OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Pinecone – Neo4j integration demo

Pinecone - Neo4j integration demo is an open-source application for processing and exploring Supreme Court cases with Pinecone vector search and a Neo4j knowledge graph. Its workflow uses MongoDB for database setup and OpenAI for case embeddings, with Jupyter notebooks handling data processing and an explorer application for use after processing.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pinecone - Neo4j integration demo — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it as a reference implementation when you need to study or adapt a case-data workflow that pairs embedding-based retrieval with graph exploration.

Who it is for

  • Developers prototyping legal-document retrieval that combines semantic search and graph relationships.
  • Researchers exploring Supreme Court case data through processed embeddings and linked knowledge.

Documented uses

  • Fetch and process raw Supreme Court case data.
  • Generate embeddings for SCOTUS cases.
  • Explore processed cases using vector search alongside a knowledge graph.
Before you choose

Requirements & limits

The repository is public and specifies an Apache-2.0 license. Running the documented workflow requires configuration for Neo4j, MongoDB, Pinecone and an OpenAI API key.

  • Case processing and embedding generation are separate from starting the explorer; data processing must be completed first.
  • Setup uses Poetry for Python dependencies and pnpm for Node.js dependencies.
  • The processing notebooks are SCOTUS-focused; another corpus may need ingestion and metadata changes (Likely compatible).
  • Using an embedding provider other than OpenAI requires modification; alternative-provider support is not demonstrated (Requires modification).

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 the repository and prepare its case data

Install the documented Python and explorer dependencies, configure service credentials, and process Supreme Court cases for the application.

Before you start

  • A MongoDB database, Neo4j account and Pinecone account
  • An OpenAI API key
  • Python dependencies managed with Poetry and Node.js dependencies managed with pnpm

Steps

  1. Clone the repository.

  2. From the repository root, run poetry install.

  3. Enter the explorer directory and run pnpm install.

  4. Create a .env file with the documented Neo4j, MongoDB, Pinecone and OpenAI settings.

  5. Use process_raw.ipynb to fetch and process raw case data, then process_scotus.ipynb to process SCOTUS cases and generate embeddings.

Expected outcome

The documented dependencies and service settings are in place, and the notebooks provide the case-processing and embedding stages used before starting the explorer.

Guide limitations

  • The setup instructions require accounts or database access for the named services.
  • The application start command is documented only after data processing is complete.
Documentation 1 ↗
Source-based practical guide

Start the explorer after processing case data

Start the application from its explorer directory once case processing is complete.

Before you start

  • The repository dependencies installed and environment variables configured
  • Case data processed using the documented notebooks

Steps

  1. Change to the explorer directory.

  2. Run pnpm dev.

Expected outcome

The documented development command starts the application after its data-processing stage.

Guide limitations

  • The README does not provide further run-time or deployment instructions.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Pinecone – Neo4j integration demoFetch and process raw Supreme Court case data.Cloud, WebThe repository is public and specifies an Apache-2.0 license. Running the documented workflow requires configuration for Neo4j, MongoDB, Pinecone and an OpenAI API key.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
pinecone-io/pinecone-neo4j-explorer · Official homepage title · retained in its source language
How we review sourcesSuggest a correction