Skip to main content
The 2024 Developer Survey results are live! See the results

All Questions

0 votes
0 answers
36 views

messages with role 'tool' must have a 'tool_call_id'

I wrote a Multi-Agent program based on AutoGen to let 2 agents play chess. But an error is randomly triggered as I execute my program: openai.BadRequestError: Error code: 400 - {'error': {'message': &...
Captain_Lee's user avatar
1 vote
0 answers
42 views

CrewAI tool is caching my response. How do I disable it

I have created a custom tool in CrewAI to request human for information. I created this tool as I found it extremely useful to include human in the loop situations. But I'm facing one issue. Every ...
Rohan Prasad's user avatar
1 vote
0 answers
41 views

why message content is alway empty when I create my own tool with retriever in langchain?

I create a simpler retriever based on docs, after I create a tool and I want to bind it in LLM object, but when I make a question it return empty content. This is the code: llm = ChatOpenAI(...
Enoch's user avatar
  • 23
0 votes
0 answers
19 views

How to set graceful stopping conditions in pyautogen

I have a group chat that seems to work quite well but i am strugglying to stop it gracefully. In particular, with this groupchat: groupchat = GroupChat( agents=[user_proxy, engineer_agent, ...
oettam_oisolliv's user avatar
0 votes
1 answer
68 views

What is the difference of AssistantAgent, ConversableAgent and UserProxyAgent of autogen?

I use the multiple agents from autogen https://microsoft.github.io/autogen/ . There are at least three agents: AssistantAgent, ConversableAgent and UserProxyAgent. What is the difference of ...
ybdesire's user avatar
  • 1,643
0 votes
0 answers
73 views

(this/thought/action/action input/observation can repeat N times) - agent entering infinite loop after giving the answer in terminal

i am doing langchain CSV agent with streamlit , it is working well upon upload of csv file and when question asked , it gives answer while entering agentexecutor chain .. i can see the answer in "...
Nikhita Kanoj's user avatar
0 votes
1 answer
222 views

Flowise chain output of Tool Agent to an LLM Chain

I have an LLM chain which job is to change the style of a passage/sentence. I tested the chain, with the prompt and it works well. Now I want to connect a Tool Agent so that the user receives the tool ...
Muhammad Nizami's user avatar
0 votes
0 answers
29 views

How do I get the destination chains which have been executed based on the input

Output which I get from the bellow code : {'input': '2+2', 'text': 'Sure, I'd be happy to help with that question!\n\nThe question you've asked is "2 + 2."\n\nTo answer this question, we can ...
Jyoti yadav's user avatar
0 votes
0 answers
47 views

Can you use an agent in a Router Chain?

Is it possible to utilize agents within router chains? I recently encountered an article addressing the topic about different chains. Given I have different use cases, each necessitating the ...
Jyoti yadav's user avatar
1 vote
0 answers
356 views

Implementing Router Chains in Langchain Agents

I recently came across this comprehensive guide on using chains in Langchain, and I'm considering incorporating router chains into my Langchain agents to efficiently route inputs to different ...
Jyoti yadav's user avatar
0 votes
0 answers
104 views

How to integrate a `FewShotPromptTemplate` directly `create_pandas_dataframe_agent` from langchain

I'm developing an AI assistant designed for non-data science users to query a dataset. My current approach involves using a FewShotPromptTemplate to translate user queries into data science tasks, ...
Luan Orion Baraúna's user avatar
0 votes
0 answers
498 views

What's the recommended way of function calling in Microsoft Autogen?

I saw that function calling in Autogen is done in several ways. Official tutorials use the register function or user_proxy.register_for_execution methods, while some of the 3rd party tutorials I saw ...
Ranga N's user avatar
  • 27
0 votes
0 answers
875 views

Stop AgentExecutor chain after arriving at the Final answer (in LangChain)

I am using a react agent in Langchain for a chatbot. I want to stop the agent execution once the agent arrives on the Final Answer. The problem is for queries like "What is your name?" the ...
Muhammed Musaddique K's user avatar
1 vote
0 answers
314 views

How to adjust the output format when using the structured chat agent from langchain

I am using a structured chat agent with an openai model to work with my SQL database, querying data using the sql database query tool found in the SQLDatabaseToolKit. I am setting the verbose to true ...
gibri's user avatar
  • 11
0 votes
0 answers
301 views

Langchain agent keyerror: 'agent'

I'm encountering a KeyError: 'agent' when initializing an AgentExecutor object in my Python script. Here's the traceback:, is there any way i could fix this: -------------------------------------------...
Gideon Oboro's user avatar

15 30 50 per page