langchain/templates/llama2-functions/README.md

# Extraction with LLaMA2 Function Calling

This template shows how to do extraction of structured data from unstructured data, using LLaMA2 [fine-tuned for grammars and jsonschema](https://replicate.com/andreasjansson/llama-2-13b-chat-gguf).

Specify the scehma you want to extract in `chain.py`

By default, it will extract the title and author of papers.

##  LLM

This template will use a `Replicate` [hosted version](https://replicate.com/andreasjansson/llama-2-13b-chat-gguf) of LLaMA2 that has support for grammars and jsonschema. 

Based on the `Replicate` example, these are supplied directly in the prompt.

Be sure that `REPLICATE_API_TOKEN` is set in your environment.
LLaMA2 with JSON schema support template (#12435) 2023-10-27 17:34:00 +00:00			`# Extraction with LLaMA2 Function Calling`

			`This template shows how to do extraction of structured data from unstructured data, using LLaMA2 [fine-tuned for grammars and jsonschema](https://replicate.com/andreasjansson/llama-2-13b-chat-gguf).`

			Specify the scehma you want to extract in `chain.py`

			`By default, it will extract the title and author of papers.`

			`## LLM`

Add invoke example to LLaMA2 function template notebook (#12437) 2023-10-27 17:58:24 +00:00			This template will use a `Replicate` [hosted version](https://replicate.com/andreasjansson/llama-2-13b-chat-gguf) of LLaMA2 that has support for grammars and jsonschema.

			Based on the `Replicate` example, these are supplied directly in the prompt.
LLaMA2 with JSON schema support template (#12435) 2023-10-27 17:34:00 +00:00
			Be sure that `REPLICATE_API_TOKEN` is set in your environment.