docs/integrations/chat/ollama/

[giscus[bot]]

docs/integrations/chat/ollama/

Ollama allows you to run open-source large language models, such as Llama 2, locally.

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

[VpkPrasanna]

when can we expect support for llama3.2 models ?

[HuangChiEn]

it already support llama3.2-vision. So i guess the other model also be supported by llm = ChatOllama(model="llama3.2xxx"). The issue will be ollama, i.e. only ollama>0.4.0.rc can pull llama3.2-vision, the older version can not. (after you pull the llama3.2 models, everything goes fine ~ )

[shan-max]

buy a car

[chocwaffles]

I have issues using chatollama to replace ollamafunctions as below
Swapped

llm = OllamaFunctions(model="mistral:7b-instruct-v0.3-q8_0", temperature=0, format="json")

for

llm = ChatOllama(model="llama3.1:8b-instruct-q5_K_M", temperature=0)

to perform

from langchain_experimental.graph_transformers import LLMGraphTransformer
llm_transformer = LLMGraphTransformer(llm=llm)
graph_documents = llm_transformer.convert_to_graph_documents(documents)

What am i missing? thanks.

[HuangChiEn]

It's a good form to support image input by using base64 encode. Although doc in here didn't explicitly describe the way, llama3.2-vision also follow the same way as bakllava to process image input (base64) in HumanMessage.