mirror of
https://github.com/hwchase17/langchain.git
synced 2025-10-30 23:29:54 +00:00
9eb7e6e27f
Still retain: - Comparison Examples - Data + QA walkthrough - QA (but really minimize it)
319 lines
9.7 KiB
Plaintext
319 lines
9.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "bce7335e-f3b2-44f3-90cc-8c0a23a89a21",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import os\n",
|
|
"from langchain.agents import load_tools\n",
|
|
"from langchain.agents import initialize_agent\n",
|
|
"from langchain.chat_models import ChatOpenAI\n",
|
|
"from langchain.utilities import GoogleSearchAPIWrapper\n",
|
|
"from langchain.schema import (\n",
|
|
" SystemMessage,\n",
|
|
" HumanMessage,\n",
|
|
" AIMessage\n",
|
|
")\n",
|
|
"\n",
|
|
"# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
|
|
"# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
|
|
"# os.environ[\"LANGCHAIN_API_KEY\"] = \"******\"\n",
|
|
"# os.environ[\"LANGCHAIN_PROJECT\"] = \"Jarvis\"\n",
|
|
"\n",
|
|
"\n",
|
|
"prefix_messages = [{\"role\": \"system\", \"content\": \"You are a helpful discord Chatbot.\"}]\n",
|
|
"\n",
|
|
"llm = ChatOpenAI(model_name='gpt-3.5-turbo', \n",
|
|
" temperature=0.5, \n",
|
|
" max_tokens = 2000)\n",
|
|
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
|
|
"agent = initialize_agent(tools,\n",
|
|
" llm,\n",
|
|
" agent=\"zero-shot-react-description\",\n",
|
|
" verbose=True,\n",
|
|
" handle_parsing_errors=True\n",
|
|
" )\n",
|
|
"\n",
|
|
"\n",
|
|
"async def on_ready():\n",
|
|
" print(f'{bot.user} has connected to Discord!')\n",
|
|
"\n",
|
|
"async def on_message(message):\n",
|
|
"\n",
|
|
" print(\"Detected bot name in message:\", message.content)\n",
|
|
"\n",
|
|
" # Capture the output of agent.run() in the response variable\n",
|
|
" response = agent.run(message.content)\n",
|
|
"\n",
|
|
" while response:\n",
|
|
" print(response)\n",
|
|
" chunk, response = response[:2000], response[2000:]\n",
|
|
" print(f\"Chunk: {chunk}\")\n",
|
|
" print(\"Response sent.\")\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 22,
|
|
"id": "1551ce9f-b6de-4035-b6d6-825722823b48",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from dataclasses import dataclass\n",
|
|
"@dataclass\n",
|
|
"class Message:\n",
|
|
" content: str"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 23,
|
|
"id": "6e6859ec-8544-4407-9663-6b53c0092903",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Detected bot name in message: Hi AI, how are you today?\n",
|
|
"\n",
|
|
"\n",
|
|
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
|
"\u001b[32;1m\u001b[1;3mThis question is not something that can be answered using the available tools.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3mI need to follow the correct format for answering questions.\n",
|
|
"Action: N/A\u001b[0m\n",
|
|
"Observation: Invalid Format: Missing 'Action Input:' after 'Action:'\n",
|
|
"Thought:\u001b[32;1m\u001b[1;3m\u001b[0m\n",
|
|
"\n",
|
|
"\u001b[1m> Finished chain.\u001b[0m\n",
|
|
"Agent stopped due to iteration limit or time limit.\n",
|
|
"Chunk: Agent stopped due to iteration limit or time limit.\n",
|
|
"Response sent.\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"await on_message(Message(content=\"Hi AI, how are you today?\"))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 24,
|
|
"id": "b850294c-7f8f-4e79-adcf-47e4e3a898df",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langsmith import Client\n",
|
|
"\n",
|
|
"client = Client()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 25,
|
|
"id": "6d089ddc-69bc-45a8-b8db-9962e4f1f5ee",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from itertools import islice\n",
|
|
"\n",
|
|
"runs = list(islice(client.list_runs(), 10))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 38,
|
|
"id": "f0349fac-5a98-400f-ba03-61ed4e1332be",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"runs = sorted(runs, key=lambda x: x.start_time, reverse=True)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 26,
|
|
"id": "02f133f0-39ee-4b46-b443-12c1f9b76fff",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"ids = [run.id for run in runs]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 39,
|
|
"id": "3366dce4-0c38-4a7d-8111-046a58b24917",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"runs2 = list(client.list_runs(id=ids))\n",
|
|
"runs2 = sorted(runs2, key=lambda x: x.start_time, reverse=True)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 42,
|
|
"id": "82915b90-39a0-47d6-9121-56a13f210f52",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"['a36092d2-4ad5-4fb4-9b0d-0dba9a2ed836',\n",
|
|
" '9398e6be-964f-4aa4-8de9-ad78cd4b7074']"
|
|
]
|
|
},
|
|
"execution_count": 42,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"[str(x) for x in ids[:2]]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 48,
|
|
"id": "f610ec91-dc48-4a17-91c5-5c4675c77abc",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langsmith.run_helpers import traceable\n",
|
|
"\n",
|
|
"@traceable(run_type=\"llm\", name=\"\"\"<iframe width=\"560\" height=\"315\" src=\"https://www.youtube.com/embed/dQw4w9WgXcQ?start=5\" title=\"YouTube video player\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" allowfullscreen></iframe>\"\"\")\n",
|
|
"def foo():\n",
|
|
" return \"bar\""
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 49,
|
|
"id": "bd317bd7-8b2a-433a-8ec3-098a84ba8e64",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"'bar'"
|
|
]
|
|
},
|
|
"execution_count": 49,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"foo()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 52,
|
|
"id": "b142519b-6885-415c-83b9-4a346fb90589",
|
|
"metadata": {
|
|
"tags": []
|
|
},
|
|
"outputs": [],
|
|
"source": [
|
|
"from langchain.llms import AzureOpenAI"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "5c50bb2b-72b8-4322-9b16-d857ecd9f347",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.11.2"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|