Problems With Python and Ollama

tux_tina

I'm using Python 3.11.7 on an M2 Mac. I have this list of dependencies in a venv. I'm having problems with Ollama. I test locally and dockerized. The error did not help me. The idea is to load an HTML and be able to query it, in that context. This is the code: from langchain_community.llms import Ollama from langchain_community.document_loaders import WebBaseLoader from langchain_community.document_loaders import PyPDFLoader from...

Originally asked by safernandez666 on Stack Exchange (stackoverflow) (CC BY-SA 4.0).

uphilltech

Great question — answering as the UphillTech team:

I tweak your code and re-run it successfully. Here's the code from langchain.text_splitter import CharacterTextSplitter from langchain.schema.document import Document text_splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=20) text = "I am going to tell you a story about Tintin." docs = [Document(page_content=x) for x in text_splitter.split_text(text)] from langchain_community.vectorstores import Chroma from langchain_community.llms import Ollama from langchain_community import embeddings persist_directory = "/tmp/chromadb" vectorstore = Chroma.from_documents( documents=docs, collection_name="test", embedding=embeddings.ollama.OllamaEmbeddings(model='nomic-embed-text') )...

Full answer by j3ffyang: https://stackoverflow.stackexchange.com/a/78164483 (CC BY-SA 4.0).

Need it done for your business? UphillTech.