AtmehEsraa commented 2 months ago

Checked other resources

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

Example Code

from langchain_anthropic import ChatAnthropic from langchain_community.tools.tavily_search import TavilySearchResults from langchain_core.prompts import ChatPromptTemplate from langchain_core.runnables import Runnable, RunnableConfig from langchain_ollama import ChatOllama

class Assistant: def init(self, runnable: Runnable): self.runnable = runnable

def __call__(self, state: State, config: RunnableConfig):
    while True:
        configuration = config.get("configurable", {})
        passenger_id = configuration.get("passenger_id", None)
        state = {**state, "user_info": passenger_id}
        result = self.runnable.invoke(state)
        # If the LLM happens to return an empty response, we will re-prompt it
        # for an actual response.
        if not result.tool_calls and (
            not result.content
            or isinstance(result.content, list)
            and not result.content[0].get("text")
        ):
            messages = state["messages"] + [("user", "Respond with a real output.")]
            state = {**state, "messages": messages}
        else:
            break
    return {"messages": result}

from langchain_openai import ChatOpenAI from langchain_experimental.llms.ollama_functions import OllamaFunctions llm = OllamaFunctions(model="llama3:8b-instruct-fp16", format="json", temperature=0)

primary_assistant_prompt = ChatPromptTemplate.from_messages( [ ( "system", "You are a helpful customer support assistant for Swiss Airlines. " " Use the provided tools to search for flights, company policies, and other information to assist the user's queries. " " When searching, be persistent. Expand your query bounds if the first search returns no results. " " If a search comes up empty, expand your search before giving up." "\n\nCurrent user:\n\n{user_info}\n" "\nCurrent time: {time}.", ), ("placeholder", "{messages}"), ] ).partial(time=datetime.now())

part_1_tools = [ fetch_user_flight_information, search_flights, update_ticket_to_new_flight, cancel_ticket, book_ticket, book_hotel, find_flights

] part_1_assistant_runnable = primary_assistant_prompt | llm.bind_tools(part_1_tools) import shutil import uuid

tutorial_questions = [ "Is my flight from Amsterdam to Oslo on time?" , "Can you tell me the flight status for my trip to Oslo?", "What time is my flight from Amsterdam scheduled to depart?", "When is my flight supposed to arrive in Oslo?", ]

Copy with the backup file so we can restart from the original place in each section

shutil.copy(backup_file, db)

thread_id = str(uuid.uuid4()) configjson = { "configurable": { "passenger_id": "3952 666242", "thread_id": thread_id, "flight_id": 30575, "ticket_no":""

}

_printed = set() for question in tutorial_questions: thread_id = str(uuid.uuid4()) configjson["configurable"]["thread_id"] = thread_id events = part_1_graph.stream( {"messages": ("user", question)}, configjson, stream_mode="values" )

for event in events:
  _print_event(event, _printed)

Error Message and Stack Trace (if applicable)

Description

ValueError: Received unsupported message type for Ollama.

System Info

%pip install git+https://github.com/langchain-ai/langchain.git\#egg=langchain-experimental\&subdirectory=libs/experimental %pip install -U langchain_ollama langgraph==0.1.19 langchain-community langchain-anthropic tavily-python pandas openai langchain_openai !curl -fsSL https://ollama.com/install.sh | sh

ccurme commented 2 months ago

Hello,

I notice you are importing ChatOllama from langchain_ollama, which is correct, but later on import and use OllamaFunctions from langchain_experimental. OllamaFunctions is deprecated and you should be getting warning messages directing you to langchain_ollama.ChatOllama.

Could you please use ChatOllama, and if this does not solve the problem, provide a minimal reproducible example that we can use to debug? This should be a short snippet that someone can copy/paste and immediately run (e.g., any tools necessary to trigger the bug should be defined, and superfluous abstractions should be cut out).