<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/xata-x-langchain-new-vector-store-and-memory-store-integrations-8avur25os" -->

---
title: Xata x LangChain: new vector store and memory store...
description: Xata and LangChain announce four new integrations: Xata as a vector store and as a memory store, available for both Python and TypeScript/JavaScript LangChain....
canonical: https://daily.dev/posts/xata-x-langchain-new-vector-store-and-memory-store-integrations-8avur25os
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Xata x LangChain: new vector store and memory store integrations | daily.dev
og:description: Xata and LangChain announce four new integrations: Xata as a vector store and as a memory store, available for both Python and TypeScript/JavaScript LangChain....
og:url: https://daily.dev/posts/xata-x-langchain-new-vector-store-and-memory-store-integrations-8avur25os
og:image: https://api.daily.dev/og/posts/8AVuR25oS.png
og:image:alt: Xata x LangChain: new vector store and memory store integrations
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Xata x LangChain: new vector store and memory store integrations

**[LangChain](https://daily.dev/sources/langchain)** · 7 min read · 0 upvotes · 0 comments

## Summary

Xata and LangChain announce four new integrations: Xata as a vector store and as a memory store, available for both Python and TypeScript/JavaScript LangChain. Xata is a serverless PostgreSQL-based platform that replicates data to Elasticsearch for full-text, vector, and hybrid search. The post walks through a TypeScript code example building a conversational Q&A chatbot that uses Xata to store document embeddings for retrieval and chat history for memory, with links to a starter-kit repo and a Python Jupyter notebook equivalent. Future plans include custom retrievers for Xata's keyword/hybrid search and its Ask AI endpoint. Xata is also running a launch-week content hackathon with prizes for building demos.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.langchain.com/blog/xata-x-langchain-new-vector-store-and-memory-store-integrations>

## Questions this post answers

### How do I use Xata as a vector store in LangChain.js?

Import XataVectorSearch from langchain/vectorstores/xata and instantiate it with an embeddings object and a Xata client plus table name, for example new XataVectorSearch(embeddings, { client, table }). Documents added via vectorStore.addDocuments() are stored with a content column and an embedding vector column, and it supports metadata filtering during similarity search.

_daily.dev surfaces integration guides like this for developers wiring vector search into LangChain apps._

### How can I store LangChain chat memory in a Xata database instead of in-memory?

Use XataChatMessageHistory from langchain/stores/message/xata as the chatHistory for a BufferMemory instance, passing a table name, a unique sessionId per conversation, and the Xata client. Messages get persisted in a Xata table (e.g. named memory), so conversation context survives across requests rather than being lost when the process restarts.

_Developers building persistent chat memory into LLM apps track integrations like this via daily.dev._

### What is Xata and how does its architecture support both keyword and vector search?

Xata is a serverless database platform that stores source-of-truth data in PostgreSQL while automatically replicating it to Elasticsearch, giving developers Postgres features like ACID transactions and joins alongside Elasticsearch's BM25 full-text, vector, and hybrid search, all behind one serverless API. It offers TypeScript/Python SDKs and integrations with GitHub, Vercel, and Netlify.

_daily.dev helps developers compare data platforms like Xata when choosing infrastructure for AI apps._

## Similar posts on daily.dev

- [Announcing the LangChain \+ MongoDB Partnership: The AI Agent Stack That Runs On The Database You Already Trust](https://daily.dev/posts/announcing-the-langchain-mongodb-partnership-the-ai-agent-stack-that-runs-on-the-database-you-alr-tppi6f9rc) · LangChain · 5 upvotes · 0 comments
- [GitHub - xataio/xata: Open source, cloud native, Postgres platform with copy-on-write branching and scale-to-zero](https://daily.dev/posts/github---xataio-xata-open-source-cloud-native-postgres-platform-with-copy-on-write-branching-and--umulkvho5) · Lobsters · 60 upvotes · 1 comments
- [Building an AI-Powered Operations Assistant with Spring AI and MongoDB Atlas — Part 2: Conversational Memory](https://daily.dev/posts/building-an-ai-powered-operations-assistant-with-spring-ai-and-mongodb-atlas-part-2-conversationa-zq3na1mno) · Foojay.io · 0 upvotes · 0 comments
- [Timescale Vector x LangChain: Making PostgreSQL A Better Vector Database for AI Applications](https://daily.dev/posts/timescale-vector-x-langchain-making-postgresql-a-better-vector-database-for-ai-applications-7asfkr7wt) · LangChain · 0 upvotes · 0 comments

---

Tags: [#postgresql](https://daily.dev/tags/postgresql), [#rag](https://daily.dev/tags/rag), [#vector-search](https://daily.dev/tags/vector-search), [#langchain](https://daily.dev/tags/langchain)

[View this post on daily.dev](https://daily.dev/posts/xata-x-langchain-new-vector-store-and-memory-store-integrations-8avur25os)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Xata x LangChain: new vector store and memory store integrations","url":"https://daily.dev/posts/xata-x-langchain-new-vector-store-and-memory-store-integrations-8avur25os","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/xata-x-langchain-new-vector-store-and-memory-store-integrations-8avur25os"},"datePublished":"2026-08-26T14:37:04.529Z","dateModified":"2026-09-13T19:46:19.456Z","description":"Xata and LangChain announce four new integrations: Xata as a vector store and as a memory store, available for both Python and TypeScript/JavaScript LangChain....","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/5f2b525a744a21f3fafc03a4559151db?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/5f2b525a744a21f3fafc03a4559151db?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/xata-x-langchain-new-vector-store-and-memory-store-integrations-8avur25os","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"postgresql,rag,vector-search,langchain","timeRequired":"PT7M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"Xata x LangChain: new vector store and memory store integrations"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/xata-x-langchain-new-vector-store-and-memory-store-integrations-8avur25os#faq","mainEntity":[{"@type":"Question","name":"How do I use Xata as a vector store in LangChain.js?","acceptedAnswer":{"@type":"Answer","text":"Import XataVectorSearch from langchain/vectorstores/xata and instantiate it with an embeddings object and a Xata client plus table name, for example new XataVectorSearch(embeddings, { client, table }). Documents added via vectorStore.addDocuments() are stored with a content column and an embedding vector column, and it supports metadata filtering during similarity search. daily.dev surfaces integration guides like this for developers wiring vector search into LangChain apps."}},{"@type":"Question","name":"How can I store LangChain chat memory in a Xata database instead of in-memory?","acceptedAnswer":{"@type":"Answer","text":"Use XataChatMessageHistory from langchain/stores/message/xata as the chatHistory for a BufferMemory instance, passing a table name, a unique sessionId per conversation, and the Xata client. Messages get persisted in a Xata table (e.g. named memory), so conversation context survives across requests rather than being lost when the process restarts. Developers building persistent chat memory into LLM apps track integrations like this via daily.dev."}},{"@type":"Question","name":"What is Xata and how does its architecture support both keyword and vector search?","acceptedAnswer":{"@type":"Answer","text":"Xata is a serverless database platform that stores source-of-truth data in PostgreSQL while automatically replicating it to Elasticsearch, giving developers Postgres features like ACID transactions and joins alongside Elasticsearch's BM25 full-text, vector, and hybrid search, all behind one serverless API. It offers TypeScript/Python SDKs and integrations with GitHub, Vercel, and Netlify. daily.dev helps developers compare data platforms like Xata when choosing infrastructure for AI apps."}}]}
```

