AttributeError: 'RunnableSequence' object has no attribute 'run'

[humanely]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain.prompts import PromptTemplate
from langchain_ollama import ChatOllama

llm = ChatOllama(model="codellama:70b", temperature=0.5)

template = """<s>[INST] <<SYS>> {system_prompt} <</SYS>> {task_message} <<SYS>> {instruction_message} <</SYS>> [/INST] {model_answer_1} </s> <s>[INST] {user_message_2} [/INST]

prompt = PromptTemplate(
            input_variables=["system_prompt", "task_message","instruction_message","model_answer_1","user_message_2"],
            template=template
     )

chain = prompt | llm | SimpleJsonOutputParser()


system_prompt = f"You are a helpful AI assistant skilled in {codelang} programming."

task_message = f"Can you help me improve this code as per the following instruction?\n\n{resObj} "
instruction_message = f"The instruction is as follows: \n\n{ReadyPrompt} "
model_answer_1 = "Certainly! I'd be happy to help improve your code. Let me analyze it for you. "
user_message_2 = "Please provide the improved code. Return your response in JSON format with a single key 'code' containing the improved code as a string. "



response = chain.run(
                                    system_prompt=system_prompt,
                                    task_message=task_message,
                                    instruction_message=instruction_message,
                                    model_answer_1=model_answer_1,
                                    user_message_2=user_message_2
                                )

Description

The code doesn't run: AttributeError: 'RunnableSequence' object has no attribute 'run'

System Info

langchain==0.2.8
langchain-community==0.2.7
langchain-core==0.2.34
langchain-ollama==0.1.1
langchain-text-splitters==0.2.2

[dosubot[bot]]

To fix the AttributeError: 'RunnableSequence' object has no attribute 'run' in your LangChain code, you should use the invoke method instead of run. The RunnableSequence class does not have a run method, but it does have an invoke method for executing the sequence.

Here is how you can modify your code:

from langchain.prompts import PromptTemplate
from langchain_ollama import ChatOllama
from langchain_core.output_parsers import SimpleJsonOutputParser

llm = ChatOllama(model="codellama:70b", temperature=0.5)

template = """<s>[INST] <<SYS>> {system_prompt} <</SYS>> {task_message} <<SYS>> {instruction_message} <</SYS>> [/INST] {model_answer_1} </s> <s>[INST] {user_message_2} [/INST]"""

prompt = PromptTemplate(
    input_variables=["system_prompt", "task_message", "instruction_message", "model_answer_1", "user_message_2"],
    template=template
)

chain = prompt | llm | SimpleJsonOutputParser()

system_prompt = f"You are a helpful AI assistant skilled in {codelang} programming."
task_message = f"Can you help me improve this code as per the following instruction?\n\n{resObj} "
instruction_message = f"The instruction is as follows: \n\n{ReadyPrompt} "
model_answer_1 = "Certainly! I'd be happy to help improve your code. Let me analyze it for you. "
user_message_2 = "Please provide the improved code. Return your response in JSON format with a single key 'code' containing the improved code as a string. "

response = chain.invoke(
    {
        "system_prompt": system_prompt,
        "task_message": task_message,
        "instruction_message": instruction_message,
        "model_answer_1": model_answer_1,
        "user_message_2": user_message_2
    }
)

print(response)

Make sure to replace any calls to run with invoke in your code ^[1].

To continue talking to Dosu, mention @dosu.