Error adding and searching short_term and entities memory

CrewAI Community Support
,
1

Hi, I am trying to use the crewai’s in-built memory feature but it is giving me an error while adding and searching.

Crewai version: 0.86.0
OS: Windows 11
pyhton: 3.12.6

    @crew
def crew(self) -> Crew:
    return Crew(
        agents=self.agents,
        tasks=self.tasks,
        manager_llm=LLM(temperature=0, model="claude-3-haiku-20240307"),
        process=Process.hierarchical,
        memory=True,
        verbose=True
    )

ERROR:root:Error during short_term save: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'
ERROR:root:Error during entities save: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'
ERROR:root:Error during entities save: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'
ERROR:root:Error during entities save: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body' 

ERROR:root:Error during short_term search: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'
ERROR:root:Error during entities search: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'
Error with Memory Feature Local LLM (LM Studio: phi-4)
2

Can you share more of your code? Also if you could add the full error message.

3

Kindly find my code for the tasks below.

import os

from crewai import Agent,Crew,Process,Task,LLM
from crewai.project import CrewBase, agent, crew, task

from src.types import Summaries, ActionItems, FollowUps, Ideas

@CrewBase
class Insights:

    agents_config = 'config/agents.yaml'
    tasks_config = 'config/tasks.yaml'

    @agent
    def meeting_summarizer(self) -> Agent:
        return Agent(
            config=self.agents_config['meeting_summarizer'],
            verbose=True
        )

    @agent
    def meeting_note_taker(self ) -> Agent:
        return Agent(
            config=self.agents_config['meeting_note_taker'],
            verbose=True
        )

    @agent
    def meeting_analyzer(self ) -> Agent:
        return Agent(
            config=self.agents_config['meeting_analyzer'],
            verbose=True,
        )

    @agent
    def meeting_follower(self ) -> Agent:
        return Agent(
            config=self.agents_config['meeting_follower'],
            verbose=True
        )

    @agent
    def meeting_ideas(self) -> Agent:
        return Agent(
            config=self.agents_config['meeting_ideas'],
            verbose=True
        )

    @task
    def summarize_meeting(self) -> Task:
        return Task(
            config=self.tasks_config['summarize_meeting'],
            output_json=Summaries,
            #async_execution=True,
        )

    @task
    def analyze_notes(self) -> Task:
        return Task(
            config=self.tasks_config['analyze_notes'],
            #async_execution=True
        )

    @task
    def analyze_action_items(self) -> Task:
        return Task(
            config=self.tasks_config['analyze_action_items'],
            output_json=ActionItems,
            #async_execution=True
        )

    @task
    def analyze_followup(self) -> Task:
        return Task(
            config=self.tasks_config['analyze_followup'],
            output_json=FollowUps,
            #async_execution=True
        )

    @task
    def analyze_ideas(self) -> Task:
        return Task(
            config=self.tasks_config['analyze_ideas'],
            output_json=Ideas,
        )

    @crew
    def crew(self) -> Crew:
        return Crew(
            agents=self.agents,
            tasks=self.tasks,
            manager_llm=LLM(temperature=0, model="claude-3-haiku-20240307"),
            process=Process.hierarchical,
            memory=True,
            verbose=True
        )

I do not get any more errors. I receive below before a task starts

    ERROR:root:Error during short_term search: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'
    ERROR:root:Error during entities search: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'

I receive below after a task has completed

ERROR:root:Error during short_term save: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'
ERROR:root:Error during entities save: APIStatusError.__init__() missing 2 required keyword-only arguments: 'response' and 'body'
4

This issue has been reported in the Github as well. I tried with the latest version 0.95.0 but it made no difference.

5

I have successfully resolved the issue I was encountering.

The resolution involved adding credits to my OpenAI account. Following this, both short-term and entity memory functionalities began to operate as expected.

I was aware Crewai memory, by default, used OpenAI embeddings. However, the documentation did not explicitly state the requirement of OpenAI credits for the memory feature to function correctly.

I am now able to observe data being populated within both my entity and short-term memory.

It would be beneficial if Crewai could return a low credit error more explicitly when this is the root cause of an issue.

1 Like
6

Really good idea on returning the exception error. Will relay.

2 Likes
7

This topic was automatically closed 24 hours after the last reply. New replies are no longer allowed.