mirror of
https://github.com/hwchase17/langchain.git
synced 2025-08-10 13:27:36 +00:00
docs: replace initialize_agent with create_react_agent in graphql.ipynb (#31133)
Thank you for contributing to LangChain! - [x] **PR title**: "package: description" - Where "package" is whichever of langchain, core, etc. is being modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI changes. - Example: "core: add foobar LLM" - [x] **PR message**: ***Delete this entire checklist*** and replace with - **Description:** a description of the change - **Issue:** the issue # it fixes, if applicable - **Dependencies:** any dependencies required for this change - **Twitter handle:** if your PR gets announced, and you'd like a mention, we'll gladly shout you out! - [x] **Add tests and docs**: If you're adding a new integration, please include 1. a test for the integration, preferably unit tests that do not rely on network access, 2. an example notebook showing its use. It lives in `docs/docs/integrations` directory. - [x] **Lint and test**: Run `make format`, `make lint` and `make test` from the root of the package(s) you've modified. See contribution guidelines for more: https://python.langchain.com/docs/contributing/ Additional guidelines: - Make sure optional dependencies are imported within a function. - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests. - Most PRs should not touch more than one package. - Changes should be backwards compatible. If no one reviews your PR within a few days, please @-mention one of baskaryan, eyurtsev, ccurme, vbarda, hwchase17. --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
parent
52732a4d13
commit
57c81dc3e3
@ -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,
|
||||
|
@ -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,
|
||||
|
@ -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,
|
||||
|
Loading…
Reference in New Issue
Block a user