Create app.py

app.py

@@ -0,0 +1,89 @@
+import openai
+import gradio as gr
+import sqlite3
+import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
+
+openai.api_key = "sk-..."  # Replace with your key
+
+def find_closest_neighbors(vector, dictionary_of_vectors):
+    """
+    Takes a vector and a dictionary of vectors and returns the three closest neighbors
+    """
+    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]
+
+    sorted_cosine_similarities = sorted(cosine_similarities.items(), key=lambda x: x[1], reverse=True)
+    match_list = sorted_cosine_similarities[0:4]
+
+    return match_list
+
+def handle_input(user_input):
+    """
+    Checks if the user input is a text file or a string.
+    If it's a text file, it reads the file, splits it into 250-character chunks, and returns the chunks.
+    If it's a string, it just returns the string.
+    """
+    if isinstance(user_input, gr.inputs.File):
+        with open(user_input.name, 'r') as file:
+            text = file.read()
+        chunks = [text[i:i+250] for i in range(0, len(text), 250)]
+        return chunks
+    else:
+        return [user_input]
+
+def predict(user_input, history):
+    # Connect to the database
+    conn = sqlite3.connect('QRIdatabase7 (1).db')
+    cursor = conn.cursor()
+    cursor.execute('''SELECT text, embedding FROM chunks''')
+    rows = cursor.fetchall()
+
+    dictionary_of_vectors = {}
+    for row in rows:
+        text = row[0]
+        embedding_str = row[1]
+        embedding = np.fromstring(embedding_str, sep=' ')
+        dictionary_of_vectors[text] = embedding
+    conn.close()
+
+    input_chunks = handle_input(user_input)
+
+    for message in input_chunks:
+        # Create embedding for the message
+        message_vector = openai.Embedding.create(
+            input=message,
+            engine="text-embedding-ada-002"
+        )['data'][0]['embedding']
+        message_vector = np.array(message_vector)
+        
+        # Find the closest neighbors
+        match_list = find_closest_neighbors(message_vector, dictionary_of_vectors)
+        context = ''
+        for match in match_list:
+            context += str(match[0])
+        context = context[:-1500]
+
+        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:  {message}  A: "
+
+        history_openai_format = []
+        for human, assistant in history:
+            history_openai_format.append({"role": "user", "content": human })
+            history_openai_format.append({"role": "assistant", "content":assistant})
+        history_openai_format.append({"role": "user", "content": prep})
+
+        response = openai.ChatCompletion.create(
+            model='gpt-4',
+            messages= history_openai_format,         
+            temperature=1.0,
+            stream=True
+        )
+        
+        partial_message = ""
+        for chunk in response:
+            if len(chunk['choices'][0]['delta']) != 0:
+                partial_message = partial_message + chunk['choices'][0]['delta']['content']
+                yield partial_message 
+
+gr.ChatInterface(predict, inputs=gr.inputs.Mixed([gr.inputs.Textbox(lines=3), gr.inputs.File()]), allow_flagging=False).queue().launch()