mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-09 06:53:59 +00:00
docs/fix links (#6498)
This commit is contained in:
Davis Chase
GitHub
@@ -7,7 +7,7 @@
|
||||
"source": [
|
||||
"# Evaluating an OpenAPI Chain\n",
|
||||
"\n",
|
||||
"This notebook goes over ways to semantically evaluate an [OpenAPI Chain](openapi.html), which calls an endpoint defined by the OpenAPI specification using purely natural language."
|
||||
"This notebook goes over ways to semantically evaluate an [OpenAPI Chain](/docs/modules/chains/additiona/openapi.html), which calls an endpoint defined by the OpenAPI specification using purely natural language."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -967,7 +967,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.11.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -1,474 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5371a9bb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Tracing Walkthrough\n",
|
||||
"\n",
|
||||
"There are two recommended ways to trace your LangChains:\n",
|
||||
"\n",
|
||||
"1. Setting the `LANGCHAIN_TRACING` environment variable to \"true\".\n",
|
||||
"1. Using a context manager with tracing_enabled() to trace a particular block of code.\n",
|
||||
"\n",
|
||||
"**Note** if the environment variable is set, all code will be traced, regardless of whether or not it's within the context manager."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "17c04cc6-c93d-4b6c-a033-e897577f4ed1",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"LANGCHAIN_TRACING\"] = \"true\"\n",
|
||||
"\n",
|
||||
"## Uncomment below if using hosted setup.\n",
|
||||
"# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://langchain-api-gateway-57eoxz8z.uc.gateway.dev\"\n",
|
||||
"\n",
|
||||
"## Uncomment below if you want traces to be recorded to \"my_session\" instead of \"default\".\n",
|
||||
"# os.environ[\"LANGCHAIN_SESSION\"] = \"my_session\"\n",
|
||||
"\n",
|
||||
"## Better to set this environment variable in the terminal\n",
|
||||
"## Uncomment below if using hosted version. Replace \"my_api_key\" with your actual API Key.\n",
|
||||
"# os.environ[\"LANGCHAIN_API_KEY\"] = \"my_api_key\"\n",
|
||||
"\n",
|
||||
"import langchain\n",
|
||||
"from langchain.agents import Tool, initialize_agent, load_tools\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.callbacks import tracing_enabled\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "1b62cd48",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Agent run with tracing. Ensure that OPENAI_API_KEY is set appropriately to run this example.\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"tools = load_tools([\"llm-math\"], llm=llm)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "bfa16b79-aa4b-4d41-a067-70d1f593f667",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2^.123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0891804557407723'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent.run(\"What is 2 raised to .123243 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "4829eb1d",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0891804557407723'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Agent run with tracing using a chat model\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" ChatOpenAI(temperature=0),\n",
|
||||
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
|
||||
" verbose=True,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"agent.run(\"What is 2 raised to .123243 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "76abfd82",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 5 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.2193914912400514\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.2193914912400514\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Both of the agent runs will be traced because the environment variable is set\n",
|
||||
"agent.run(\"What is 2 raised to .123243 power?\")\n",
|
||||
"with tracing_enabled() as session:\n",
|
||||
" agent.run(\"What is 5 raised to .123243 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "fe833c33-033f-4806-be0c-cc3d147db13d",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 5 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.2193914912400514\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.2193914912400514\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2 ^ .123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3mI now know the answer to the question. \n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0891804557407723'"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Now, we unset the environment variable and use a context manager.\n",
|
||||
"if \"LANGCHAIN_TRACING\" in os.environ:\n",
|
||||
" del os.environ[\"LANGCHAIN_TRACING\"]\n",
|
||||
"\n",
|
||||
"# here, we are writing traces to \"my_test_session\"\n",
|
||||
"with tracing_enabled(\"my_session\") as session:\n",
|
||||
" assert session\n",
|
||||
" agent.run(\"What is 5 raised to .123243 power?\") # this should be traced\n",
|
||||
"\n",
|
||||
"agent.run(\"What is 2 raised to .123243 power?\") # this should not be traced"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "b34105a4-be8e-46e4-8abe-01adba3ba727",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 3^0.123\u001b[0m\u001b[32;1m\u001b[1;3mI need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2^0.123\u001b[0m\u001b[32;1m\u001b[1;3mAny number raised to the power of 0 is 1, but I'm not sure about a decimal power.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 1^.123\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.1446847956963533\u001b[0m\n",
|
||||
"Thought:\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0889970153361064\u001b[0m\n",
|
||||
"Thought:\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0\u001b[0m\n",
|
||||
"Thought:\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0'"
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# The context manager is concurrency safe:\n",
|
||||
"import asyncio\n",
|
||||
"\n",
|
||||
"if \"LANGCHAIN_TRACING\" in os.environ:\n",
|
||||
" del os.environ[\"LANGCHAIN_TRACING\"]\n",
|
||||
"\n",
|
||||
"questions = [f\"What is {i} raised to .123 power?\" for i in range(1, 4)]\n",
|
||||
"\n",
|
||||
"# start a background task\n",
|
||||
