Add ntbk

README.md

@@ -148,6 +148,14 @@ LangGraph Studio also integrates with [LangSmith](https://smith.langchain.com/)
 
 [^1]: https://python.langchain.com/docs/concepts/#tools
 
+## LangGraph API 
+
+We can also interact with the graph using the LangGraph API. 
+
+See `ntbk/testing.ipynb` for an example of how to do this.
+
+LangGraph Cloud (see [here](https://langchain-ai.github.io/langgraph/cloud/#overview)) make it possible to deploy the agent. 
+
 <!--
 Configuration auto-generated by `langgraph template lock`. DO NOT EDIT MANUALLY.
 {

src/enrichment_agent/tools.py

@@ -21,7 +21,9 @@
 
 
 async def search(
-    query: str, *, config: Annotated[RunnableConfig, InjectedToolArg]
+    query: str, 
+    *, 
+    config: Annotated[RunnableConfig, InjectedToolArg]
 ) -> Optional[list[dict[str, Any]]]:
     """
     Perform a general web search using the Tavily search engine.
@@ -31,19 +33,6 @@ async def search(
     2. Initializes a TavilySearchResults object with a maximum number of results.
     3. Invokes the Tavily search with the given query.
     4. Returns the search results as a list of dictionaries.
-
-    Args:
-        query (str): The search query string.
-        config (RunnableConfig): Configuration object containing search parameters.
-
-    Returns:
-        Optional[list[dict[str, Any]]]: A list of search result dictionaries, or None if the search fails.
-        Each dictionary typically contains information like title, url, content snippet, etc.
-
-    Note:
-        This function uses the Tavily search engine, which is designed for comprehensive
-        and accurate results, particularly useful for current events and factual queries.
-        The maximum number of results is determined by the configuration.
     """
     configuration = Configuration.from_runnable_config(config)
     wrapped = TavilySearchResults(max_results=configuration.max_search_results)
@@ -80,18 +69,6 @@ async def scrape_website(
     2. Formats a prompt using the fetched content and the extraction schema from the state.
     3. Initializes a language model using the provided configuration.
     4. Invokes the model with the formatted prompt to summarize the content.
-
-    Args:
-        url (str): The URL of the website to scrape.
-        state (State): Injected state containing the extraction schema.
-        config (RunnableConfig): Configuration for initializing the language model.
-
-    Returns:
-        str: A summary of the scraped content, tailored to the extraction schema.
-
-    Note:
-        The function uses aiohttp for asynchronous HTTP requests and assumes the
-        existence of a _INFO_PROMPT template and an init_model function.
     """
     async with aiohttp.ClientSession() as session:
         async with session.get(url) as response: