# pashpashpash/vault-ai

OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.

Repository: https://github.com/pashpashpash/vault-ai
Canonical: https://ross.abutalabs.com/products/vault-ai
Homepage: https://vault.pash.city
Language: JavaScript
License: MIT
License Family: permissive
Topics: chatgpt, go, golang, knowledge-base, long-term-memory, machine-learning, openai, pdf-support, pinecone, question-answering, react, reactjs, vector-search, ai, artificial-intelligence, generative, openai-api, qdrant-vector-database
Last push: 2025-07-08T16:02:56+00:00

## Health v2 (maintenance only)
Score: 43/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 30, release rhythm 35, longevity 88
- inputs: {"age_days": 1233, "days_push": 421, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3388, forks 296 (observed 2026-08-28T04:07:58.897904+00:00)

## What it is
OP Vault is a self-hosted application combining a Go backend with a React frontend that lets users upload documents (PDF, txt, epub) into a custom knowledge base and ask ChatGPT questions about them using OpenAI plus the Pinecone vector database. It returns answers with citations pointing to the source file and section.

## Use cases
- chat with my own pdf documents using chatgpt
- build a question-answering app over a personal knowledge base
- give chatgpt long-term memory over my books and notes
- upload epub and txt files and ask questions about their contents
- get cited answers from a document library with source snippets
- self-host a rag chatbot with openai and pinecone

## When to choose
- you want a self-hosted document Q&A app with a ready-made React UI
- you want answers that cite the exact file and section they came from
- you want to load a large library of books and query it with OpenAI models

## When to avoid
- you need a plug-and-play library to embed RAG into an existing app rather than a standalone app
- you don't want to manage OpenAI and Pinecone API keys and costs
- you need fully local/offline inference without external APIs

## Facets
- artifact type: application
- maturity: active
- function: rag, vector-database, llm-inference, chatbot, pdf, web-framework, search-engine
- domain: large-language-models, artificial-intelligence, chatbots, pdf, web-development
- platform: go, self-hosted, cross-platform
- tags: openai, pinecone, qdrant, knowledge-base, document-qa, chatgpt, vector-search, react-frontend, golang-server, retrieval-augmented-generation, nodejs, web-server

## Member repositories
- pashpashpash/vault-ai (main) score 43

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:58.897904+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:39:05.302897+00:00, confidence not recorded.
  - readme: https://github.com/pashpashpash/vault-ai (fetched 2026-08-28T04:07:58.897904+00:00, sha c009fa2e9e97)
  - homepage: https://vault.pash.city (fetched 2026-08-29T09:33:14.547526+00:00, sha 36321ae6e06f)
- Data as of 2026-08-30T08:39:29.467469+00:00.