Farcaster Memory Store

The Fastercaster Memory Vector Store stores the casts of a given fid in memory.

This vector store can be useful to give context to an agent about his pasts casts, or to make him act like an existing user on Farcaster.

Usage

In order to use the Farcaster Memory Vector Store, you need to pass a valid fid and a NEYNAR_API_KEY for fetching the casts from Farcaster.

import { createFarcasterMemoryVectorStore } from "@brian-ai/langchain";
 
const farcasterMemoryVectorStore = await createFarcasterMemoryVectorStore({
  fid: process.env.FID,
  neynarApiKey: process.env.NEYNAR_API_KEY,
});

Query the store

You can use the similaritySearch method on the vector store to retrieve the most similar casts to a given text.

const similarCasts = await memoryStore.similaritySearch(
  "Brian is such an awesome project!"
);

Retriever

Most of the times, you want to use this store as a retriever for easier usage in your chains.

const retriever = memoryStore.asRetriever({
  // optional filter
  filter,
  k: 2, // number of casts to retrieve
});
await retriever.invoke("Brian is such an awesome project!");

More complex stores

In case you need a store with persisting, and the capability of filtering for metadata for example, you can check the Farcaster Supabase Store.