Skip to main content

Getting Started

Vector is a HTTP API that allows you to process files contents and process it through an embedding pipeline. Vectorflows works with a couple services including rabbitmq, postgres database, and a vector database of your choice() To get Vectorflow up and running, we will need to run a docker container.

## Prerequisites

Before you get started, ensure you have the following:

1. **Docker Installed**: This tutorial extensively uses `docker` and `docker-compose`. If you don't have Docker installed, you can download and install it from [Docker's official website](

2. **AWS Account**: If you plan to use AWS S3 integration, make sure you have an AWS account and appropriate permissions to generate pre-signed URLs.

3. **API Keys**: Have your API keys for the respective services (e.g., OpenAI ADA embeddings, Pinecone, Qdrant, Weaviate, Milvus) you plan to use.

4. **Latest Version of Python and PIP**: Make sure you have the latest versions of python and pip installed.

## Clone the Repo

**Locally**: To get started clone the repo and cd into it.

**Codespaces Walkthrough**: Codespaces coming soon!

Chat with our Dev Docs 🤖

Circular button