Integrate LangChain with FastAPI

[milesha]

Description

This PR is based on the PR for the FastAPI setup

Summary

• Added LangChain and GPT-instance support for the application
• Created a chat endpoint in the intelligence-service that uses LangChain to interact with LLMs
• Provided a .env.example file with the necessary environment variables.

Motivation

To effectively interface with large language models (LLMs), we need to integrate LangChain into our FastAPI intelligence service

Related Issue

Integrate LangChain with FastAPI Issue #32

Checklist

General

• PR title is clear and descriptive
• PR description explains the purpose and changes
• Code follows project coding standards
• Self-review of the code has been done
• Changes have been tested locally
• Screenshots have been attached (if applicable)
• Documentation has been updated (if applicable)

Client (if applicable)

• UI changes look good on all screen sizes and browsers
• No console errors or warnings
• User experience and accessibility have been tested
• Added Storybook stories for new components
• Components follow design system guidelines (if applicable)

Server (if applicable)

• Code is performant and follows best practices
• No security vulnerabilities introduced
• Proper error handling has been implemented
• Added tests for new functionality
• Changes have been tested in different environments (if applicable)

Screenshots (if applicable)

Attach screenshots here.

[GODrums]

Looks great, good job! Just added a few very small remarks.

Tested it successfully with OpenAI (Azure got some permission issues with my account, have to get that fixed first).

[GODrums]

This file should be omittable since we are already ignoring .env-files with the .gitignore of the base folder.

[GODrums]

Would love to have an additional more concrete description of which services we are currently using (e.g. OpenAI/Azure OpenAI, GPT-3.5-turbo, etc.).

[GODrums]

Is there a reason you explicit typing it as str?

[FelixTJDietrich]

@milesha you can stack PRs by branching of the feature/set-up-intelligence-service and then setting the target to feature/set-up-intelligence-service instead of develop.