john-adeojo

Given the fields `question`, produce the fields `answer`.

---

Follow the following format.

Question: ${question}
Answer: ${answer}

---

john-adeojo

Given the fields `question`, produce the fields `answer`.

---

Follow the following format.

Question: ${question}
Answer: ${answer}

---

john-adeojo

Given the fields `question`, produce the fields `answer`.

---

Follow the following format.

Question: ${question}
Answer: ${answer}

---

john-adeojo

Given the fields `question`, produce the fields `answer`.

---

Follow the following format.

Question: ${question}
Answer: ${answer}

---

john-adeojo

Solve a question answering task with interleaving Thought, Action, Observation steps. Thought can reason about the current
situation, and Action can be three types:
2 (1) Search[entity], which searches the exact entity on Wikipedia and returns the first paragraph if it exists. If not, it
will return some similar entities to search.
3 (2) Lookup[keyword], which returns the next sentence containing keyword in the current passage.
4 (3) Finish[answer], which returns the answer and finishes the task.
5 Here are some examples.
6 Question: What is the elevation range for the area that the eastern sector of the Colorado orogeny extends into?
7 Action 1: Search[Colorado orogeny]
8 Observation 1: The Colorado orogeny was an episode of mountain building (an orogeny) in Colorado and surrounding areas.

john-adeojo

prompt = '''
Sentence 1: "The church choir sings to the masses as they sing joyous songs from the book at a church."
Sentence 2: "The church has cracks in the ceiling."
'''

john-adeojo

context = '''
Task: For each pair of sentences below, determine the relationship between them. Label them as:

0 (entailment) if the second sentence is a logical outcome or directly inferred from the first.
1 (neutral) if the second sentence is neither entailed nor contradicted by the first; it's just additional information.
2 (contradiction) if the second sentence contradicts or opposes the information in the first.
Example 1:

Sentence 1: "The cat sat on the mat."
Sentence 2: "The mat has a cat on it."

john-adeojo

def generate_response(prompt, context):
    openai.api_key = API_KEY
    
    content = "You are a text classification model"
    
    response = openai.ChatCompletion.create(
        model="gpt-3.5-turbo",
        messages=[
            {"role": "system", "content": content},
            {"role": "user", "content": f"Context: {context}. {prompt}"}

john-adeojo

from haystack import Pipeline
from function_call import OpenAIFunctionCall

def create_pipeline(retriever, API_KEY):
    p = Pipeline()
    p.add_node(component=retriever, name="retriever", inputs=["Query"])
    p.add_node(component=OpenAIFunctionCall(API_KEY), name="OpenAIFunctionCall", inputs=["retriever"])
    return p

john-adeojo

import openai
from haystack.nodes.base import BaseComponent
from typing import List
import json

class OpenAIFunctionCall(BaseComponent):
    outgoing_edges = 1
    def __init__(self, API_KEY):
        self.API_KEY = API_KEY