Skip to content

Latest commit

 

History

14 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CogniChain

No GenAI experience required! Skip the classroom and courses and get started on building your own GenAI applications using CogniSwitch. Using its unique automated pipeline, CogniSwitch helps developers build GenAI applications by:

💨 Speeding up GenAI development

⚙️ Handling decisions related to ICP (Ingestion, Curation & Procurement) of knowledge/Information

🪄Drastically reduces hallucinations of LLMs

🎯 Improves accuracy of responses generated

🚀 Only takes 3 simple steps to get started

To help LangChain users conquer generative AI, we’ve put together “CogniChain” that helps seamlessly integrate with CogniSwitch to develop state of the art GenAI applications.

Become A GenAI Developer now: Signup (cogniswitch.ai)

Learn more about CogniSwitch: https://www.cogniswitch.ai/developer

Registration:

  • Signup with your email and verify your registration
  • You will get a mail with a platform token and OAuth token for using the services.

Step 1: CogniSwitch Store Chain:

  • Use your CogniSwitch token, OpenAI API key, OAuth token and your file or URL to run the chain.
  • Currently we support PDF(.pdf), Word(.docx, .doc), text(.txt), HTML(.html) file formats. (more formats are coming)
  • It will be processed and stored in your knowledge store.
  • You can check the status of document processing in CogniSwitch console.

Step 2: CogniSwitch Answer Chain:

  • Use your CogniSwitch token, OpenAI API key, OAuth token and your question to run the chain.
  • You will get the answer from your knowledge as the response.
  • In order to use the CogniSwitch chains you need to get the "CogniChain" folder from the repository and put it in the same directory as notebook and import the chains as shown in the notebook.

Use this example notebook to try the cogniswitch chains from here

About

Use CogniSwitch with LangChain

Resources

Stars

7 stars

Watchers

2 watching

Forks

Releases

Packages

Contributors

Languages