Hacker News Reader

Comment by edmundsauto | Hacker News Reader

How does this compare to LangChain?

I don't know how its performance compares, but its architecture is completely different: LangChain is a "normal" software library, but Gorilla is itself an LLM:

> Gorilla is a LLM that can provide appropriate API calls. It is trained on three massive machine learning hub datasets: Torch Hub, TensorFlow Hub and HuggingFace. We are rapidly adding new domains, including Kubernetes, GCP, AWS, OpenAPI, and more. Zero-shot Gorilla outperforms GPT-4, Chat-GPT and Claude. Gorilla is extremely reliable, and significantly reduces hallucination errors.

My reading of that abstract is that it's an LLM that outputs API calls instead of natural language (or maybe it still outputs natural language, but it can use API calls during inference? I didn't read very far), whereas LangChain is simply a software library. In theory, you could probably get Gorilla to output LangChain "API" (function) calls...

"We release Gorilla, a finetuned LLaMA-based model that surpasses the performance of GPT-4 on writing API calls"

Sounds like it's another LLaMA variant specifically fine tuned for API calls.

Good point. This was the original release, we now also have Apache-2.0 licensed models finetuned on MPT-7B and Falcon-7B!

There is Open Llama 7B which is Apache 2.0 licensed, please consider checking it out https://github.com/openlm-research/open_llama

Still outputs natural language. Example from their colab:

Input: I would like to translate from English to Chinese.

Output:

<<<domain>>>: Natural Language Processing Text2Text Generation

<<<api_call>>>: M2M100ForConditionalGeneration.from_pretrained('facebook/m2m100_1.2B')

<<<api_provider>>>: Hugging Face Transformers

<<<explanation>>>: 1. Import M2M100ForConditionalGeneration and M2M100Tokenizer from the transformers library.

2. Load the pre-trained M2M100 model and tokenizer using the from_pretrained() method. The model is trained to translate text from English to Chinese, among other languages.

3. Encode the input text in English using the tokenizer.

4. Generate the translation using the model.generate() method.

5. Decode the output tokens using the tokenizer to obtain the translated text in Chinese.

6. Print the translated text.

Hi @csjh, we trained to model to also additionally output additional context so it would be useful for a downstream task. We wrapped the API call with special decorator so it's easier to just regex. Would you like to just have the API instead? Happy to release an API only model if there is wider interest - It's a strictly easier task for Gorilla LLM :)

I would love this!

Ideally I'd like the result to be in a clean json with a key that's strictly the result and other keys for context information. It would reduce needing to use regex everywhere.

Langchain is a terrific project that tries to teach agents how to use tools using prompting. Our take on this is that prompting is not scalable if you want to pick between 1000s of APIs. So Gorilla is a LLM that can pick and write the semantically and syntactically correct API for you to call! A drop in replacement into Langchain!

Reply on news.ycombinator.com