OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Firstbatch SDK

Firstbatch SDK is a Python library that connects vector databases to FirstBatch personalization so an application can manage user sessions, update embeddings from interaction signals and retrieve tailored content batches.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Firstbatch SDK — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when application code needs to turn user-session activity into personalized batches from content held in a vector database.

Who it is for

  • Python application developers adding personalized recommendations to an app.
  • Teams using vector databases such as Pinecone or Weaviate for application content.

Documented uses

  • Connect an application's vector database to FirstBatch personalization.
  • Create persistent-ID or temporary user sessions.
  • Return content batches tailored to session embeddings.
  • Send likes or clicks as signals that update user embeddings.
Before you choose

Requirements & limits

  • Requires Python 3.9 or later and API keys for FirstBatch and the selected vector database.
  • The README provides a concrete Pinecone setup example; repository topics also name Weaviate, Chroma, Supabase and Typesense.
  • The repository lists an MIT license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a Pinecone-backed recommendation session

Connect a Pinecone index to FirstBatch and request a personalized content batch.

Before you start

  • Python 3.9 or later
  • FirstBatch API key
  • Pinecone API key and environment
  • A Pinecone index

Steps

  1. Install the package with the command below.

    Documented command
    pip install firstbatch

  2. Initialize Pinecone and open the index to use.

  3. Create a FirstBatch instance with its API key and configuration, then register the index as a vector database.

  4. Create a session with a selected algorithm and the registered vector database ID, then call batch for recommendations.

Expected outcome

The example returns item IDs and a personalized batch for the session.

Guide limitations

  • The example does not document how to create or populate the Pinecone index.
  • It does not specify the available algorithms beyond showing AlgorithmLabel.AI_AGENTS as an example.
Documentation 1 ↗
Source-based practical guide

Use a like signal to update a session embedding

Send a user's like for an item from a returned batch as a personalization signal.

Before you start

  • A configured FirstBatch instance and vector database
  • An active session
  • Item IDs from a previously returned batch

Steps

  1. Request a batch for the session and retain its item IDs.

  2. Select the ID corresponding to the item the user liked.

  3. Call add_signal with the session, a LIKE user action and the selected item ID.

Expected outcome

The like is sent as a signal to shape the user's embedding.

Guide limitations

  • The example demonstrates a like signal; it does not give detailed handling for other signal types.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
firstbatchxyz/firstbatch-sdk · Official homepage title · retained in its source language
How we review sourcesSuggest a correction