Updating files

.github/workflows/integration-tests.yml

@@ -39,6 +39,5 @@ jobs:
           TAVILY_API_KEY: ${{ secrets.TAVILY_API_KEY }}
           LANGSMITH_API_KEY: ${{ secrets.LANGSMITH_API_KEY }}
           LANGSMITH_TRACING: true
-          LANGSMITH_TEST_CACHE: tests/casettes
         run: |
           uv run pytest tests/integration_tests

README.md

@@ -40,10 +40,10 @@ Setup instruction auto-generated by `langgraph template lock`. DO NOT EDIT MANUA
 
 ### Setup Model
 
-The defaults values for `model_name` are shown below:
+The defaults values for `model` are shown below:
 
 ```yaml
-model_name: anthropic/claude-3-5-sonnet-20240620
+model: anthropic/claude-3-5-sonnet-20240620
 ```
 
 Follow the instructions below to get set up, or pick one of the additional options.
@@ -58,18 +58,20 @@ To use Anthropic's chat models:
 ```
 ANTHROPIC_API_KEY=your-api-key
 ```
-
 #### OpenAI
 
 To use OpenAI's chat models:
 
 1. Sign up for an [OpenAI API key](https://platform.openai.com/signup).
 2. Once you have your API key, add it to your `.env` file:
-
 ```
 OPENAI_API_KEY=your-api-key
 ```
 
+
+
+
+
 <!--
 End setup instructions
 -->
@@ -169,7 +171,7 @@ Configuration auto-generated by `langgraph template lock`. DO NOT EDIT MANUALLY.
     "agent": {
       "type": "object",
       "properties": {
-        "model_name": {
+        "model": {
           "type": "string",
           "default": "anthropic/claude-3-5-sonnet-20240620",
           "description": "The name of the language model to use for the agent. Should be in the form: provider/model-name.",
@@ -295,4 +297,4 @@ Configuration auto-generated by `langgraph template lock`. DO NOT EDIT MANUALLY.
     }
   }
 }
--->
+-->

ntbk/testing.ipynb

@@ -37,6 +37,7 @@
    "outputs": [],
    "source": [
     "from langgraph_sdk import get_client\n",
+    "\n",
     "client = get_client(url=\"http://localhost:56396\")"
    ]
   },
@@ -55,41 +56,38 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "schema =  {\n",
+    "schema = {\n",
     "    \"type\": \"object\",\n",
     "    \"properties\": {\n",
     "        \"companies\": {\n",
     "            \"type\": \"array\",\n",
     "            \"items\": {\n",
     "                \"type\": \"object\",\n",
     "                \"properties\": {\n",
-    "                    \"name\": {\n",
-    "                        \"type\": \"string\",\n",
-    "                        \"description\": \"Company name\"\n",
-    "                    },\n",
+    "                    \"name\": {\"type\": \"string\", \"description\": \"Company name\"},\n",
     "                    \"technologies\": {\n",
     "                        \"type\": \"string\",\n",
-    "                        \"description\": \"Brief summary of key technologies used by the company\"\n",
+    "                        \"description\": \"Brief summary of key technologies used by the company\",\n",
     "                    },\n",
     "                    \"market_share\": {\n",
     "                        \"type\": \"string\",\n",
-    "                        \"description\": \"Overview of market share for this company\"\n",
+    "                        \"description\": \"Overview of market share for this company\",\n",
     "                    },\n",
     "                    \"future_outlook\": {\n",
     "                        \"type\": \"string\",\n",
-    "                        \"description\": \"Brief summary of future prospects and developments in the field for this company\"\n",
+    "                        \"description\": \"Brief summary of future prospects and developments in the field for this company\",\n",
     "                    },\n",
     "                    \"key_powers\": {\n",
     "                        \"type\": \"string\",\n",
-    "                        \"description\": \"Which of the 7 Powers (Scale Economies, Network Economies, Counter Positioning, Switching Costs, Branding, Cornered Resource, Process Power) best describe this company's competitive advantage\"\n",
-    "                    }\n",
+    "                        \"description\": \"Which of the 7 Powers (Scale Economies, Network Economies, Counter Positioning, Switching Costs, Branding, Cornered Resource, Process Power) best describe this company's competitive advantage\",\n",
+    "                    },\n",
     "                },\n",
-    "                \"required\": [\"name\", \"technologies\", \"market_share\", \"future_outlook\"]\n",
+    "                \"required\": [\"name\", \"technologies\", \"market_share\", \"future_outlook\"],\n",
     "            },\n",
-    "            \"description\": \"List of companies\"\n",
+    "            \"description\": \"List of companies\",\n",
     "        }\n",
     "    },\n",
-    "    \"required\": [\"companies\"]\n",
+    "    \"required\": [\"companies\"],\n",
     "}"
    ]
   },
@@ -118,7 +116,7 @@
     "# Stream\n",
     "async for event in client.runs.stream(\n",
     "    thread[\"thread_id\"],\n",
-    "    assistant_id= \"agent\",\n",
+    "    assistant_id=\"agent\",\n",
     "    input={\n",
     "        \"topic\": topic,\n",
     "        \"extraction_schema\": schema,\n",
@@ -223,10 +221,11 @@
    "source": [
     "from IPython.display import Markdown, display\n",
     "\n",
+    "\n",
     "def format_llm_chip_info(data):\n",
     "    markdown_text = \"# Top 5 Chip Providers for LLM Training\\n\\n\"\n",
-    "    \n",
-    "    for company in data['companies']:\n",
+    "\n",
+    "    for company in data[\"companies\"]:\n",
     "        markdown_text += f\"\"\"\n",
     "## {company['name']}\n",
     "\n",
@@ -240,9 +239,10 @@
     "\n",
     "---\n",
     "\"\"\"\n",
-    "    \n",
+    "\n",
     "    return Markdown(markdown_text)\n",
     "\n",
+    "\n",
     "# Display the formatted markdown\n",
     "display(format_llm_chip_info(current_state[\"values\"][\"info\"]))"
    ]

