@ -25,7 +25,7 @@
},
{
"cell_type": "code",
"execution_count": null ,
"execution_count": 1 ,
"id": "aa761a93-caa1-4e56-b901-5ff50a89bc82",
"metadata": {},
"outputs": [],
@ -35,10 +35,21 @@
},
{
"cell_type": "code",
"execution_count": null ,
"execution_count": 12 ,
"id": "5944a18a-95eb-44ce-a66f-5f50db1d3e1f",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"[ThreadMessage(id='msg_qgxkD5kvkZyl0qOaL4czPFkZ', assistant_id='asst_0T8S7CJuUa4Y4hm1PF6n62v7', content=[MessageContentText(text=Text(annotations=[], value='The result of the calculation \\\\(10 - 4^{2.7}\\\\) is approximately \\\\(-32.224\\\\).'), type='text')], created_at=1700169519, file_ids=[], metadata={}, object='thread.message', role='assistant', run_id='run_aH3ZgSWNk3vYIBQm3vpE8tr4', thread_id='thread_9K6cYfx1RBh0pOWD8SxwVWW9')]"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"interpreter_assistant = OpenAIAssistantRunnable.create_assistant(\n",
" name=\"langchain assistant\",\n",
@ -72,19 +83,21 @@
},
{
"cell_type": "code",
"execution_count": null ,
"execution_count": 3 ,
"id": "cc0cba70-8507-498d-92ac-fe47133db200",
"metadata": {},
"outputs": [],
"source": [
"import getpass\n",
"\n",
"from langchain.tools import DuckDuckGoSearchRun, E2BDataAnalysisTool\n",
"\n",
"tools = [E2BDataAnalysisTool(api_key=\"...\" ), DuckDuckGoSearchRun()]"
"tools = [E2BDataAnalysisTool(api_key=getpass.getpass() ), DuckDuckGoSearchRun()]"
]
},
{
"cell_type": "code",
"execution_count": null ,
"execution_count": 4 ,
"id": "91e6973d-3d9a-477f-99e2-4aaad16004ec",
"metadata": {},
"outputs": [],
@ -103,15 +116,31 @@
"id": "78fa9320-06fc-4cbc-a3cf-39aaf2427080",
"metadata": {},
"source": [
"#### Using AgentExecutor"
"#### Using AgentExecutor\n",
"\n",
"The OpenAIAssistantRunnable is compatible with the AgentExecutor, so we can pass it in as an agent directly to the executor. The AgentExecutor handles calling the invoked tools and uploading the tool outputs back to the Assistants API. Plus it comes with built-in LangSmith tracing."
]
},
{
"cell_type": "code",
"execution_count": null ,
"execution_count": 5 ,
"id": "e38007a4-fcc1-419b-9ae4-70d36c3fc1cd",
"metadata": {},
"outputs": [],
"outputs": [
{
"data": {
"text/plain": [
"{'content': \"What's the weather in SF today divided by 2.7\",\n",
" 'output': \"The search results indicate that the weather in San Francisco is 67 °F. Now I will divide this temperature by 2.7 and provide you with the result. Please note that this is a mathematical operation and does not represent a meaningful physical quantity.\\n\\nLet's calculate 67 °F divided by 2.7.\\nThe result of dividing the current temperature in San Francisco, which is 67 °F, by 2.7 is approximately 24.815.\",\n",
" 'thread_id': 'thread_hcpYI0tfpB9mHa9d95W7nK2B',\n",
" 'run_id': 'run_qOuVmPXS9xlV3XNPcfP8P9W2'}"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.agents import AgentExecutor\n",
"\n",
@ -119,17 +148,28 @@
"agent_executor.invoke({\"content\": \"What's the weather in SF today divided by 2.7\"})"
]
},
{
"cell_type": "markdown",
"id": "db6b9cbf-dd54-4346-be6c-842e08756ccc",
"metadata": {},
"source": [
":::tip [LangSmith trace](https://smith.langchain.com/public/6750972b-0849-4beb-a8bb-353d424ffade/r)\n",
":::"
]
},
{
"cell_type": "markdown",
"id": "6bf4199a-eed1-485a-8da3-aed948c0e1e2",
"metadata": {},
"source": [
"#### Custom execution"
"#### Custom execution\n",
"\n",
"Or with LCEL we can easily write our own execution loop for running the assistant. This gives us full control over execution."
]
},
{
"cell_type": "code",
"execution_count": null ,
"execution_count": 6 ,
"id": "357361ff-f54d-4fd0-b69b-77689f56f40e",
"metadata": {},
"outputs": [],
@ -145,7 +185,7 @@
},
{
"cell_type": "code",
"execution_count": null ,
"execution_count": 7 ,
"id": "864e7f9b-0501-4bb7-8aad-a7aa19b601af",
"metadata": {},
"outputs": [],
@ -177,34 +217,86 @@
},
{
"cell_type": "code",
"execution_count": null ,
"execution_count": 8 ,
"id": "5ad6bb07-aac4-4b71-9e67-cc177fcbc537",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"e2b_data_analysis {'python_code': 'result = 10 - 4 ** 2.7\\nprint(result)'} {\"stdout\": \"-32.22425314473263\", \"stderr\": \"\", \"artifacts\": []}\n",
"\n",
"\\( 10 - 4^{2.7} \\) equals approximately -32.224.\n"
]
}
],
"source": [
"response = execute_agent(agent, tools, {\"content\": \"What's 10 - 4 raised to the 2.7\"})\n",
"print(response.return_values[\"output\"])"
]
},
{
"cell_type": "markdown",
"id": "6fd9f9c0-4b07-4f71-a784-88ee7bd4b089",
"metadata": {},
"source": [
"## Using existing Thread\n",
"\n",
"To use an existing thread we just need to pass the \"thread_id\" in when invoking the agent."
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 9 ,
"id": "f55a3a3a-8169-491e-aa15-cf30a2b230df",
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"e2b_data_analysis {'python_code': 'result = 10 - 4 ** 2.7 + 17.241\\nprint(result)'} {\"stdout\": \"-14.983253144732629\", \"stderr\": \"\", \"artifacts\": []}\n",
"\n",
"\\( 10 - 4^{2.7} + 17.241 \\) equals approximately -14.983.\n"
]
}
],
"source": [
"next_response = execute_agent(\n",
" agent, tools, {\"content\": \"now add 17.241\", \"thread_id\": response.thread_id}\n",
" agent,\n",
" tools,\n",
" {\"content\": \"now add 17.241\", \"thread_id\": response.return_values[\"thread_id\"]},\n",
")\n",
"print(next_response.return_values[\"output\"])"
]
},
{
"cell_type": "markdown",
"id": "1b97ee01-a657-452c-ba7f-95227ec7056e",
"metadata": {},
"source": [
"## Using existing Assistant\n",
"\n",
"To use an existing Assistant we can initialize the `OpenAIAssistantRunnable` directly with an `assistant_id`."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "08ef6ef5-e8bc-4c69-882d-65273655f6a7",
"metadata": {},
"outputs": [],
"source": [
"agent = OpenAIAssistantRunnable(assistant_id=\"<ASSISTANT_ID>\", as_agent=True)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"display_name": "poetry-venv ",
"language": "python",
"name": "python3"
"name": "poetry-venv "
},
"language_info": {
"codemirror_mode": {