apocas / restai Goto Github PK

This project is pretty great BUT we need more options to use different LLM's.You don't have to worry about creating a solution which supports 100+ LLM easily as LiteLLM is another foss project which is capable of doing this task for you.
Project LiteLLM link - https://github.com/BerriAI/litellm
You can study there project and see how it can be implemented in this project like you implemented support for ollama I believe similarly you can do it for LiteLLM which will be big win for the project as many will be easily able to use many more LLM easily which everyone wants and project will require 3 major parameters from user like base url,model name,api key that's all and with open ai api general structure it can query and give back result for the query.Many big projects have started adding support for this project in there project to make things advanced in easier way so study it and after that if you have any query you can ask them they are pretty responsive plus if u want to know more about my personal experience of using it with other great projects like flowise then I can tell you that too in detail.

I have a deployed openai service in azure and I want to utilize it, is there anyway to import besides using OPENAI_API_KEY ?

AZURE_OPENAI_API_ENDPOINT=
AZURE_OPENAI_API_KEY=
AZURE_OPENAI_API_VERSION=
AZURE_OPENAI_API_INSTANCE_NAME=
AZURE_OPENAI_API_DEPLOYMENT_NAME=
AZURE_OPENAI_API_EMBEDDINGS_DEPLOYMENT_NAME=

their format looks like this. Thanks!

A very good project.
I have a question, i see a docker-compose.yml located in the root directory. Is it means can directly launched it to run project without the need for other dependency operations.
Also, i think the document is worth improving, like ollama docs/ 😀

I see a lot of potential of this project. chroma and radis are added as database . it would be great if you kindly add at least one cloud database like pinecone. Thank you.

It would be great to see Knowledge Graph Integration in RestAI, this is now Trending in RAG Community.

Both the ragsql projects return a error 500.

One of the growing and important discussions in the RAG Community now is Agent. It would be great to see Agent Implementation in this project and also some advanced Retrieval like Automerging Retrieval in llama index.

Hi,

I was going through your recent ReAct agent code. On my computer, this code cannot load chat history:

chat = self.brain.memories.loadMemory(project.model.name).loadChat(chatModel)

Could you please explain how this chat loading works in your code? Additionally, are you able to give the agent chat history when the agent is answering the next question?

Thank you!

The requirements.txt file is a text file used for Python projects, which lists all the required dependencies and their version numbers for the project.

llama_index-0.10.14 is wrong
from llama_index.embeddings.langchain import LangchainEmbedding
from llama_index.postprocessor.colbert_rerank import ColbertRerank

As a user of the project, I would like the ability to integrate my own API keys for inference and embedding services such as OpenAI, Cohere, and Anthropic, allowing for greater flexibility and customization in utilizing these services within the project.

Hi @apocas,
I found the project very helpful and want to add some improvement to the project if you agree with the change.

Issues

1. Loading environment variable is not organized.
2. docker-compose file is not configured properly to run the project.

I want to add those changes if you think those change will improve the project.