Merge branch 'main' into dev/corwin/improve-mcp-eval-book

Author: CorwinCheung

examples/partners/eval_driven_system_design/receipt_inspection.ipynb

@@ -139,18 +139,9 @@
     "\n",
     "### 2. Assemble Examples (Gather Data)\n",
     "\n",
-    "It's very rare that a real-world project will start with all the data necessary to get\n",
-    "to a satisfactory solution, much less to establish confidence.\n",
-    "\n",
-    "In our case, we're going to assume that we have a decent sample of system *inputs*, \n",
-    "in the form of but receipt images, but start without any fully annotated data. We find \n",
-    "this is a not-unusual situation when automating an existing process. Instead, \n",
-    "we'll walk through the process of building that out as we go along by collaborating with\n",
-    "domain experts, and make our evals progressively more comprehensive.\n",
-    "In our case, we're going to assume that we have a decent sample of system *inputs*\n",
-    "(here, photographs of receipts), but start without any fully annotated data. We'll walk\n",
-    "through the process of incrementally expanding our test and training sets as we go along\n",
-    "and make our evals progressively more comprehensive.\n",
+    "It's very rare for a real-world project to begin with all the data necessary to achieve a satisfactory solution, let alone establish confidence.\n",
+    "\n",
+    "In our case, we'll assume we have a decent sample of system *inputs*, in the form of but receipt images, but start without any fully annotated data. We find this is a not-unusual situation when automating an existing process. We'll walk through the process of incrementally expanding our test and training sets in collaboration with domain experts as we go along and make our evals progressively more comprehensive.\n",
     "\n",
     "### 3. Build an End-to-End V0 System\n",
     "\n",

examples/partners/mcp_powered_voice_agents/database.db

@@ -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")