docs.langflux.space
  • Welcome to LangFlux
  • Using LangFlux
    • API
    • Streaming
    • Embed
    • Variables
  • Configuration
    • Auth
      • Chatflow Level
    • Rate Limit
  • Integrations
    • Cache
      • InMemory Cache
    • Chains
      • Conversational Retrieval QA Chain
      • Vectara QA Chain
    • Document Loaders
      • S3 File Loader
      • PDF Files
    • Chat Models
      • Azure ChatOpenAI
      • ChatLocalAI
      • Google VertexAI
    • Embeddings
      • Azure OpenAI Embeddings
      • LocalAI Embeddings
    • Memory
      • Short Term Memory
      • Long Term Memory
        • Zep Memory
      • Threads
    • Text Splitters
      • Character Text Splitter
    • Tools
      • Custom Tool
    • Vector Stores
      • Chroma
      • Pinecone
      • Elastic
      • Qdrant
      • SingleStore
      • Supabase
      • Vectara
    • Utilities
      • Set/Get Variable
      • If Else
    • External Integrations
      • Zapier Zaps
  • Use Cases
    • Web Scrape QnA
    • Webhook Tool
Powered by GitBook
On this page
  • Prerequisite
  • Setup
  • Additional
  • Resources

Was this helpful?

  1. Integrations
  2. Vector Stores

Chroma

PreviousVector StoresNextPinecone

Last updated 1 year ago

Was this helpful?

Prerequisite

  1. Download & Install and

  2. Clone with your terminal

git clone https://github.com/chroma-core/chroma.git
  1. Change directory path to your cloned Chroma

cd chroma
  1. Run docker compose to build up Chroma image and container

docker-compose up -d --build
  1. If success, you will be able to see the docker images spun up:

Setup

Input
Description
Default

Document

Embeddings

Collection Name

Chroma URL

Specify the URL of your chroma instance

http://localhost:8000

Additional

If you are running both LangFlux and Chroma on Docker, there are additional steps involved.

  1. Spin up Chroma docker first

docker-compose up -d --build
  1. Open docker-compose.yml in LangFlux

cd Flowise && cd docker
  1. Modify the file to:

version: '3.1'

services:
    flowise:
        image: flowiseai/flowise
        restart: always
        environment:
            - PORT=${PORT}
            - FLOWISE_USERNAME=${FLOWISE_USERNAME}
            - FLOWISE_PASSWORD=${FLOWISE_PASSWORD}
            - DEBUG=${DEBUG}
            - DATABASE_PATH=${DATABASE_PATH}
            - APIKEY_PATH=${APIKEY_PATH}
            - SECRETKEY_PATH=${SECRETKEY_PATH}
            - FLOWISE_SECRETKEY_OVERWRITE=${FLOWISE_SECRETKEY_OVERWRITE}
            - LOG_PATH=${LOG_PATH}
            - LOG_LEVEL=${LOG_LEVEL}
            - EXECUTION_MODE=${EXECUTION_MODE}
        ports:
            - '${PORT}:${PORT}'
        volumes:
            - ~/.flowise:/root/.flowise
        networks:
            - flowise_net
        command: /bin/sh -c "sleep 3; flowise start"
networks:
    flowise_net:
        name: chroma_net
        external: true
  1. Spin up LangFlux docker image

docker-compose up -d

Resources

Can be connected with nodes from

Can be connected with nodes from

Chroma collection name. Refer to for naming convention

On the Chroma URL, for Windows and MacOS Operating Systems specify . For Linux based systems the default docker gateway should be used since host.docker.internal is not available:

http://host.docker.internal:8000
http://172.17.0.1:8000
LangChain JS Chroma
Chroma Getting Started
Document Loader
Embeddings
here
Docker
Git
Chroma's repository