mcp powered voice agents

examples/Reinforcement_Fine_Tuning.ipynb

@@ -1339,8 +1339,8 @@
    "outputs": [],
    "source": [
     "# Set your training and test file paths\n",
-    "train_file = \"data/medical_01_verifiable_problem_train_with_prompt.jsonl\"\n",
-    "test_file = \"data/medical_01_verifiable_problem_val_with_prompt.jsonl\"\n",
+    "train_file = \"data/medical_01_verifiable_problem_train_simple_prompt.jsonl\"\n",
+    "test_file = \"data/medical_01_verifiable_problem_val_simple_prompt.jsonl\"\n",
     "\n",
     "def upload_file(file_path: str) -> str:\n",
     "    \"\"\"Upload a file to the OpenAI platform for fine-tuning.\"\"\"\n",
@@ -1389,7 +1389,7 @@
     "grader = model_grader_2\n",
     "response_format = None\n",
     "compute_multiplier = 1.0\n",
-    "etest_samples = 1\n",
+    "eval_samples = 1\n",
     "eval_interval = 5"
    ]
   },
@@ -1409,7 +1409,7 @@
     "# Launch the RFT job\n",
     "payload = dict(\n",
     "    training_file=train_file_id,\n",
-    "    test_file=test_file_id,\n",
+    "    validation_file=test_file_id,\n",
     "    model=model,\n",
     "    suffix=suffix,\n",
     "    method=dict(\n",
@@ -1419,7 +1419,7 @@
     "            response_format=response_format,\n",
     "            hyperparameters=dict(\n",
     "                compute_multiplier=compute_multiplier,\n",
-    "                etest_samples=etest_samples,\n",
+    "                eval_samples=eval_samples,\n",
     "                eval_interval=eval_interval,\n",
     "                n_epochs=n_epochs,\n",
     "                reasoning_effort=reasoning_effort,\n",
@@ -2116,7 +2116,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.12.9"
   }
  },
  "nbformat": 4,

examples/o-series/o3o4-mini_prompting_guide.ipynb

@@ -163,6 +163,18 @@
     "Validate arguments against the format before sending the call; if you are unsure, ask for clarification instead of guessing.\n",
     "```\n",
     "\n",
+    "3. Another note on lazy behavior\n",
+    "We are aware of rare instances of lazy behavior from o3, such as stating it does not have enough time to complete a task, promising to follow up separately, or giving terse answers even when explicitly prompted to provide more detail. We have found that the following steps help ameliorate this behavior:\n",
+    "\n",
+    "    a. Start a new conversation for unrelated topics:\n",
+    "       When switching to a new or unrelated topic, begin a fresh conversation thread rather than continuing in the same context. This helps the model focus on the current subject and prevents it from being influenced by previous, irrelevant context, which can sometimes lead to incomplete or lazy responses. For example, if you were previously discussing code debugging and now want to ask about documentation best practices, which does not require previous conversation context, start a new conversation to ensure clarity and focus.\n",
+    "\n",
+    "    b. Discard irrelevant past tool calls/outputs when the list gets too long, and summarize them as context in the user message:\n",
+    "       If the conversation history contains a long list of previous tool calls or outputs that are no longer relevant, remove them from the context. Instead, provide a concise summary of the important information as part of the user message. This keeps the context manageable and ensures the model has access to only the most pertinent information. For instance, if you have a lengthy sequence of tool outputs, you can summarize the key results and include only that summary in your next message.\n",
+    "\n",
+    "    c. We are constantly improving our models and expect to have this issue addressed in future versions.\n",
+    "\n",
+    "\n",
     "### Avoid Chain of Thought Prompting\n",
     "Since these models are reasoning models and produce an internal chain of thought, they do not have to be explicitly prompted to plan and reason between toolcalls. Therefore, a developer should not try to induce additional reasoning before each function call by asking the model to plan more extensively. Asking a reasoning model to reason more may actually hurt the performance. \n",
     "\n",

