Transforming Invoice Data into JSON: Local LLM with LlamaIndex & Pydantic 🚀 Complete video: Code: I explain how to get structured JSON output with LlamaIndex and dynamic Pydantic class. This helps to implement the use case of data extraction from invoice documents. The solution runs on the local machine,... thanks to Ollama. I'm using a MacBook Air M1 with 8GB RAM. LlamaIndex 🦙 Pydantic ollama #Python #LLM #RAGshow more

Does this work on financial statements?

Starling LLM, the one I'm using here, is generic. It should work on financial statements. It can be replaced easily by switching the LLM name in config.yml with Mixtral or another more powerful LLM to process more complex docs.

Thank you. 👍🏻

@andrejusb What are you using for OCR? Invoice formats have no standardization and they vary across different vendors/suppliers, do you not need to train the model for accuracy?

That's a lovely piece of "Fintech"

I built same thing with chatgpt, it works very well

The whole point is to built it without chatgpt to run for private data workflows

I'm GPU poor so...

With Ollama it runs on CPU or on Apple M1, Nvidia GPU is not needed. I’m also GPU poor and run LLMs on CPU locally

Thanks man, much appreciated 👏

@LinasVastakas

@memdotai Mem it

Learn how to access market data using Polygon's Stock API and the Python programming language.