Ollama meets LangChain

preview_player
Показать описание

My Links:

Github:

00:00 Intro
01:02 How to load Ollama model locally?
01:57 Basic Chain
03:10 Rag example

#ollama #langchain
Рекомендации по теме
Комментарии
Автор

I’d definitely be interested in seeing how to build a full local rag system using ollama

jdallain
Автор

It would be great to have a video on using ollama to build a local RAG system.

tiagodejesus
Автор

I'd really be interested in seeing a JavaScript implementation of using Langchain and Ollama.

jdray
Автор

Great coverage. Thank you for taking the time to review 0llama

bahramboutorabi
Автор

Yes! Awesome! - and I'd love to see a full RAG local setup for scraping as well as local docs vector database. Thanks for sharing!

autonomousreviews
Автор

Yes please make a full local rag, I have so many ideas for this!
🙏

Gee
Автор

yes, the followup idea would be very interesting to see.

wryltxw
Автор

Amazing! Thanks for sharing this. I made and uploaded a video that talks about the problems I experienced in installing Langchain. Mostly they had to do with trying to use python=3.12. 3.10 worked. So now I have a development environment with Langchain and Ollama! That means no OpenAI bills. It must be Christmas.

dr.mikeybee
Автор

Wow, great combo.Maybe I'll use something similar in future to summarize RSS news

luigitech
Автор

thank you. always interesting, always informative, nearly always useful!

sup
Автор

Full local rag would be good. Thanks for the video :)

bleo
Автор

20/10 - awesome video and presentation.

warlordkeys
Автор

Will you be adding any of your newest code to github anytime soon? I see everything looks to be about 4 months old. Your videos are very interesting.

haqthat
Автор

Would love to see a Nextjs app with Chromadb, BGE embeddings and ollama a fully functioning locally installed app that can be accessed through the web

mohammedalhazmi
Автор

Very nice video! I would love to see an implementation of a NextJs app powered by Langchain and most specifically the deployment process for both. I know that nextJs is deployed with Vercel but what about Langchain?

EmaSuriano
Автор

Thanks for introducing me to Ollama! I am running open-source models on LangChain, but having trouble with models calling (or not using) custom tools appropriately. Would you mind making a tutorial for initializing agents without openai models? Perhaps with kwargs. 🙏 All the docs, tutorials, deeplearning courses use openai models.... 😢

Annachrome
Автор

Thank you for this... Can we use ollama model for building open source LLM based langchain agents? I tried to build sql database agent using PaLM2, got to know that agent type can only OpenAI based LLMs... Can you please share your views.

AritraSen
Автор

How did I miss this. Can can wrap an agent with tools around it?

Anorch-oyjk
Автор

How do you pass a URL to the Ollama class if your Ollama instance is running somewhere online?

I imagine there should be a parameter like "host" but I am yet to come across it. Please let me know if such parameter is named differently!

AdemolaBalogun-qv
Автор

Super helpful video, Sam! I need to do RAG processing with confidential PDFs. Is there a way to download the model without using hugging face? The reason is it’s blocked on our corporate VPN.

paullopez_ai