llm data now streams in

app.py

@@ -6,9 +6,11 @@ from openai import OpenAI
 
 # CONSTANTS
 client = chromadb.PersistentClient(path="./chromadb_linux/")
-MODEL_NAME: str = "mixedbread-ai/mxbai-embed-large-v1" # ~ 0.5 gb
+MODEL_NAME: str = "mixedbread-ai/mxbai-embed-large-v1"  # ~ 0.5 gb
 COLLECTION_NAME: str = "scheme"
-EMBEDDING_FUNC = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=MODEL_NAME)
+EMBEDDING_FUNC = embedding_functions.SentenceTransformerEmbeddingFunction(
+    model_name=MODEL_NAME
+)
 schemer = client.get_collection(
     name=COLLECTION_NAME,
     embedding_function=EMBEDDING_FUNC,
@@ -17,11 +19,15 @@ DATA_AVAL: bool = schemer.count() > 0
 APP_NAME: str = "Groove-GPT"
 history = []
 
-# INFO 
+# INFO
 st.title(APP_NAME)
 st.header("What is Groovy-GPT?")
-st.write("Groovy-GPT is a RAG (Retrieval-Augmented Generation) model that uses ChromaDB to retrieve relevant documents and then uses OpenAI's models to generate a response.")
-st.write("The model is trained on the MIT Scheme textbook and a handful of Discrete Math and Paradigms related content that Professor Troeger posted")
+st.write(
+    "Groovy-GPT is a RAG (Retrieval-Augmented Generation) model that uses ChromaDB to retrieve relevant documents and then uses OpenAI's models to generate a response."
+)
+st.write(
+    "The model is trained on the MIT Scheme textbook and a handful of Discrete Math and Paradigms related content that Professor Troeger posted"
+)
 st.write("Data Avaliable: ", DATA_AVAL)
 
 # INPUTS
@@ -29,48 +35,80 @@ user_question: str = st.text_area("Enter your groovy questions here")
 
 remember_chat_history = st.toggle("Remember This Chat's History")
 
-temperature = st.slider(label="Creativity of Model", min_value=0.0, max_value=2.0, value=0.8)
+temperature = st.slider(
+    label="Creativity of Model", min_value=0.0, max_value=2.0, value=0.8
+)
 st.markdown("*High creativity will make it go crazy - keep it low*")
 
-num_samples = st.slider(label="Amount of References to Give to Model", min_value=10, max_value=100, value=10)
-st.markdown("*High amount will make it slow and expensive (and may not be relevant) - keep it low*")
+num_samples = st.slider(
+    label="Amount of References to Give to Model", min_value=10, max_value=100, value=10
+)
+st.markdown(
+    "*High amount will make it slow and expensive (and may not be relevant) - keep it low*"
+)
 
 access_key: str = st.text_input("Enter your gpt key here", type="password")
-st.markdown("*For more information about how to get an access key, read [this article](https://platform.openai.com/api-keys). Make sure it has money in it ☠️*", unsafe_allow_html=True)
+st.markdown(
+    "*For more information about how to get an access key, read [this article](https://platform.openai.com/api-keys). Make sure it has money in it ☠️*",
+    unsafe_allow_html=True,
+)
 
-gpt_type: str = st.selectbox(label="Choose GPT Type", options=["gpt-3.5-turbo", "gpt-3.5-turbo-1106", "gpt-3.5-turbo-0125", "gpt-4-32k-0613", "gpt-4-0613", "gpt-4-0125-preview"], index=0)
-st.markdown("*For more information about GPT types, read [this article](https://platform.openai.com/docs/models).*", unsafe_allow_html=True)
+gpt_type: str = st.selectbox(
+    label="Choose GPT Type",
+    options=[
+        "gpt-3.5-turbo",
+        "gpt-3.5-turbo-1106",
+        "gpt-3.5-turbo-0125",
+        "gpt-4-32k-0613",
+        "gpt-4-0613",
+        "gpt-4-0125-preview",
+    ],
+    index=0,
+)
+st.markdown(
+    "*For more information about GPT types, read [this article](https://platform.openai.com/docs/models).*",
+    unsafe_allow_html=True,
+)
 
 st.divider()
 
 # ON BUTTON CLICK
-if st.button('Start Scheming') & (access_key != "") & (user_question != ""):
+if st.button("Start Scheming") & (access_key != "") & (user_question != ""):
     openai_client = OpenAI(api_key=access_key)
 
-    with st.spinner('Loading...'):
+    with st.spinner("Loading..."):
         # Perform the Chromadb query.
         results = schemer.query(
-            query_texts=[user_question],
-            n_results=num_samples,
-            include = ['documents']
+            query_texts=[user_question], n_results=num_samples, include=["documents"]
         )
         documents = results["documents"]
         response = openai_client.chat.completions.create(
             model="gpt-3.5-turbo",
             messages=[
-                {"role": "system", "content": "You are an expert in functional programming in R5RS, with great knowledge on programming paradigms. You wish to teach the user everything you know about programming paradigms in R5RS - so you explain everything thoroughly. Surround Latex equations in dollar signs as such Inline equation: $equation$ & Display equation: $$equation$$. You will focus your examples to work exclusively in interative and recursive apporaches"},
+                {
+                    "role": "system",
+                    "content": "You are an expert in functional programming in R5RS, with great knowledge on programming paradigms. You wish to teach the user everything you know about programming paradigms in R5RS - so you explain everything thoroughly. Surround Latex equations in dollar signs as such Inline equation: $equation$ & Display equation: $$equation$$. You will focus your examples to work exclusively in interative and recursive apporaches",
+                },
                 {"role": "user", "content": user_question},
                 {"role": "assistant", "content": str(documents)},
-                {"role": "user", "content": f"Conversation History: {history}"}
+                {"role": "user", "content": f"Conversation History: {history}"},
             ],
-            temperature=temperature
+            temperature=temperature,
+            stream=True,
         )
-        
-    history.append({user_question : response.choices[0].message.content} if remember_chat_history else {})
-        
-    st.header("Prof Says ...")
-    st.write(response.choices[0].message.content)
+
+    # history.append({user_question : response.choices[0].message.content} if remember_chat_history else {})
+
+    st.header("The Mega Schemer Says ...")
+
+    text_placeholder = st.empty()
+
+    content = ""
+    for i, chunk in enumerate(response):
+        if chunk.choices[0].delta.content is not None:
+            # Append the chunk content to the string
+            content += chunk.choices[0].delta.content
+
+            text_placeholder.markdown(content)
 else:
     st.write("Please provide an input and (valid) API key")
-
-