The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
docs: replace initialize_agent with create_react_agent in graphql.ipynb (#31133)
Michael Li57c81dc3e3e8
diff --git a/docs/docs/integrations/tools/graphql.ipynb b/docs/docs/integrations/tools/graphql.ipynbindex bc0ded37bd..cbc67d7fcf 100644--- a/docs/docs/integrations/tools/graphql.ipynb+++ b/docs/docs/integrations/tools/graphql.ipynb@@ -12,33 +12,49 @@"\n","This Jupyter Notebook demonstrates how to use the `GraphQLAPIWrapper` component with an Agent.\n","\n",- "In this example, we'll be using the public `Star Wars GraphQL API` available at the following endpoint: https://swapi-graphql.netlify.app/.netlify/functions/index.\n",+ "In this example, we'll be using the public `Star Wars GraphQL API` available at the following endpoint: https://swapi-graphql.netlify.app/graphql .\n","\n","First, you need to install `httpx` and `gql` Python packages."]},{"cell_type": "code",- "execution_count": null,+ "execution_count": 1,"metadata": {"vscode": {"languageId": "shellscript"}},- "outputs": [],+ "outputs": [+ {+ "name": "stdout",+ "output_type": "stream",+ "text": [+ "Note: you may need to restart the kernel to use updated packages.\n"+ ]+ }+ ],"source": ["pip install httpx gql > /dev/null"]},{"cell_type": "code",- "execution_count": null,+ "execution_count": 2,"metadata": {"vscode": {"languageId": "shellscript"}},- "outputs": [],+ "outputs": [+ {+ "name": "stdout",+ "output_type": "stream",+ "text": [+ "Note: you may need to restart the kernel to use updated packages.\n"+ ]+ }+ ],"source": ["%pip install --upgrade --quiet langchain-community"]@@ -56,21 +72,36 @@"metadata": {},"outputs": [],"source": [- "from langchain.agents import AgentType, initialize_agent, load_tools\n",- "from langchain_openai import OpenAI\n",+ "import os\n","\n",- "llm = OpenAI(temperature=0)\n",+ "os.environ[\"OPENAI_API_KEY\"] = \"\""+ ]+ },+ {+ "cell_type": "code",+ "execution_count": 4,+ "metadata": {},+ "outputs": [],+ "source": [+ "from langchain.agents import load_tools\n","\n","tools = load_tools(\n"," [\"graphql\"],\n",- " graphql_endpoint=\"https://swapi-graphql.netlify.app/.netlify/functions/index\",\n",- ")\n",- "\n",- "agent = initialize_agent(\n",- " tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",+ " graphql_endpoint=\"https://swapi-graphql.netlify.app/graphql\",\n",")"]},+ {+ "cell_type": "code",+ "execution_count": 5,+ "metadata": {},+ "outputs": [],+ "source": [+ "from langgraph.prebuilt import create_react_agent\n",+ "\n",+ "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"+ ]+ },{"cell_type": "markdown","metadata": {},@@ -80,35 +111,55 @@},{"cell_type": "code",- "execution_count": 4,+ "execution_count": 6,"metadata": {},"outputs": [{"name": "stdout","output_type": "stream","text": [+ "================================\u001b[1m Human Message \u001b[0m=================================\n",+ "\n",+ "Search for the titles of all the stawars films stored in the graphql database that has this schema allFilms {\n",+ " films {\n",+ " title\n",+ " director\n",+ " releaseDate\n",+ " speciesConnection {\n",+ " species {\n",+ " name\n",+ " classification\n",+ " homeworld {\n",+ " name\n",+ " }\n",+ " }\n",+ " }\n",+ " }\n",+ " }\n","\n","\n",- "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",- "\u001b[32;1m\u001b[1;3m I need to query the graphql database to get the titles of all the star wars films\n",- "Action: query_graphql\n",- "Action Input: query { allFilms { films { title } } }\u001b[0m\n",- "Observation: \u001b[36;1m\u001b[1;3m\"{\\n \\\"allFilms\\\": {\\n \\\"films\\\": [\\n {\\n \\\"title\\\": \\\"A New Hope\\\"\\n },\\n {\\n \\\"title\\\": \\\"The Empire Strikes Back\\\"\\n },\\n {\\n \\\"title\\\": \\\"Return of the Jedi\\\"\\n },\\n {\\n \\\"title\\\": \\\"The Phantom Menace\\\"\\n },\\n {\\n \\\"title\\\": \\\"Attack of the Clones\\\"\\n },\\n {\\n \\\"title\\\": \\\"Revenge of the Sith\\\"\\n }\\n ]\\n }\\n}\"\u001b[0m\n",- "Thought:\u001b[32;1m\u001b[1;3m I now know the titles of all the star wars films\n",- "Final Answer: The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.