Проблемы с Python и Ollama ⇐ Python

[Anonymous]

Я использую Python 3.11.7 на Mac M2. У меня есть этот список зависимостей в венве.
У меня проблемы с Олламой. Я тестирую локально и докеризую. Ошибка мне не помогла.
Идея состоит в том, чтобы загрузить HTML и иметь возможность запрашивать его в этом контексте.
Это код:

Код: Выделить всё

from langchain_community.llms import Ollama
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.document_loaders import PyPDFLoader
from langchain_community.vectorstores import Chroma
from langchain_community import embeddings
from langchain_community.chat_models import ChatOllama
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain.output_parsers import PydanticOutputParser
from langchain.text_splitter import CharacterTextSplitter

model_local = Ollama(base_url="http://192.168.0.200:11434", model="mistral")

# 1. Split data into chunks
urls = [
"https://es.wikipedia.org/wiki/The_A-Team",
]
docs = [WebBaseLoader(url).load() for url in urls]
docs_list = [item for sublist in docs for item in sublist]
text_splitter = CharacterTextSplitter.from_tiktoken_encoder(chunk_size=7500, chunk_overlap=100)
doc_splits = text_splitter.split_documents(docs_list)

# 2. Convert documents to Embeddings and store them
vectorstore = Chroma.from_documents(
documents=doc_splits,
collection_name="rag-chroma",
embedding=embeddings.ollama.OllamaEmbeddings(model='nomic-embed-text'),
)
retriever = vectorstore.as_retriever()

# 3. Before RAG
print("Before RAG\n")
before_rag_template = "What is {topic}"
before_rag_prompt = ChatPromptTemplate.from_template(before_rag_template)
before_rag_chain = before_rag_prompt | model_local | StrOutputParser()
print(before_rag_chain.invoke({"topic": "Ollama"}))

# 4.  After RAG
print("\n########\nAfter RAG\n")
after_rag_template = """Answer the question based only on the following context:
{context}
Question: {question}
"""
after_rag_prompt = ChatPromptTemplate.from_template(after_rag_template)
after_rag_chain = (
{"context": retriever, "question": RunnablePassthrough()}
| after_rag_prompt
| model_local
| StrOutputParser()
)
print(after_rag_chain.invoke("Quien integra Brigada A?"))

Справа я перечисляю модели, а слева сообщаю, ответит ли Оллама.

Ошибка

Код: Выделить всё

cd /Users/santiago/Proyects/OllamaURL ; /usr/bin/env /Users/santiago/Proyects/OllamaURL/env/bin/python /Users/santiago/.vscode/extensions/ms-python.debugpy-2024.2.0-darwin-arm64/bundled/libs/debugpy/adapter/../../debugpy/launcher 54637 -- /Users/santiago/Proyects/OllamaURL/rag.py
Traceback (most recent call last):
File "/Users/santiago/Proyects/OllamaURL/rag.py", line 25, in 
vectorstore = Chroma.from_documents(
^^^^^^^^^^^^^^^^^^^^^^
File "/Users/santiago/Proyects/OllamaURL/env/lib/python3.11/site-packages/langchain_community/vectorstores/chroma.py", line 778, in from_documents
return cls.from_texts(
^^^^^^^^^^^^^^^
File "/Users/santiago/Proyects/OllamaURL/env/lib/python3.11/site-packages/langchain_community/vectorstores/chroma.py", line 736, in from_texts
chroma_collection.add_texts(
File "/Users/santiago/Proyects/OllamaURL/env/lib/python3.11/site-packages/langchain_community/vectorstores/chroma.py", line 275, in add_texts
embeddings = self._embedding_function.embed_documents(texts)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/santiago/Proyects/OllamaURL/env/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 204, in embed_documents
embeddings = self._embed(instruction_pairs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/santiago/Proyects/OllamaURL/env/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 192, in _embed
return [self._process_emb_response(prompt) for prompt in iter_]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/santiago/Proyects/OllamaURL/env/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 192, in 
return [self._process_emb_response(prompt) for prompt in iter_]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/santiago/Proyects/OllamaURL/env/lib/python3.11/site-packages/langchain_community/embeddings/ollama.py", line 166, in _process_emb_response
raise ValueError(
ValueError: Error raised by inference API HTTP code: 404, {"error":"model 'nomic-embed-text' not found, try pulling it first"}

Я хотел бы, чтобы вы помогли мне устранить эту ошибку.

Подробнее здесь: https://stackoverflow.com/questions/781 ... and-ollama