update gpt-3.5 version

notebooks/01-Basic_Tutor.ipynb

@@ -99,7 +99,7 @@
       },
       "outputs": [],
       "source": [
-        "# Defining a function to answer a question using \"gpt-3.5-turbo-16k\" model.\n",
+        "# Defining a function to answer a question using \"gpt-3.5-turbo-0125\" model.\n",
         "def ask_ai_tutor(question):\n",
         "    try:\n",
         "        # Formulating the system prompt and condition the model to answer only AI-related questions.\n",
@@ -113,8 +113,8 @@
         "\n",
         "        # Call the OpenAI API\n",
         "        response = client.chat.completions.create(\n",
-        "                model='gpt-3.5-turbo-16k',\n",
-        "                temperature=0.0,\n",
+        "                model='gpt-3.5-turbo-0125',\n",
+        "                temperature=0,\n",
         "                messages=[\n",
         "                    {\"role\": \"system\", \"content\": system_prompt},\n",
         "                    {\"role\": \"user\", \"content\": prompt}\n",
@@ -218,7 +218,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.11.7"
+      "version": "3.11.8"
     }
   },
   "nbformat": 4,

notebooks/02-Basic_RAG.ipynb

@@ -533,7 +533,7 @@
         "\n",
         "    # Call the OpenAI API\n",
         "    response = client.chat.completions.create(\n",
-        "      model='gpt-3.5-turbo-16k',\n",
+        "      model='gpt-3.5-turbo-0125',\n",
         "      temperature=0.0,\n",
         "      messages=[\n",
         "        {\"role\": \"system\", \"content\": system_prompt},\n",
@@ -610,7 +610,7 @@
         "\n",
         "# Call the OpenAI API\n",
         "response = client.chat.completions.create(\n",
-        "  model='gpt-3.5-turbo-16k',\n",
+        "  model='gpt-3.5-turbo-0125',\n",
         "  temperature=.9,\n",
         "  messages=[\n",
         "    {\"role\": \"system\", \"content\": system_prompt},\n",
@@ -680,7 +680,7 @@
       "name": "python",
       "nbconvert_exporter": "python",
       "pygments_lexer": "ipython3",
-      "version": "3.11.7"
+      "version": "3.11.8"
     },
     "widgets": {
       "application/vnd.jupyter.widget-state+json": {

notebooks/03-RAG_with_LlamaIndex.ipynb

@@ -231,9 +231,11 @@
    },
    "outputs": [],
    "source": [
+    "from llama_index.llms.openai import OpenAI\n",
     "# Define a query engine that is responsible for retrieving related pieces of text,\n",
     "# and using a LLM to formulate the final answer.\n",
-    "query_engine = index.as_query_engine()"
+    "llm = OpenAI(temperature=0, model=\"gpt-3.5-turbo-0125\", max_tokens=512)\n",
+    "query_engine = index.as_query_engine(llm=llm)"
    ]
   },
   {
@@ -290,7 +292,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,

notebooks/04-RAG_with_VectorStore.ipynb

@@ -275,9 +275,12 @@
    },
    "outputs": [],
    "source": [
+    "from llama_index.llms.openai import OpenAI\n",
     "# Define a query engine that is responsible for retrieving related pieces of text,\n",
     "# and using a LLM to formulate the final answer.\n",
-    "query_engine = index.as_query_engine()"
+    "\n",
+    "llm = OpenAI(temperature=0, model=\"gpt-3.5-turbo-0125\", max_tokens=512)\n",
+    "query_engine = index.as_query_engine(llm=llm)"
    ]
   },
   {
@@ -334,7 +337,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,

notebooks/05-Improve_Prompts_+_Add_Source.ipynb

@@ -82,7 +82,7 @@
    "source": [
     "from llama_index.llms.openai import OpenAI\n",
     "\n",
-    "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
+    "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo-0125\", max_tokens=512)"
    ]
   },
   {
@@ -724,7 +724,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.11.8"
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {

notebooks/06-Evaluate_RAG.ipynb

@@ -82,7 +82,7 @@
    "source": [
     "from llama_index.llms.openai import OpenAI\n",
     "\n",
-    "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
+    "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo-0125\", max_tokens=512)"
    ]
   },
   {
@@ -589,7 +589,7 @@
     "from llama_index.core.evaluation import generate_question_context_pairs\n",
     "from llama_index.llms.openai import OpenAI\n",
     "\n",
-    "llm = OpenAI(model=\"gpt-3.5-turbo\")\n",
+    "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
     "rag_eval_dataset = generate_question_context_pairs(\n",
     "    nodes,\n",
     "    llm=llm,\n",
@@ -795,7 +795,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.11.8"
   },
   "widgets": {
    "application/vnd.jupyter.widget-state+json": {