\u001b[0m\n",+ "==================================\u001b[1m Ai Message \u001b[0m==================================\n",+ "Tool Calls:\n",+ " query_graphql (call_tN5A0dBbfOMewuw8Yy13bYpW)\n",+ " Call ID: call_tN5A0dBbfOMewuw8Yy13bYpW\n",+ " Args:\n",+ " tool_input: query { allFilms { films { title } } }\n",+ "=================================\u001b[1m Tool Message \u001b[0m=================================\n",+ "Name: query_graphql\n","\n",- "\u001b[1m> Finished chain.\u001b[0m\n"+ "\"{\\n \\\"allFilms\\\": {\\n \\\"films\\\": [\\n {\\n \\\"title\\\": \\\"A New Hope\\\"\\n },\\n {\\n \\\"title\\\": \\\"The Empire Strikes Back\\\"\\n },\\n {\\n \\\"title\\\": \\\"Return of the Jedi\\\"\\n },\\n {\\n \\\"title\\\": \\\"The Phantom Menace\\\"\\n },\\n {\\n \\\"title\\\": \\\"Attack of the Clones\\\"\\n },\\n {\\n \\\"title\\\": \\\"Revenge of the Sith\\\"\\n }\\n ]\\n }\\n}\"\n",+ "==================================\u001b[1m Ai Message \u001b[0m==================================\n",+ "\n",+ "The titles of all the Star Wars films stored in the database are:\n",+ "1. A New Hope\n",+ "2. The Empire Strikes Back\n",+ "3. Return of the Jedi\n",+ "4. The Phantom Menace\n",+ "5. Attack of the Clones\n",+ "6. Revenge of the Sith\n",+ "\n",+ "If you would like more information about any of these films, please let me know!\n"]- },- {- "data": {- "text/plain": [- "'The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.'"- ]- },- "execution_count": 4,- "metadata": {},- "output_type": "execute_result"}],"source": [@@ -133,9 +184,24 @@"\n","suffix = \"Search for the titles of all the stawars films stored in the graphql database that has this schema \"\n","\n",+ "input_message = {\n",+ " \"role\": \"user\",\n",+ " \"content\": suffix + graphql_fields,\n",+ "}\n","\n",- "agent.run(suffix + graphql_fields)"+ "for step in agent.stream(\n",+ " {\"messages\": [input_message]},\n",+ " stream_mode=\"values\",\n",+ "):\n",+ " step[\"messages\"][-1].pretty_print()"]+ },+ {+ "cell_type": "code",+ "execution_count": null,+ "metadata": {},+ "outputs": [],+ "source": []}],"metadata": {@@ -157,7 +223,7 @@"name": "python","nbconvert_exporter": "python","pygments_lexer": "ipython3",- "version": "3.10.12"+ "version": "3.13.2"}},"nbformat": 4,diff --git a/docs/docs/integrations/tools/openweathermap.ipynb b/docs/docs/integrations/tools/openweathermap.ipynbindex caf3c41f8e..46dd954110 100644--- a/docs/docs/integrations/tools/openweathermap.ipynb+++ b/docs/docs/integrations/tools/openweathermap.ipynb@@ -153,7 +153,7 @@"source": ["input_message = {\n"," \"role\": \"user\",\n",- " \"content\": (\"What's the weather like in London?\"),\n",+ " \"content\": \"What's the weather like in London?\",\n","}\n","\n","for step in agent.stream(\n",@@ -188,7 +188,7 @@"name": "python","nbconvert_exporter": "python","pygments_lexer": "ipython3",- "version": "3.13.3"+ "version": "3.13.2"}},"nbformat": 4,diff --git a/docs/docs/integrations/tools/yahoo_finance_news.ipynb b/docs/docs/integrations/tools/yahoo_finance_news.ipynbindex a2da3dd406..76613b0bf5 100644--- a/docs/docs/integrations/tools/yahoo_finance_news.ipynb+++ b/docs/docs/integrations/tools/yahoo_finance_news.ipynb@@ -108,7 +108,7 @@"source": ["input_message = {\n"," \"role\": \"user\",\n",- " \"content\": (\"What happened today with Microsoft stocks?\"),\n",+ " \"content\": \"What happened today with Microsoft stocks?\",\n","}\n","\n","for step in agent.stream(\n",@@ -165,7 +165,7 @@"source": ["input_message = {\n"," \"role\": \"user\",\n",- " \"content\": (\"How does Microsoft feels today comparing with Nvidia?\"),\n",+ " \"content\": \"How does Microsoft feels today comparing with Nvidia?\",\n","}\n","\n","for step in agent.stream(\n",@@ -258,7 +258,7 @@"name": "python","nbconvert_exporter": "python","pygments_lexer": "ipython3",- "version": "3.13.3"+ "version": "3.13.2"}},"nbformat": 4,