OllamaEmbeddings Fails with 404 Error After Migration to langchain_ollama

[weitsung50110]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).

Example Code

from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain.chains import create_retrieval_chain, create_history_aware_retriever
from langchain_core.prompts import ChatPromptTemplate
from langchain_ollama import OllamaLLM, OllamaEmbeddings
from langchain_community.vectorstores import FAISS
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler

# Initialize Ollama LLM with streaming callback
llm = OllamaLLM(
    model='llama3',
    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])
)

# Initialize Ollama Embeddings
embeddings = OllamaEmbeddings(
    model='llama3'
)

# Create FAISS vector store and retriever
vector = FAISS.from_texts(["You are an AI assistant named Weibert's Angel."], embeddings)
retriever = vector.as_retriever()

# Prompt templates
prompt_search_query = ChatPromptTemplate.from_messages([
    ("user", "{input}"),
    ("user", "Generate a search query based on the previous conversation.")
])

prompt_get_answer = ChatPromptTemplate.from_messages([
    ("system", "Answer the user's question based on the following context:\n\n{context}"),
    ("user", "{input}")
])

# Create retriever and document processing chains
retriever_chain = create_history_aware_retriever(llm, retriever, prompt_search_query)
document_chain = create_stuff_documents_chain(llm, prompt_get_answer)

# Combine into a retrieval chain
retrieval_chain_combine = create_retrieval_chain(retriever_chain, document_chain)

def main():
    """Main function to handle user input and generate responses."""
    print("Welcome to Weibert's Angel Chatbot! Type 'bye' to exit.")

    while True:
        try:
            user_input = input(">>> ").strip()

            if user_input.lower() == "bye":
                print("Goodbye! See you next time!")
                break

            if user_input:
                response = retrieval_chain_combine.invoke({'input': user_input})

                # Store conversation in FAISS
                vector.add_texts([
                    f"User Input: {user_input}",
                    f"AI Response: {response['answer']}"
                ])

                # Output response
                print("--------------------------")
                print(response)
        except Exception as e:
            print(f"Error occurred: {e}")

if __name__ == "__main__":
    main()

Error Message and Stack Trace (if applicable)

Traceback (most recent call last):
File "/app/langchain_Conversation_Retrieval_Faiss.py", line 21, in
vector = FAISS.from_texts(["You are an AI assistant named Weibert's Angel."], embeddings)
File "/usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/faiss.py", line 1041, in from_texts
embeddings = embedding.embed_documents(texts)
File "/usr/local/lib/python3.10/dist-packages/langchain_ollama/embeddings.py", line 237, in embed_documents
embedded_docs = self._client.embed(
File "/usr/local/lib/python3.10/dist-packages/ollama/_client.py", line 356, in embed
return self._request(
File "/usr/local/lib/python3.10/dist-packages/ollama/_client.py", line 177, in _request
return cls(**self._request_raw(*args, **kwargs).json())
File "/usr/local/lib/python3.10/dist-packages/ollama/_client.py", line 122, in _request_raw
raise ResponseError(e.response.text, e.response.status_code) from None
ollama._types.ResponseError: 404 page not found

Description

Previously, I was using OllamaEmbeddings from langchain_community.embeddings, and everything worked fine. However, after migrating to langchain_ollama, I started encountering a 404 page not found error.

It seems that after migrating OllamaEmbeddings from langchain_community.embeddings to langchain_ollama, something broke. Could you confirm if this is a bug or if additional configuration is required?

Thanks!

System Info

System Information

OS: Linux
OS Version: #1 SMP Thu Jan 11 04:09:03 UTC 2024
Python Version: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]

Package Information

langchain_core: 0.3.33
langchain: 0.3.13
langchain_community: 0.3.8
langsmith: 0.1.147
langchain_Conversation_Retrieval: Installed. No version info available.
langchain_Conversation_Retrieval_Faiss: Installed. No version info available.
langchain_Conversation_Retrieval_chroma: Installed. No version info available.
langchain_agents_STRUCTURED_CHAT: Installed. No version info available.
langchain_agents_STRUCTURED_CHAT2: Installed. No version info available.
langchain_agents_STRUCTURED_CHAT_demo: Installed. No version info available.
langchain_agents_STRUCTURED_CHAT_demo2: Installed. No version info available.
langchain_agents_ZERO_SHOT: Installed. No version info available.
langchain_agents_ZERO_SHOT_langsmith: Installed. No version info available.
langchain_agents_ZERO_SHOT_wiki: Installed. No version info available.
langchain_agents_conversational-react_memory: Installed. No version info available.
langchain_agents_conversational-react_memory-Summary: Installed. No version info available.
langchain_agents_conversational-react_memory-Vector: Installed. No version info available.
langchain_agents_conversational-react_memory2: Installed. No version info available.
langchain_agents_conversational-react_memory3: Installed. No version info available.
langchain_agents_conversational-react_memory3_langsmith: Installed. No version info available.
langchain_json_test: Installed. No version info available.
langchain_ollama: 0.2.3
langchain_pdf_test: Installed. No version info available.
langchain_rag_doc_Faiss: Installed. No version info available.
langchain_rag_doc_chroma: Installed. No version info available.
langchain_rag_json_Faiss: Installed. No version info available.
langchain_rag_pdf_Faiss: Installed. No version info available.
langchain_rag_pdf_chroma: Installed. No version info available.
langchain_rag_textloader_Faiss: Installed. No version info available.
langchain_sqlite: Installed. No version info available.
langchain_sqlite_langsmith: Installed. No version info available.
langchain_sys_SEOtitle_article_generate: Installed. No version info available.
langchain_sys_SEOtitle_article_love: Installed. No version info available.
langchain_sys_SEOtitle_article_post: Installed. No version info available.
langchain_sys_article_loveletter: Installed. No version info available.
langchain_sys_article_novel: Installed. No version info available.
langchain_sys_article_poetry: Installed. No version info available.
langchain_text_splitters: 0.3.4
langchain_tools_YouTube: Installed. No version info available.
langchain_web_Conversation_Faiss: Installed. No version info available.
langchain_web_Conversation_Faiss_langsmith: Installed. No version info available.
langchain_web_Conversation_chroma: Installed. No version info available.
langchain_web_test: Installed. No version info available.
langgraph_sdk: 0.1.48

Optional packages not installed

langserve

Other Dependencies

aiohttp: 3.9.5
async-timeout: 4.0.3
dataclasses-json: 0.6.5
httpx: 0.27.0
httpx-sse: 0.4.0
jsonpatch: 1.33
langsmith-pyo3: Installed. No version info available.
numpy: 1.26.4
ollama: 0.4.5
orjson: 3.10.1
packaging: 23.2
pydantic: 2.10.4
pydantic-settings: 2.7.1
PyYAML: 6.0.1
requests: 2.31.0
requests-toolbelt: 1.0.0
SQLAlchemy: 2.0.29
tenacity: 8.2.3
typing-extensions: 4.12.2