Add main_eng.py with English content

stream-agent/main_eng.py

@@ -0,0 +1,57 @@
+import os
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts import PromptTemplate
+from langchain_core.output_parsers import PydanticOutputParser
+from langchain_core.messages import HumanMessage
+from langchain_core.tools import tool
+from typing import List
+
+# ---
+# Example task: display a price table for products in Kazan
+# ---
+
+# 1. Define the model
+llm = ChatOpenAI(temperature=0, model="gpt-4o")
+
+# 2. Create a tool (mock price lookup)
+@tool
+def get_price(product: str, city: str = "Kazan") -> str:
+    """Return a string with the price of a product in a given city."""
+    # Example static data
+    prices = {
+        "milk": "89",
+        "bread": "30",
+        "sugar": "70",
+    }
+    return f"{product} in {city}: {prices.get(product, 'not found')} rub."
+
+# 3. Create the agent
+from langchain.agents import create_openai_functions_agent, AgentExecutor
+
+agent = create_openai_functions_agent(llm=llm, tools=[get_price])
+
+# 4. Run in stream mode
+executor = AgentExecutor(agent=agent, tools=[get_price], verbose=False)
+
+# Run
+input_message = "What is the price of milk and bread in Kazan?"
+
+# Stream
+stream = executor.stream(
+    {"messages": [HumanMessage(content=input_message)]},
+    stream_mode=["messages"],
+)
+
+step = 1
+for chunk in stream:
+    chunk_type, chunk_data = chunk
+    if chunk_type == "messages":
+        message, meta = chunk_data
+        if meta["langgraph_step"] != step:
+            step = meta["langgraph_step"]
+            print("\n---------\n")
+        if message.content:
+            print(message.content, end="", flush=True)
+
+# Print final result
+print("\n\n---\n" + executor.run({"messages": [HumanMessage(content=input_message)]})["output"])