src/enrichment_agent/configuration.py

@@ -14,7 +14,7 @@
 class Configuration:
     """The configuration for the agent."""
 
-    model_name: Annotated[str, {"__template_metadata__": {"kind": "llm"}}] = field(
+    model: Annotated[str, {"__template_metadata__": {"kind": "llm"}}] = field(
         default="anthropic/claude-3-5-sonnet-20240620",
         metadata={
             "description": "The name of the language model to use for the agent. "

src/enrichment_agent/graph.py

@@ -19,7 +19,6 @@
 from enrichment_agent.utils import init_model
 
 
-# Define the nodes
 async def call_agent_model(
     state: State, *, config: Optional[RunnableConfig] = None
 ) -> Dict[str, Any]:
@@ -115,6 +114,12 @@ async def reflect(
     p = prompts.MAIN_PROMPT.format(
         info=json.dumps(state.extraction_schema, indent=2), topic=state.topic
     )
+    last_message = state.messages[-1]
+    if not isinstance(last_message, AIMessage):
+        raise ValueError(
+            f"{reflect.__name__} expects the last message in the state to be an AI message with tool calls."
+            f" Got: {type(last_message)}"
+        )
     messages = [HumanMessage(content=p)] + state.messages[:-1]
     presumed_info = state.info
     checker_prompt = """I am thinking of calling the info tool with the info below. \
@@ -128,13 +133,6 @@ async def reflect(
     raw_model = init_model(config)
     bound_model = raw_model.with_structured_output(InfoIsSatisfactory)
     response = cast(InfoIsSatisfactory, await bound_model.ainvoke(messages))
-    last_message = state.messages[-1]
-    if not isinstance(last_message, AIMessage):
-        raise ValueError(
-            f"{reflect.__name__} expects the last message in the state to be an AI message with tool calls."
-            f" Got: {type(last_message)}"
-        )
-
     if response.is_satisfactory and presumed_info:
         return {
             "info": presumed_info,

src/enrichment_agent/utils.py

@@ -25,7 +25,7 @@ def get_message_text(msg: AnyMessage) -> str:
 def init_model(config: Optional[RunnableConfig] = None) -> BaseChatModel:
     """Initialize the configured chat model."""
     configuration = Configuration.from_runnable_config(config)
-    fully_specified_name = configuration.model_name
+    fully_specified_name = configuration.model
     if "/" in fully_specified_name:
         provider, model = fully_specified_name.split("/", maxsplit=1)
     else:

tests/integration_tests/test_graph.py

@@ -1,9 +1,8 @@
 from typing import Any, Dict
 
 import pytest
-from langsmith import unit
-
 from enrichment_agent import graph
+from langsmith import unit
 
 
 @pytest.fixture(scope="function")