# Create\_react\_agent.invoke throwing error

**URL:** <https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653>\
**Category:** LangGraph\
**Tags:** python-help\
**Created:** [July 23, 2025, 10:15am UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653 "2025-07-23T10:15:04Z")\
**Posts on this page:** 10\
**Page:** 1

<div class="post-metadata">

**Author:** ![ibrahim](https://avatars.discourse-cdn.com/v4/letter/i/43a26b/32.png) [@ibrahim](https://forum.langchain.com/u/ibrahim)\
**Post date:** [July 23, 2025, 10:15am UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/1 "2025-07-23T10:15:04Z")

</div>

Here’s my code -  
react\_prompt = hub.pull(“hwchase17/react”)  
react\_agent = create\_react\_agent(model=chat, tools=execute\_tools, prompt=react\_prompt)  
response = react\_agent.invoke({“input”: “What is 5+3?”})

What I would like to know is that do I need to call .partial on the prompt to fill in the values for tools and tool\_names because I am getting the error below. My understanding was the create\_react\_agent takes care of this internally.

KeyError: "Input to PromptTemplate is missing variables {‘input’, ‘tools’, ‘tool\_names’, ‘agent\_scratchpad’}. Expected: [‘agent\_scratchpad’, ‘input’, ‘tool\_names’, ‘tools’] Received: [‘messages’, ‘is\_last\_step’, ‘remaining\_steps’]\nNote: if you intended {input} to be part of the string and not a variable, please escape it with double curly braces like: ‘{{input}}’.\nFor troubleshooting, visit: [INVALID\_PROMPT\_INPUT | 🦜️🔗 LangChain](https://python.langchain.com/docs/troubleshooting/errors/INVALID_PROMPT_INPUT) "

---

<div class="post-metadata">

**Author:** ![niilooy](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/niilooy/32/2886_2.png) [@niilooy](https://forum.langchain.com/u/niilooy)\
**Post date:** [July 23, 2025, 12:05pm UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/2 "2025-07-23T12:05:31Z")

</div>

You don’t need to call .partial() on the prompt, your understanding is correct.

I think you’re using ChatOpenAI with create\_react\_agent, but the prompt is designed for completion models. Just replace it with OpenAI and it should work!

```auto
from langchain_openai import OpenAI 
#...
model = OpenAI()

react_prompt = hub.pull("hwchase17/react")
react_agent = create_react_agent(llm=model, tools=execute_tools, prompt=react_prompt)

# Wrap in AgentExecutor
agent_executor = AgentExecutor(agent=react_agent, tools=execute_tools, verbose=True)

response = agent_executor.invoke({"input": "What is 5+3?"})

```

---

<div class="post-metadata">

**Author:** ![ibrahim](https://avatars.discourse-cdn.com/v4/letter/i/43a26b/32.png) [@ibrahim](https://forum.langchain.com/u/ibrahim)\
**Post date:** [July 23, 2025, 5:06pm UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/3 "2025-07-23T17:06:06Z")

</div>

Thanks, @niilooy. We are using two different create\_react\_agent - you are using the one from LangChain and I am using the one from LangGraph. The one from LangChain works ok (with ChatOpenAI) while the one from LangGraph is giving me missing variable issues. See if you can try it yourself. I may have missed something here…

---

<div class="post-metadata">

**Author:** ![niilooy](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/niilooy/32/2886_2.png) [@niilooy](https://forum.langchain.com/u/niilooy)\
**Post date:** [July 23, 2025, 5:54pm UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/4 "2025-07-23T17:54:14Z")

</div>

Hey @ibrahim, thanks for clarifying that you are using the LangGraph implementation. In that case use this. This is way cleaner and the prompt is built in as well!

```auto
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

model = ChatOpenAI()

#...

agent_executor = create_react_agent(model, execute_tools)

# Invoke with messages format
response = agent_executor.invoke({"messages": [("user", "What is 5+3?")]})

```

---

<div class="post-metadata">

**Author:** ![ibrahim](https://avatars.discourse-cdn.com/v4/letter/i/43a26b/32.png) [@ibrahim](https://forum.langchain.com/u/ibrahim)\
**Post date:** [July 24, 2025, 4:31am UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/5 "2025-07-24T04:31:02Z")

</div>

@niilooy, I tried…and it worked. Thank you! Now, my next question is that if I were to pass the prompt, it throws the error. So how should we handle prompts? Thanks again for all the help.

