MarketplaceStudioActivityLLM Framework - Langchain Activities

Create your first automation in just a few minutes.Try Studio Web

LLM Framework - Langchain Activities

LLM Framework - Langchain Activities

by Russel A P.

StarStarStarStarStarStarStarStarStarStar

0

Activity

Downloads

<100

back button
back button
next button
next button

Summary

Summary

Easily build your own Generative AI powered automation using these custom activities powered by LangChain Framework for context-aware, memory-backed and multi-input chain LLM calls

Overview

Overview

LLM Powered Custom Activities built using LangChain Framework. These activities build up the core elements to enable context-aware and memory-backed interaction with your favorite large language models.

Host Python Backend using Docker

The following steps portray Docker container running on a local machine. In a production scenario, it’s best to host the API on a proper remote app server.

  1. Download & Install Docker - https://www.docker.com/products/docker-desktop/.
  2. Make sure Docker is running by starting up the application. Verify docker is running by checking docker icon in the right icons panel.
  3. Run the following script in command line --> docker run -p 5000:5000 zell12/qblangchainapi:latest.
  4. Verify if http://localhost:5000 is running in the browser, which means the API is running.

Video Walkthrough

  • 00:10 - LLM Framework Activities Overview
  • 00:38 - Host Backend API with Docker
  • 02:18 - Add Activity Package
  • 04:11 - Generate Embeddings API Key
  • 05:16 - Create Vector Store
  • 11:08 - Configurations via LLM Framework Template
  • 11:53 - Memory Reference
  • 13:31 - Execute basic setup

Features

Features

🗝️ LLM Powered Custom Activities using LangChain Framework – Industry Standard for LLM App Development

  • Ingest Knowledge Source –  Create and serialize vector database out of provided sources such as CSV, PDF, DOCX, YouTube video links, Word documents, etc.
  • Converse With Context – Context Aware, Multi-input (llm model, context docs, memory/history, prompt template) LLM Chain.

Additional Information

Additional Information

Dependencies

o Docker - Download Docker Desktop | Docker - https://www.docker.com/ o OpenAI API Key (https://platform.openai.com/) or Claude API Key (Anthropic Console) o Pinecone Account - https://app.pinecone.io/ A. Register and create a project. B. Create/Name your index. C. Index Dimensions should be 1536 (OpenAI output embeddings dimension).

Code Language

C#, Visual Basic

Runtime

Windows (.Net 5.0 or higher)

Publisher

Russel A P.

Visit publisher's page

License & Privacy

Apache

Privacy Terms

Technical

Version

2.0.1

Updated

October 16, 2023

Works with

Studio: 23.4+

Certification

Silver Certified

Application

Anthropic ClaudeOpenAIPineconeUiPath Studio

Support

UiPath Community Support

Resources

Similar Listings