Spaces:
Running
Running
File size: 3,170 Bytes
a957f06 1a7f63c 082f753 1a7f63c 9611b40 1a7f63c e7857bc 1a7f63c 8ca89d6 1a7f63c 8ca89d6 1a7f63c 27f8d96 1a7f63c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 |
import sklearn
import sqlite3
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity
import openai
import os
openai.api_key = os.environ["Secret"]
def find_closest_neighbors(vector1, dictionary_of_vectors):
"""
Takes a vector and a dictionary of vectors and returns the three closest neighbors
"""
# Convert the input string to a vector
vector = openai.Embedding.create(
input=vector1,
engine="text-embedding-ada-002"
)['data'][0]['embedding']
vector = np.array(vector)
# Finds cosine similarities between the vector and values in the dictionary and Creates a dictionary of cosine similarities with its text key
cosine_similarities = {}
for key, value in dictionary_of_vectors.items():
cosine_similarities[key] = cosine_similarity(vector.reshape(1, -1), value.reshape(1, -1))[0][0]
# Sorts the dictionary by value and returns the three highest values
sorted_cosine_similarities = sorted(cosine_similarities.items(), key=lambda x: x[1], reverse=True)
match_list = sorted_cosine_similarities[0:4]
web = str(sorted_cosine_similarities[0][0])
return match_list
# Connect to the database
conn = sqlite3.connect('QRIdatabase.db')
# Create a cursor
cursor = conn.cursor()
# Select the text and embedding from the chunks table
cursor.execute('''SELECT text, embedding FROM chunks''')
# Fetch the rows
rows = cursor.fetchall()
# Create a dictionary to store the text and embedding for each row
dictionary_of_vectors = {}
# Iterate through the rows and add them to the dictionary
for row in rows:
text = row[0]
embedding_str = row[1]
# Convert the embedding string to a NumPy array
embedding = np.fromstring(embedding_str, sep=' ')
dictionary_of_vectors[text] = embedding
# Close the connection
conn.close()
def context_gpt_response(question):
"""
Takes a question and returns an answer
"""
# Find the closest neighbors
match_list = find_closest_neighbors(question, dictionary_of_vectors)
# Create a string of the text from the closest neighbors
context = ''
for match in match_list:
context += str(match[0])
prep = f"This is an OpenAI model tuned to answer questions specific to the Qualia Research institute, a research institute that focuses on consciousness. Here is some question-specific context, and then the Question to answer, related to consciousness, the human experience, and phenomenology: {context}. Here is a question specific to QRI and consciousness in general Q: {question} A: "
# Generate an answer
response = openai.Completion.create(
engine="text-davinci-003",
prompt=prep,
temperature=0.7,
max_tokens=150,
)
# Return the answer
return response['choices'][0]['text']
import gradio as gr
iface = gr.Interface(fn=context_gpt_response, inputs="text", outputs="text",title="Qualia Research Institute GPTbot", description="Ask any question and get QRI specific answers!", examples=[["What is QRI?"], ["What is the Symmetry Theory of Valence?"], ["Explain Logarithmic scales of pain and pleasure"]])
iface.launch()
|