app.py

#ESTABLISH THE SERVER
from flask import Flask,request
from dotenv import load_dotenv

# Initializing flask app
app = Flask(__name__)
load_dotenv()

@app.route("/", methods=['GET','POST'])
def index():   
    from typing import List

    from langchain.prompts import PromptTemplate
    from langchain_core.output_parsers import JsonOutputParser
    from langchain_core.pydantic_v1 import BaseModel, Field
    from langchain_openai import ChatOpenAI
    from langchain_community.tools.convert_to_openai import format_tool_to_openai_function
    from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder


    # Define your desired data structure.
    class FrontEndActions(BaseModel):
        """Structure to pass actions back to the frontend"""
        text: str = Field(description="The text to display on the button")
        type: str = Field(description="This should be a string that identifies the type of action. It can be one of: SuggestGoal, SuggestRiseActivity")

    class ResponseSchema(BaseModel):
        """Final response to the question being asked"""
        message: str = Field(description="final answer to respond to the user")
        #characters: str = Field(description="number of characters in the answer")
        #actions: List[FrontEndActions] = Field(description="List of suggested actions that should be passed back to the frontend to display. The use will click these to enact them. ")
        #tokens: int = Field(description="Count the number of used to produce the response")

    # Set up a parser + inject instructions into the prompt template.
    parser = JsonOutputParser(pydantic_object=ResponseSchema)

    prompt = PromptTemplate(
        template="""Answer the user query.\n{format_instructions}\n{input}\n{agent_scratchpad}""",
        input_variables=["input"],
        partial_variables={"format_instructions": parser.get_format_instructions()}
    )

    print(parser)

    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)

    from langchain.agents import tool

    @tool
    def get_word_length():
        """Returns the length of a word."""
        return 1


    tools = [get_word_length]

    from langchain_openai import ChatOpenAI

    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
    from langchain.agents import create_openai_functions_agent

    agent = create_openai_functions_agent(llm, tools, prompt)

    from langchain.agents import AgentExecutor

    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
    response = agent_executor.invoke({"input": "What are you?"})

    return response['output']