notebooks/07-RAG_Improve_Chunking.ipynb

@@ -82,7 +82,7 @@
       "source": [
         "from llama_index.llms.openai import OpenAI\n",
         "\n",
-        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
+        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo-0125\", max_tokens=512)"
       ]
     },
     {
@@ -758,7 +758,7 @@
         "\n",
         "index_no_metadata = VectorStoreIndex(\n",
         "    nodes=nodes_no_meta,\n",
-        "    service_context=ServiceContext.from_defaults(llm=OpenAI(model=\"gpt-3.5-turbo\")),\n",
+        "    service_context=ServiceContext.from_defaults(llm=OpenAI(model=\"gpt-3.5-turbo-0125\")),\n",
         ")"
       ]
     },
@@ -876,7 +876,7 @@
         "# Create questions for each segment. These questions will be used to\n",
         "# assess whether the retriever can accurately identify and return the\n",
         "# corresponding segment when queried.\n",
-        "llm = OpenAI(model=\"gpt-3.5-turbo\")\n",
+        "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
         "rag_eval_dataset = generate_question_context_pairs(\n",
         "    nodes,\n",
         "    llm=llm,\n",
@@ -1035,7 +1035,7 @@
         "    query_engine = index.as_query_engine(similarity_top_k=i)\n",
         "\n",
         "    # While we use GPT3.5-Turbo to answer questions, we can use GPT4 to evaluate the answers.\n",
-        "    llm_gpt4 = OpenAI(temperature=0, model=\"gpt-4-1106-preview\")\n",
+        "    llm_gpt4 = OpenAI(temperature=0, model=\"gpt-4-0125-preview\")\n",
         "    service_context_gpt4 = ServiceContext.from_defaults(llm=llm_gpt4)\n",
         "\n",
         "    faithfulness_evaluator = FaithfulnessEvaluator(service_context=service_context_gpt4)\n",

notebooks/08-Finetune_Embedding.ipynb

@@ -259,7 +259,7 @@
         "from llama_index.llms.openai import OpenAI\n",
         "\n",
         "# Load the OpenAI API with the \"gpt-3.5-turbo\" model\n",
-        "llm = OpenAI()\n",
+        "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
         "\n",
         "# Generate questions for each chunk.\n",
         "TRAIN_DATASET = generate_qa_embedding_pairs(TRAIN_NODEs, llm=llm)\n",

notebooks/09-Better_Embedding_Model.ipynb

@@ -92,7 +92,7 @@
       "source": [
         "from llama_index.llms.openai import OpenAI\n",
         "\n",
-        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
+        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo-0125\", max_tokens=512)"
       ]
     },
     {
@@ -665,7 +665,7 @@
         "# Create questions for each segment. These questions will be used to\n",
         "# assess whether the retriever can accurately identify and return the\n",
         "# corresponding segment when queried.\n",
-        "llm = OpenAI(model=\"gpt-3.5-turbo\")\n",
+        "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
         "rag_eval_dataset = generate_question_context_pairs(\n",
         "    nodes,\n",
         "    llm=llm,\n",
@@ -824,7 +824,7 @@
         "    query_engine = index.as_query_engine(similarity_top_k=i)\n",
         "\n",
         "    # While we use GPT3.5-Turbo to answer questions, we can use GPT4 to evaluate the answers.\n",
-        "    llm_gpt4 = OpenAI(temperature=0, model=\"gpt-4-1106-preview\")\n",
+        "    llm_gpt4 = OpenAI(temperature=0, model=\"gpt-4-0125-preview\")\n",
         "    service_context_gpt4 = ServiceContext.from_defaults(llm=llm_gpt4)\n",
         "\n",
         "    faithfulness_evaluator = FaithfulnessEvaluator(service_context=service_context_gpt4)\n",

notebooks/10-Adding_Reranking.ipynb

@@ -93,7 +93,7 @@
       "source": [
         "from llama_index.llms.openai import OpenAI\n",
         "\n",
-        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
+        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo-0125\", max_tokens=512)"
       ]
     },
     {
@@ -617,7 +617,7 @@
         "# Create questions for each segment. These questions will be used to\n",
         "# assess whether the retriever can accurately identify and return the\n",
         "# corresponding segment when queried.\n",
-        "llm = OpenAI(model=\"gpt-3.5-turbo\")\n",
+        "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
         "rag_eval_dataset = generate_question_context_pairs(\n",
         "    nodes,\n",
         "    llm=llm,\n",