"task = asyncio.create_task(agent.arun(questions[0])) # this should not be traced\n",
|
||||
"with tracing_enabled() as session:\n",
|
||||
" assert session\n",
|
||||
" tasks = [agent.arun(q) for q in questions[1:3]] # these should be traced\n",
|
||||
" await asyncio.gather(*tasks)\n",
|
||||
"\n",
|
||||
"await task"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c552a5dd-cbca-48b9-90e6-930076006f78",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## [Beta] Tracing V2\n",
|
||||
"\n",
|
||||
"We are rolling out a newer version of our tracing service with more features coming soon. Here are the instructions on how to use it to trace your runs.\n",
|
||||
"\n",
|
||||
"To use, you can use the `tracing_v2_enabled` context manager or set `LANGCHAIN_TRACING_V2 = 'true'`\n",
|
||||
"\n",
|
||||
"**Option 1 (Local)**: \n",
|
||||
"* Run the local LangChainPlus Server\n",
|
||||
"```\n",
|
||||
"pip install --upgrade langchain\n",
|
||||
"langchain plus start\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"**Option 2 (Hosted)**:\n",
|
||||
"* After making an account an grabbing a LangChainPlus API Key, set the `LANGCHAIN_ENDPOINT` and `LANGCHAIN_API_KEY` environment variables"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "87027b0d-3a61-47cf-8a65-3002968be7f9",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"\n",
|
||||
"os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
|
||||
"# os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.langchain.plus\" # Uncomment this line if you want to use the hosted version\n",
|
||||
"# os.environ[\"LANGCHAIN_API_KEY\"] = \"<YOUR-LANGCHAINPLUS-API-KEY>\" # Uncomment this line if you want to use the hosted version."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "5b4f49a2-7d09-4601-a8ba-976f0517c64c",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import langchain\n",
|
||||
"from langchain.agents import Tool, initialize_agent, load_tools\n",
|
||||
"from langchain.agents import AgentType\n",
|
||||
"from langchain.callbacks import tracing_enabled\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.llms import OpenAI"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "029b4a57-dc49-49de-8f03-53c292144e09",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Agent run with tracing. Ensure that OPENAI_API_KEY is set appropriately to run this example.\n",
|
||||
"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"tools = load_tools([\"llm-math\"], llm=llm)\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "91a85fb2-6027-4bd0-b1fe-2a3b3b79e2dd",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to use a calculator to solve this.\n",
|
||||
"Action: Calculator\n",
|
||||
"Action Input: 2^.123243\u001b[0m\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\u001b[0m\n",
|
||||
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: 1.0891804557407723\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'1.0891804557407723'"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent.run(\"What is 2 raised to .123243 power?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "f2291e9f-02f3-4b55-bd3d-d719de815df1",
|
||||
"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": "3.10.9"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 73 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 348 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 239 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 253 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 117 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 94 KiB |
@@ -1,57 +0,0 @@
|
||||
# Tracing
|
||||
|
||||
By enabling tracing in your LangChain runs, you’ll be able to more effectively visualize, step through, and debug your chains and agents.
|
||||
|
||||
First, you should install tracing and set up your environment properly.
|
||||
You can use either a locally hosted version of this (uses Docker) or a cloud hosted version (in closed alpha).
|
||||
If you're interested in using the hosted platform, please fill out the form [here](https://forms.gle/tRCEMSeopZf6TE3b6).
|
||||
|
||||
- [Locally Hosted Setup](./local_installation.md)
|
||||
- [Cloud Hosted Setup](./hosted_installation.md)
|
||||
|
||||
## Tracing Walkthrough
|
||||
|
||||
When you first access the UI, you should see a page with your tracing sessions.
|
||||
An initial one "default" should already be created for you.
|
||||
A session is just a way to group traces together.
|
||||
If you click on a session, it will take you to a page with no recorded traces that says "No Runs."
|
||||
You can create a new session with the new session form.
|
||||
|
||||
|
||||
|
||||
If we click on the `default` session, we can see that to start we have no traces stored.
|
||||
|
||||
|
||||
|
||||
If we now start running chains and agents with tracing enabled, we will see data show up here.
|
||||
To do so, we can run [this notebook](./agent_with_tracing.html) as an example.
|
||||
After running it, we will see an initial trace show up.
|
||||
|
||||
|
||||
|
||||
From here we can explore the trace at a high level by clicking on the arrow to show nested runs.
|
||||
We can keep on clicking further and further down to explore deeper and deeper.
|
||||
|
||||
|
||||
|
||||
We can also click on the "Explore" button of the top level run to dive even deeper.
|
||||
Here, we can see the inputs and outputs in full, as well as all the nested traces.
|
||||
|
||||
|
||||
|
||||
We can keep on exploring each of these nested traces in more detail.
|
||||
For example, here is the lowest level trace with the exact inputs/outputs to the LLM.
|
||||
|
||||
|
||||
|
||||
## Changing Sessions
|
||||
|
||||
1. To initially record traces to a session other than `"default"`, you can set the `LANGCHAIN_SESSION` environment variable to the name of the session you want to record to:
|
||||
|
||||
```python
|
||||
import os
|
||||
os.environ["LANGCHAIN_TRACING"] = "true"
|
||||
os.environ["LANGCHAIN_SESSION"] = "my_session" # Make sure this session actually exists. You can create a new session in the UI.
|
||||
```
|
||||
|
||||
2. To switch sessions mid-script or mid-notebook, do NOT set the `LANGCHAIN_SESSION` environment variable. Instead: `langchain.set_tracing_callback_manager(session_name="my_session")`
|
||||
Reference in New Issue
Block a user