News for hackers. Stuff that matters.
Re:Show HN: Chat with your data using LangChain, Pinecone, a... by jmorgan on Tuesday August 08, 2023 @12:28PM (#37051571)
LangChain supports local LLMs like Llama 2 with Ollama (https://github.com/jmorganca/ollama) as of this morning, in both their Python and Javascript versions:

https://python.langchain.com/docs/integrations/llms/ollama

This can be a great option if you'd like to keep your data local versus submitting it to a cloud LLM, with the added benefit of saving costs if you're submitting many questions in a row (e.g. in batches)

Re:Show HN: Chat with your data using LangChain, Pinecone, a... by mtricot on Tuesday August 08, 2023 @01:01PM (#37052146)
I am sure we can build something around that. Going to take a look at it. Thanks for mentioning it.
Re:Show HN: Chat with your data using LangChain, Pinecone, a... by hnhg on Tuesday August 08, 2023 @02:22PM (#37053348)
Thanks. How would this differ from running Llama2 through the Huggingface-Langchain integration? I haven't tried it but it looked like the way to go until you shared this.
Re:Show HN: Chat with your data using LangChain, Pinecone, a... by zwaps on Tuesday August 08, 2023 @03:03PM (#37053925)
This one is for Mac
Re:Show HN: Chat with your data using LangChain, Pinecone, a... by wahnfrieden on Wednesday August 09, 2023 @01:10AM (#37058930)
Huggingface launched swift/mac today or in recent days
Re:Show HN: Chat with your data using LangChain, Pinecone, a... by bestcoder69 on Tuesday August 08, 2023 @09:05PM (#37057548)
How well does it work?
Re:Show HN: Chat with your data using LangChain, Pinecone, a... by zarazas on Thursday August 10, 2023 @05:07AM (#37073728)
Can llama 2 also be used to create the embeddings?