examples/partners/mcp_powered_voice_agents/search_server.py

@@ -0,0 +1,107 @@
+import os
+from mcp.server.fastmcp import FastMCP
+from openai import OpenAI
+from agents import set_tracing_export_api_key
+
+# Create server
+mcp = FastMCP("Search Server")
+_vector_store_id = ""
+
+def _run_rag(query: str) -> str:
+    """Do a search for answers within the knowledge base and internal documents of the user.
+    Args:
+        query: The user query
+    """
+    results = client.vector_stores.search(
+        vector_store_id=_vector_store_id,
+        query=query,
+        rewrite_query=True,  # Query rewriting generally improves results
+    )
+    return results.data[0].content[0].text
+
+
+def _summarize_rag_response(rag_output: str) -> str:
+    """Summarize the RAG response using GPT-4
+    Args:
+        rag_output: The RAG response
+    """
+    response = client.responses.create(
+        model="gpt-4.1-mini",
+        tools=[{"type": "web_search_preview"}],
+        input="Summarize the following text concisely: \n\n" + rag_output,
+    )
+    return response.output_text
+
+
+@mcp.tool()
+def generate_rag_output(query: str) -> str:
+    """Generate a summarized RAG output for a given query.
+    Args:
+        query: The user query
+    """
+    print("[debug-server] generate_rag_output: ", query)
+    rag_output = _run_rag(query)
+    return _summarize_rag_response(rag_output)
+
+
+@mcp.tool()
+def run_web_search(query: str) -> str:
+    """Run a web search for the given query.
+    Args:
+        query: The user query
+    """
+    print("[debug-server] run_web_search:", query)
+    response = client.responses.create(
+        model="gpt-4.1-mini",
+        tools=[{"type": "web_search_preview"}],
+        input=query,
+    )
+    return response.output_text
+
+
+def index_documents(directory: str):
+    """Index the documents in the given directory to the vector store
+    Args:
+        directory: The directory to index the documents from
+    """
+    # OpenAI supported file extensions for retrieval (see docs)
+    SUPPORTED_EXTENSIONS = {'.pdf', '.txt', '.md', '.docx', '.pptx', '.csv', '.rtf', '.html', '.json', '.xml'}
+    # Collect all files in the specified directory
+    files = [os.path.join(directory, f) for f in os.listdir(directory)]
+    # Filter files for supported extensions only
+    supported_files = []
+    for file_path in files:
+        _, ext = os.path.splitext(file_path)
+        if ext.lower() in SUPPORTED_EXTENSIONS:
+            supported_files.append(file_path)
+        else:
+            print(f"[warning] Skipping unsupported file for retrieval: {file_path}")
+
+    vector_store = client.vector_stores.create( # Create vector store
+        name="Support FAQ",
+    )
+    global _vector_store_id
+    _vector_store_id = vector_store.id
+
+    for file_path in supported_files:
+        # Upload each file to the vector store, ensuring the file handle is closed
+        with open(file_path, "rb") as fp:
+            client.vector_stores.files.upload_and_poll(
+                vector_store_id=vector_store.id,
+                file=fp
+            )
+        print(f"[debug-server] uploading file: {file_path}")
+
+
+if __name__ == "__main__":
+    oai_api_key = os.environ.get("OPENAI_API_KEY")
+    if not oai_api_key:
+        raise ValueError("OPENAI_API_KEY environment variable is not set")
+    set_tracing_export_api_key(oai_api_key)
+    client = OpenAI(api_key=oai_api_key)
+
+    current_dir = os.path.dirname(os.path.abspath(__file__))
+    samples_dir = os.path.join(current_dir, "sample_files")
+    index_documents(samples_dir)
+
+    mcp.run(transport="sse")

examples/vector_databases/elasticsearch/elasticsearch-semantic-search.ipynb

@@ -37,14 +37,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "8c304b93",
    "metadata": {},
    "outputs": [],
    "source": [
     "# install packages\n",
     "\n",
-    "!python3 -m pip install -qU openai pandas wget elasticsearch\n",
+    "! python3 -m pip install -qU openai pandas wget elasticsearch\n",
     "\n",
     "# import modules\n",
     "\n",
@@ -54,7 +54,7 @@
     "import zipfile\n",
     "import pandas as pd\n",
     "import json\n",
-    "import openai"
+    "from openai import OpenAI"
    ]
   },
   {
@@ -321,25 +321,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "id": "57385c69",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Get OpenAI API key\n",
-    "OPENAI_API_KEY = getpass(\"Enter OpenAI API key\")\n",
-    "\n",
-    "# Set API key\n",
-    "openai.api_key = OPENAI_API_KEY\n",
-    "\n",
-    "# Define model\n",
-    "EMBEDDING_MODEL = \"text-embedding-3-small\"\n",
+    "# Create OpenAI client\n",
+    "openai_client = OpenAI()\n",
     "\n",
     "# Define question\n",
     "question = 'Is the Atlantic the biggest ocean in the world?'\n",
     "\n",
-    "# Create embedding\n",
-    "question_embedding = openai.Embedding.create(input=question, model=EMBEDDING_MODEL)\n"
+    "question_embedding = openai_client.embeddings.create(\n",
+    "    input=question,\n",
+    "    model=\"text-embedding-3-small\"\n",
+    ")"
    ]
   },
   {
@@ -383,7 +379,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": null,
    "id": "fc834fdd",
    "metadata": {},
    "outputs": [
@@ -764,7 +760,7 @@
     "  index = \"wikipedia_vector_index\",\n",
     "  knn={\n",
     "      \"field\": \"content_vector\",\n",
-    "      \"query_vector\":  question_embedding[\"data\"][0][\"embedding\"],\n",
+    "      \"query_vector\":  question_embedding.data[0].embedding,\n",
     "      \"k\": 10,\n",
     "      \"num_candidates\": 100\n",
     "    }\n",

registry.yaml

@@ -4,6 +4,20 @@
 # should build pages for, and indicates metadata such as tags, creation date and
 # authors for each page.
 
+- title: MCP Powered Voice Agents
+  path: examples/partners/mcp_powered_voice_agents/mcp_powered_agents_cookbook.ipynb
+  date: 2025-06-12
+  authors:
+    - shikhar-cyber
+    - Cece Z
+    - Sibon li
+  tags:
+    - mcp
+    - voice
+    - agents-sdk
+    - functions
+    - tracing
+
 - title: Eval Driven System Design - From Prototype to Production
   path: examples/partners/eval_driven_system_design/receipt_inspection.ipynb
   date: 2025-06-02
@@ -866,7 +880,6 @@
     - leemthompo
   tags:
     - embeddings
-    - completions
 
 - title: Using Hologres as a vector database for OpenAI embeddings
   path: >-