notebooks/11-Adding_Hybrid_Search.ipynb

@@ -91,7 +91,7 @@
       "source": [
         "from llama_index.llms.openai import OpenAI\n",
         "\n",
-        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
+        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo-0125\", max_tokens=512)"
       ]
     },
     {
@@ -807,7 +807,7 @@
         "# Create questions for each segment. These questions will be used to\n",
         "# assess whether the retriever can accurately identify and return the\n",
         "# corresponding segment when queried.\n",
-        "llm = OpenAI(model=\"gpt-3.5-turbo\")\n",
+        "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
         "rag_eval_dataset = generate_question_context_pairs(\n",
         "    nodes,\n",
         "    llm=llm,\n",

notebooks/12-Improve_Query.ipynb

@@ -91,7 +91,7 @@
       "source": [
         "from llama_index.llms.openai import OpenAI\n",
         "\n",
-        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
+        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo-0125\", max_tokens=512)"
       ]
     },
     {
@@ -501,7 +501,7 @@
       "source": [
         "from llama_index.core import ServiceContext\n",
         "\n",
-        "gpt4 = OpenAI(temperature=0, model=\"gpt-4\")\n",
+        "gpt4 = OpenAI(temperature=0, model=\"gpt-4-0125-preview\")\n",
         "service_context_gpt4 = ServiceContext.from_defaults(llm=gpt4)"
       ]
     },
@@ -766,7 +766,7 @@
         "from llama_index.core.indices.query.query_transform.base import StepDecomposeQueryTransform\n",
         "from llama_index.core.query_engine.multistep_query_engine import MultiStepQueryEngine\n",
         "\n",
-        "gpt3 = OpenAI(temperature=0, model=\"gpt-3.5-turbo\")\n",
+        "gpt3 = OpenAI(temperature=0, model=\"gpt-3.5-turbo-0125\")\n",
         "service_context_gpt3 = ServiceContext.from_defaults(llm=gpt3)\n",
         "\n",
         "step_decompose_transform_gpt3 = StepDecomposeQueryTransform(llm=gpt3, verbose=True)\n",

notebooks/14-Adding_Chat.ipynb

@@ -91,7 +91,7 @@
       "source": [
         "from llama_index.llms.openai import OpenAI\n",
         "\n",
-        "llm = OpenAI(temperature=0.9, model=\"gpt-3.5-turbo\", max_tokens=512)"
+        "llm = OpenAI(temperature=0, model=\"gpt-3.5-turbo-0125\", max_tokens=512)"
       ]
     },
     {
@@ -740,7 +740,7 @@
       "outputs": [],
       "source": [
         "# Define GPT-4 model that will be used by the chat_engine to improve the query.\n",
-        "gpt4 = OpenAI(temperature=0.9, model=\"gpt-4\")"
+        "gpt4 = OpenAI(temperature=0.9, model=\"gpt-4-0125-preview\")"
       ]
     },
     {

notebooks/15-Use_OpenSource_Models.ipynb

@@ -782,7 +782,7 @@
         "# Create questions for each segment. These questions will be used to\n",
         "# assess whether the retriever can accurately identify and return the\n",
         "# corresponding segment when queried.\n",
-        "llm = OpenAI(model=\"gpt-3.5-turbo\")\n",
+        "llm = OpenAI(model=\"gpt-3.5-turbo-0125\")\n",
         "rag_eval_dataset = generate_question_context_pairs(\n",
         "    nodes,\n",
         "    llm=llm,\n",

scripts/basic_tutor.py

@@ -3,9 +3,10 @@ import os
 from openai import OpenAI
 
 # Retrieve your OpenAI API key from the environment variables and activate the OpenAI client
-openai_api_key = os.environ.get('OPENAI_API_KEY')
+openai_api_key = os.environ.get("OPENAI_API_KEY")
 client = OpenAI(api_key=openai_api_key)
 
+
 def ask_ai_tutor(question):
 
     # Check if OpenAI key has been correctly added
@@ -25,19 +26,20 @@ def ask_ai_tutor(question):
 
         # Call the OpenAI API
         response = client.chat.completions.create(
-                model='gpt-3.5-turbo-16k',
-                messages=[
-                    {"role": "system", "content": system_prompt},
-                    {"role": "user", "content": prompt}
-                ]
-            )
-        
+            model="gpt-3.5-turbo-0125",
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": prompt},
+            ],
+        )
+
         # Return the AI's response
         return response.choices[0].message.content.strip()
 
     except Exception as e:
         return f"An error occurred: {e}"
 
+
 def main():
     # Check if a question was provided as a command-line argument
     if len(sys.argv) != 2:
@@ -46,12 +48,13 @@ def main():
 
     # The user's question is the first command-line argument
     user_question = sys.argv[1]
-    
+
     # Get the AI's response
     ai_response = ask_ai_tutor(user_question)
-    
+
     # Print the AI's response
     print(f"AI Tutor says: {ai_response}")
 
+
 if __name__ == "__main__":
     main()