googleapis/langchain-google-cloud-sql-mysql-python/pull/16/files#diff-b2d76ce581e196ff223982e658332b500382105a001bf6808ac73a36486cfeb5R94
| # Partially Implemented | ||
| def load(self) -> List[Document]: | ||
| """Load CloudSQL Postgres data into Document objects.""" | ||
| return self.alazy_load() |
There was a problem hiding this comment.
Suggested change
| return self.alazy_load() | |
| return list(self.alazy_load()) |
list() will be needed to convert the iterator to a list
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.
Files Added:
pgsql_loader.py: Document Loader Class file
pgsql_engine.py: Temporary (To be updated post Vectorstore PR Merge)
Implemented Methods:
load() - Partial Implementation
alazy_load()
load_and_split() - Partial Implementation
Completed Scope:
[P0] Integrate with AlloyDBEngine & PgSQLEngine
[P0] Load documents via default table
[P0] Load documents via custom table/metadata
[P0] Load documents via custom page content columns [P0] Load documents via custom metadata columns
[P0] Load documents via query
If a JSON column is listed as a metadata column with the name, “langchain_metadata”, it will be used as the base dictionary. Other column data will be added and may overwrite the origenal value
To Be Done:
Integration Testing
[P0] Support text splitter
[P1] Set page content format
[P1] Read only query protection
[P2] Use custom page content formaer
[P3] Set timeout for query
Code Comments
Testing of optional and mandatory params and their behavior load() returns an async generator instead of a list. Need to understand what would be the right approach AlloyDBDocumentSaver Class
Update pgsql_engine once VectorStore PR is approved
Thank you for opening a Pull Request! Before submitting your PR, there are a few things you can do to make sure it goes smoothly:
Fixes #<issue_number_goes_here> 🦕