Create app.py

app.py

@@ -0,0 +1,85 @@
+
+import sqlite3
+import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
+import openai
+
+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])  
+
+    # Generate an answer
+    response = openai.Completion.create(
+        engine="text-davinci-003",
+        prompt=context + question,
+        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")
+iface.launch()
+