Update app.py

app.py

@@ -1,107 +1,4 @@
 import gradio as gr
-import openai
-import numpy as np
-import pandas as pd
-import os
-
-# Set your OpenAI API key
-openai.api_key = os.getenv("OPENAI_API_KEY") 
-
-COMPLETIONS_MODEL = "gpt-3.5-turbo-instruct" # "text-davinci-003" used earlier is deprecated.
-# EMBEDDING_MODEL = "text-embedding-3-small" #"text-embedding-ada-002"
-EMBEDDING_MODEL = "text-embedding-3-large"
-
-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,
-}
-
-df = pd.read_csv('services-links.csv')
-df = df.set_index("service")
-
-def get_embedding(text: str, model: str=EMBEDDING_MODEL) -> list[float]:
-    result = openai.Embedding.create(
-      model=model,
-      input=text
-    )
-    return result["data"][0]["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 select_document_section_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[0]
-
-def compute_doc_embeddings(df: pd.DataFrame) -> dict[tuple[str, str], list[float]]:
-    """
-    Create an embedding for each row in the dataframe using the OpenAI Embeddings API.
-    
-    Return a dictionary that maps between each embedding vector and the index of the row that it corresponds to.
-    """
-    return {
-        idx: get_embedding(r.description) for idx, r in df.iterrows()
-    }
-
-document_embeddings = compute_doc_embeddings(df)
-
-def construct_prompt(question: str, context_embeddings: dict, df: pd.DataFrame) -> str:
-    """
-    Fetch relevant 
-    """
-    _ , chosen_service = select_document_section_by_query_similarity(question, context_embeddings)
-        
-    service_description = df.loc[chosen_service].description.replace("\n", " ")
-    header = "Answer the question as truthfully as possible using the provided context, and if the answer is not contained within the text below, say "
-    message = "I could not find an answer to your question, please reach out to Helpdesk."
-    link = df.loc[chosen_service].link
-    return header + message + "\n* " + "\n\nContext:\n" + service_description + "\n\n Q: " + question + "\n A:", link
-
-def answer_query_with_context(
-    query: str,
-    df: pd.DataFrame,
-    document_embeddings: dict[(str, str), np.array],
-    show_prompt: bool = False
-) -> str:
-    prompt, link = construct_prompt(
-        query,
-        document_embeddings,
-        df
-    )
-    
-    if show_prompt:
-        print(prompt)
-
-    response = openai.Completion.create(
-                prompt=prompt,
-                **COMPLETIONS_API_PARAMS
-            )
-    
-    end_message = "\n\nPlease check out the relevant HMC service catalogue for more details: "+ link 
-    end_message += """\n\nIf not satisfied with the answer, please email helpdesk@hmc.edu, call 909.607.7777 or visit the Helpdesk located on the Sprague first floor. """
-    end_message += """Helpdesk representatives are also available for a remote chat session during normal hours on Monday - Friday, 8:00 AM - 5:00 PM PST via https://helpdesk.hmc.edu"""
-    
-    reply = response["choices"][0]["text"] + end_message
-
-    return reply
 
 def chatbot(input):
     try: