Expected mapping type as input to PromptTemplate. Received <class 'str'>. Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...

[shobhitagnihotri69]

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.chains import SequentialChain , SimpleSequentialChain
prompt_1 = PromptTemplate.from_template("""You are a assistant to help write story from given topic {'question'}, Your answer :""")
prompt_2 = PromptTemplate.from_template("""You are an expert translater , Translate the given story in indian languages """)
chain = {"answer" : prompt_1 | model | StrOutputParser} | prompt_2 | model | StrOutputParser
chain.invoke(' writa a mexican drink ')
I AM WRITING THIS CODE AND I AM FACING THIS ISSUE AGAN AND AGAIN
Expected mapping type as input to PromptTemplate. Received <class 'str'>.
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...

Description

I am using langchain from 4 months , I am facing this problem for chaining prompt template and chain.invoke requierement

System Info

M1 MacBook

[dosubot[bot]]

Hey there @shobhitagnihotri69! Great to see you diving into some exciting challenges with LangChain again. How's the coding journey been treating you since our last adventure? 🚀😄

The error you're encountering, "Expected mapping type as input to PromptTemplate. Received <class 'str'>", is due to the fact that the invoke method of the BasePromptTemplate class expects its input to be a dictionary (Dict), but it received a string (str) instead. This is evident from the _format_prompt_with_error_handling method within the BasePromptTemplate class, which checks the type of inner_input and raises a TypeError if it is not a dictionary. This method is called by invoke, which passes the input argument to it.

Here's the relevant part of the code that checks the input type:

def _format_prompt_with_error_handling(self, inner_input: Dict) -> PromptValue:
    if not isinstance(inner_input, dict):
        if len(self.input_variables) == 1:
            var_name = self.input_variables[0]
            inner_input = {var_name: inner_input}
        else:
            raise TypeError(
                f"Expected mapping type as input to {self.__class__.__name__}. "
                f"Received {type(inner_input)}."
            )

To resolve this error, ensure that when you call the invoke method on an instance of a class derived from BasePromptTemplate, you pass a dictionary with the expected keys and values as defined by the input_variables and input_types of your prompt template, rather than passing a string or any other non-dictionary type.

Regarding your question about chaining multiple PromptTemplates in LangChain, you can use the PipelinePromptTemplate class. Here is an example of how to chain multiple PromptTemplates:

from langchain_core.prompts.base import BasePromptTemplate
from langchain_core.prompts.pipeline import PipelinePromptTemplate

# Define your custom PromptTemplates
class FirstPromptTemplate(BasePromptTemplate):
    # Implementation of the first prompt template

class SecondPromptTemplate(BasePromptTemplate):
    # Implementation of the second prompt template

# Create instances of your custom PromptTemplates
first_prompt = FirstPromptTemplate(...)
second_prompt = SecondPromptTemplate(...)

# Define the final prompt template, which will use the outputs of the previous templates
final_prompt = SomeOtherPromptTemplate(...)

# Create the PipelinePromptTemplate
pipeline_prompt = PipelinePromptTemplate(
    final_prompt=final_prompt,
    pipeline_prompts=[
        ("first_output", first_prompt),
        ("second_output", second_prompt),
    ]
)

# Use the pipeline prompt
formatted_prompt = pipeline_prompt.format(**input_variables)

In this example, FirstPromptTemplate and SecondPromptTemplate are custom prompt templates you would have defined elsewhere. SomeOtherPromptTemplate is the final prompt template that uses the outputs of the first two prompts. The outputs of first_prompt and second_prompt are passed to subsequent templates and the final prompt as first_output and second_output, respectively. You would replace ... with actual implementations and configurations for your prompt templates.

I hope this helps! If you have any other questions, feel free to ask.

Sources

• libs/core/langchain_core/prompts/base.py
• libs/core/langchain_core/prompts/prompt.py
• libs/core/langchain_core/prompts/pipeline.py

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.