app.py

import os
import numpy as np
import openai
import pandas as pd
import tiktoken
import gradio as gr

COMPLETIONS_MODEL = "text-davinci-003"
EMBEDDING_MODEL = "text-embedding-ada-002"

openai.api_key = os.getenv("OPENAI_API_KEY")

# 1) Preprocess the document library
df = pd.read_csv("olympics_sections_text.csv")
df = df.set_index(["title", "heading"])

def get_embedding(text: str, model: str=EMBEDDING_MODEL) -> list[float]:
    result = openai.Embedding.create(
      model=model,
      input=text
    )
    return result["data"][0]["embedding"]

# uncomment the below line to caculate embeddings from scratch. ========

#def compute_doc_embeddings(df: pd.DataFrame) -> dict[tuple[str, str], list[float]]:
#    return {
#        idx: get_embedding(r.content) for idx, r in df.iterrows()
#    }

#document_embeddings = compute_doc_embeddings(df)

def load_embeddings(fname: str) -> dict[tuple[str, str], list[float]]:
    """
    Read the document embeddings and their keys from a CSV.
    
    fname is the path to a CSV with exactly these named columns: 
        "title", "heading", "0", "1", ... up to the length of the embedding vectors.
    """
    
    df = pd.read_csv(fname, header=0)
    max_dim = max([int(c) for c in df.columns if c != "title" and c != "heading"])
    return {
           (r.title, r.heading): [r[str(i)] for i in range(max_dim + 1)] for _, r in df.iterrows()
    }

document_embeddings = load_embeddings("olympics_sections_document_embeddings.csv")

# 2) Find the most similar document embeddings to the question embedding

def vector_similarity(x: list[float], y: list[float]) -> float:
    """
    Returns the similarity between two vectors.
    
    Because OpenAI Embeddings are normalized to length 1, the cosine similarity is the same as the dot product.
    """
    return np.dot(np.array(x), np.array(y))

def order_document_sections_by_query_similarity(query: str, contexts: dict[(str, str), np.array]) -> list[(float, (str, str))]:
    """
    Find the query embedding for the supplied query, and compare it against all of the pre-calculated document embeddings
    to find the most relevant sections. 
    
    Return the list of document sections, sorted by relevance in descending order.
    """
    query_embedding = get_embedding(query)
    
    document_similarities = sorted([
        (vector_similarity(query_embedding, doc_embedding), doc_index) for doc_index, doc_embedding in contexts.items()
    ], reverse=True)
    
    return document_similarities

# 3) Add the most relevant document sections to the query prompt

MAX_SECTION_LEN = 500
SEPARATOR = "\n* "
ENCODING = "gpt2"  # encoding for text-davinci-003

encoding = tiktoken.get_encoding(ENCODING)
separator_len = len(encoding.encode(SEPARATOR))

def construct_prompt(question: str, context_embeddings: dict, df: pd.DataFrame) -> str:
    """
    Fetch relevant 
    """
    most_relevant_document_sections = order_document_sections_by_query_similarity(question, context_embeddings)
    
    chosen_sections = []
    chosen_sections_len = 0
    chosen_sections_indexes = []
     
    for _, section_index in most_relevant_document_sections:
        # Add contexts until we run out of space.        
        document_section = df.loc[section_index]
        
        chosen_sections_len += document_section.tokens + separator_len
        if chosen_sections_len > MAX_SECTION_LEN:
            break
            
        chosen_sections.append(SEPARATOR + document_section.content.replace("\n", " "))
        chosen_sections_indexes.append(str(section_index))
    
    header = """Answer the question as truthfully as possible using the provided context, and if the answer is not contained within the text below, say "I don't know."\n\nContext:\n"""
    
    return header + "".join(chosen_sections) + "\n\n Q: " + question + "\n A:"

prompt = construct_prompt(
    "Who won the 2020 Summer Olympics men's high jump?",
    document_embeddings,
    df
)

# 4) Answer the user's question based on the context.

COMPLETIONS_API_PARAMS = {
    # We use temperature of 0.0 because it gives the most predictable, factual answer.
    "temperature": 0.0,
    "max_tokens": 300,
    "model": COMPLETIONS_MODEL,
}

def answer_query_with_context(
    query: str,
    df: pd.DataFrame,
    document_embeddings: dict[(str, str), np.array]
) -> str:
    prompt = construct_prompt(
        query,
        document_embeddings,
        df
    )

    response = openai.Completion.create(
                prompt=prompt,
                **COMPLETIONS_API_PARAMS
            )

    return response["choices"][0]["text"].strip(" \n")

def answer_question(query):
    return answer_query_with_context(query, df, document_embeddings)

iface = gr.Interface(fn=answer_question, inputs="text", outputs="text")
iface.launch()