---

<div class="post-metadata">

**Author:** ![niilooy](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/niilooy/32/2886_2.png) [@niilooy](https://forum.langchain.com/u/niilooy)\
**Post date:** [July 24, 2025, 6:51am UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/6 "2025-07-24T06:51:45Z")

</div>

In LangGraph, you cannot inject the “hwchase17/react” prompt when using `ChatOpenAI`. That prompt is incompatible with chat models. You can structure your prompt something like this to start:

```auto
system_prompt = """You are a helpful math assistant that can perform calculations.

You have access to the following tool:

<tool>
<name>calculator</name>
<description>Performs basic mathematical calculations including arithmetic, trigonometry, and common math functions.</description>
<parameters>
<parameter name="expression" type="string" required>Mathematical expression to evaluate (e.g., "2+3", "10*5", "sqrt(16)", "sin(30)")</parameter>
</parameters>
</tool>

.
.
.
(Rest of your instructions...)
"""

```

You can now pass your defined prompt and tools inside the create\_react\_agent function within the “prompt” and “tools” parameters!

---

<div class="post-metadata">

**Author:** ![ibrahim](https://avatars.discourse-cdn.com/v4/letter/i/43a26b/32.png) [@ibrahim](https://forum.langchain.com/u/ibrahim)\
**Post date:** [July 24, 2025, 8:20am UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/7 "2025-07-24T08:20:05Z")

</div>

Thanks, @niilooy . Will play with it and get back to you if I need help. Much appreciated!

---

<div class="post-metadata">

**Author:** ![ibrahim](https://avatars.discourse-cdn.com/v4/letter/i/43a26b/32.png) [@ibrahim](https://forum.langchain.com/u/ibrahim)\
**Post date:** [July 24, 2025, 4:19pm UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/8 "2025-07-24T16:19:35Z")

</div>

@niilooy , quick question - is there a way to see the Thought/Action/Observation the way a langchain ZERO\_SHOT\_REACT\_AGENT would display after each step. I am seeing pieces of it using stream…but not something like what was displayed with the former…is there a way to print it out after each step. I just feel that my results have gotten worse after I moved to LangGraph. The logic hasn’t changed but the LLM is not taking the correct actions as it would earlier (feels like it’s not thinking as well as it would earlier). Want to see the thought/action/observation to see what might be issue…thanks.

---

<div class="post-metadata">

**Author:** ![niilooy](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/niilooy/32/2886_2.png) [@niilooy](https://forum.langchain.com/u/niilooy)\
**Post date:** [July 25, 2025, 3:43pm UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/9 "2025-07-25T15:43:37Z")

</div>

Hey @ibrahim. You can add some instructions to your prompt to follow a Thought/Action/Observation pattern, and then replace your .invoke with a streaming function and incorporate that. You can try something like this:

```auto
Example prompt instructions to add
"""
...

For each user question, follow this pattern:
1. **Thought** : Think about what needs to be calculated
2. **Action** : Use the calculator tool with the appropriate expression  
3. **Observation** : Note the result from the tool
4. **Thought** : Reflect on whether this answers the question or if more steps are needed
...
"""

```

Example function for streaming

```auto
def print_steps(question: str):
    """Print each step of the ReAct process"""
    print(f"\n{'='*60}")
    print(f"QUESTION: {question}")
    print(f"{'='*60}")
    
    step_count = 0
    
    # Stream the agent's response
    for chunk in agent.stream({"messages": [HumanMessage(content=question)]}):
        for node_name, node_data in chunk.items():
            if node_name == "agent":
                step_count += 1
                messages = node_data.get("messages", [])
                
                for message in messages:
                    if isinstance(message, AIMessage):
                        print(f"\n--- STEP {step_count}: AGENT REASONING ---")
                        print(f"Content: {message.content}")
                        
                        # Check if there are tool calls
                        if hasattr(message, 'tool_calls') and message.tool_calls:
                            for tool_call in message.tool_calls:
                                print(f"Tool Call: {tool_call['name']}")
                                print(f"Arguments: {tool_call['args']}")
                    
                    elif isinstance(message, ToolMessage):
                        print(f"\n--- TOOL OBSERVATION ---")
                        print(f"Tool: {message.name}")
                        print(f"Result: {message.content}")
            
            elif node_name == "tools":
                # This shows tool execution
                pass
    
    print(f"\n{'='*60}")

```

Hope this’ll work! ✨

---

<div class="post-metadata">

**Author:** ![ibrahim](https://avatars.discourse-cdn.com/v4/letter/i/43a26b/32.png) [@ibrahim](https://forum.langchain.com/u/ibrahim)\
**Post date:** [July 28, 2025, 6:12am UTC](https://forum.langchain.com/t/create-react-agent-invoke-throwing-error/653/10 "2025-07-28T06:12:42Z")

</div>

Thanks, @niilooy.