Upload TAD.py (#1)

- Upload TAD.py (2ebbddda40372666ed324a9dbb374b84d6ec87f7)


Co-authored-by: Tharrun S <TheDunkinNinja@users.noreply.huggingface.co>

TAD.py

@@ -0,0 +1,124 @@
+import ollama 
+import chromadb
+import speech_recognition as sr
+import requests 
+import pyttsx3
+
+
+client = chromadb.Client()
+
+message_history = [
+
+    {
+        'id' : 1,
+        'prompt' : 'What is your name?',
+        'response' : 'My name is TADBot,  a bot to help with short term remedial help for mental purposes. '
+
+    },
+
+    {
+        'id' : 2,
+        'prompt' : 'Bye',
+        'response' : 'Good to see you get better. Hopefully you reach out to me if you have any problems.'
+
+    },
+
+    {
+        'id' : 3,
+        'prompt' : 'What is the essence of Life?',
+        'response' : 'The essence of life is to create what you want of yourself.'
+
+    }
+]
+convo = []
+
+modelname = "ms"
+
+
+def create_vector_db(conversations):
+
+    vector_db_name = 'conversations'
+
+    try: 
+        client.delete_collection(vector_db_name)
+    except ValueError as e:
+        pass
+
+    vector_db = client.create_collection(name=vector_db_name)
+    for c in conversations:
+
+        serialized_convo = 'prompt: ' + c["prompt"] + ' response: ' + c["response"]
+
+        response = ollama.embeddings(model = "nomic-embed-text",prompt = serialized_convo)
+        embedding = response["embedding"]
+
+        vector_db.add(ids = [str(c['id'])], embeddings = [embedding], documents = [serialized_convo])
+
+
+def stream_response(prompt):
+    
+    convo.append({'role': "user", 'content': prompt})
+    output = ollama.chat(model = modelname, messages = convo)
+    response = output['message']['content']
+
+    print("TADBot: ") 
+    print(response)
+    engine = pyttsx3.init()
+    engine.say(response)
+    engine.runAndWait()
+
+    convo.append({'role': "assistant", 'content': response})
+
+def retrieve_embeddings(prompt):
+    response = ollama.embeddings(model = "nomic-embed-text", prompt = prompt)
+    propmt_embedding = response['embedding']
+
+    vector_db = client.get_collection(name = 'conversations')
+    results = vector_db.query(query_embeddings=[propmt_embedding], n_results = 1)
+
+    best_embedding = results['documents'][0][0]
+    return best_embedding
+
+create_vector_db(message_history)
+
+
+while True: 
+    
+    r = sr.Recognizer()
+    m = sr.Microphone()
+    
+    try:
+
+
+        print("Say something!")
+        with m as source: 
+            audio = r.listen(source)
+
+
+        try:
+            # for testing purposes, we're just using the default API key
+            # to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
+            # instead of `r.recognize_google(audio)`
+            prompt = r.recognize_google(audio)
+            print("Tadbot thinks you said: " + prompt)
+        except sr.UnknownValueError:
+            print("Tadbot could not understand audio")
+        except sr.RequestError as e:
+            print("Could not request results from Google Speech Recognition service; {0}".format(e))
+
+
+        print("Please wait...")
+        with m as source: 
+            r.adjust_for_ambient_noise(source)
+
+        if  prompt == "bye" or prompt == "Bye": 
+            print("TADBot: Hopefully I was able to help you out today. Have a Nice Day!")
+            break
+        """
+        context = retrieve_embeddings(prompt)
+
+        prompt = prompt + "CONTEXT FROM EMBEDDING: " + context
+        """
+        stream_response(prompt)
+    except KeyboardInterrupt:
+        pass