[PR #231] [CLOSED] Feature: Add Document Retrieval with Metadata Filtering #253

New Issue

2026-02-16T05:17:07-05:00

yindo commented

2026-02-16 05:17:07 -05:00

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/langchain-postgres/pull/231
Author: @cedrickrusche
Created: 7/2/2025
Status: ❌ Closed

Base: main ← Head: feature/search_by_metadata

📝 Commits (5)

1b0c89d Implement get through filter
99d1440 Implement synchronous get with pydoc and test cases
a986493 Implement missing async implementation into sync vector store
b0ce110 Merge branch 'main' into feature/search_by_metadata
7e4ba91 Merge branch 'main' into feature/search_by_metadata

📊 Changes

4 files changed (+181 additions, -0 deletions)

View changed files

📝 langchain_postgres/v2/async_vectorstore.py (+120 -0)
📝 langchain_postgres/v2/vectorstores.py (+34 -0)
📝 tests/unit_tests/v2/test_async_pg_vectorstore_search.py (+13 -0)
📝 tests/unit_tests/v2/test_pg_vectorstore_search.py (+14 -0)

📄 Description

This pull request introduces the methods get and aget like in ChromaDB to retrieve data by metadata.

🔧 Changes

Asynchronous Document Retrieval: Implemented the aget method to asynchronously retrieve documents based on optional filters and parameters.
Synchronous Document Retrieval: Added the get method for synchronous document retrieval, leveraging the asynchronous aget method.
Metadata Filtering: Created the __query_collection_with_filter method to support filtering conditions in the SQL WHERE clause without similarity function
Test Cases: Added unit tests for both asynchronous and synchronous document retrieval methods to ensure functionality and reliability.

📈 Impact

These changes let us retrieve the current content to get insights about the data in the database e.g. to find outdated content.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/langchain-postgres/pull/231 **Author:** [@cedrickrusche](https://github.com/cedrickrusche) **Created:** 7/2/2025 **Status:** ❌ Closed **Base:** `main` ← **Head:** `feature/search_by_metadata` --- ### 📝 Commits (5) - [`1b0c89d`](https://github.com/langchain-ai/langchain-postgres/commit/1b0c89d2f9c9e16d4866176c031f769178f8ebdd) Implement get through filter - [`99d1440`](https://github.com/langchain-ai/langchain-postgres/commit/99d1440e6989b257361314c5e2e5a3db19d74d0c) Implement synchronous get with pydoc and test cases - [`a986493`](https://github.com/langchain-ai/langchain-postgres/commit/a9864930f3e873951c1157b47aadd37851b9ff80) Implement missing async implementation into sync vector store - [`b0ce110`](https://github.com/langchain-ai/langchain-postgres/commit/b0ce110252de1ab2765083f1b8f017701172b573) Merge branch 'main' into feature/search_by_metadata - [`7e4ba91`](https://github.com/langchain-ai/langchain-postgres/commit/7e4ba91c089e6b9b2cfd01c4d99c69d8b406bb7d) Merge branch 'main' into feature/search_by_metadata ### 📊 Changes **4 files changed** (+181 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `langchain_postgres/v2/async_vectorstore.py` (+120 -0) 📝 `langchain_postgres/v2/vectorstores.py` (+34 -0) 📝 `tests/unit_tests/v2/test_async_pg_vectorstore_search.py` (+13 -0) 📝 `tests/unit_tests/v2/test_pg_vectorstore_search.py` (+14 -0) </details> ### 📄 Description This pull request introduces the methods get and aget like in ChromaDB to retrieve data by metadata. ### 🔧 Changes - **Asynchronous Document Retrieval**: Implemented the `aget` method to asynchronously retrieve documents based on optional filters and parameters. - **Synchronous Document Retrieval**: Added the `get` method for synchronous document retrieval, leveraging the asynchronous `aget` method. - **Metadata Filtering**: Created the `__query_collection_with_filter` method to support filtering conditions in the SQL WHERE clause without similarity function - **Test Cases**: Added unit tests for both asynchronous and synchronous document retrieval methods to ensure functionality and reliability. ### 📈 Impact These changes let us retrieve the current content to get insights about the data in the database e.g. to find outdated content. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

yindo added the pull-request label 2026-02-16 05:17:07 -05:00

yindo closed this issue

2026-02-16 05:17:07 -05:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: langchain-ai/langchain-postgres#253