github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-07 22:11:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

Callbacks Refactor [base] (#3256)

Browse Source 
Co-authored-by: Nuno Campos <nuno@boringbits.io>
Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com>
Co-authored-by: Zander Chase <130414180+vowelparrot@users.noreply.github.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
This commit is contained in:
Ankush Gola
2023-04-30 11:14:09 -07:00
committed by GitHub
parent 18ec22fe56
commit d3ec00b566
208 changed files with 6394 additions and 3353 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/ecosystem/aim_tracking.ipynb
View File

@@ -61,7 +61,6 @@
"from datetime import datetime\n",
"\n",
"from langchain.llms import OpenAI\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks import AimCallbackHandler, StdOutCallbackHandler"
]
},
@@ -109,8 +108,8 @@
" experiment_name=\"scenario 1: OpenAI LLM\",\n",
")\n",
"\n",
"manager = CallbackManager([StdOutCallbackHandler(), aim_callback])\n",
"llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
"callbacks = [StdOutCallbackHandler(), aim_callback]\n",
"llm = OpenAI(temperature=0, callbacks=callbacks)"
]
},
{
@@ -177,7 +176,7 @@
"Title: {title}\n",
"Playwright: This is a synopsis for the above play:\"\"\"\n",
"prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callbacks=callbacks)\n",
"\n",
"test_prompts = [\n",
" {\"title\": \"documentary about good video games that push the boundary of game design\"},\n",
@@ -249,13 +248,12 @@
],
"source": [
"# scenario 3 - Agent with Tools\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=callbacks)\n",
"agent = initialize_agent(\n",
" tools,\n",
" llm,\n",
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
" callback_manager=manager,\n",
" verbose=True,\n",
" callbacks=callbacks,\n",
")\n",
"agent.run(\n",
" \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",

10
docs/ecosystem/clearml_tracking.ipynb
View File

@@ -79,7 +79,6 @@
"source": [
"from datetime import datetime\n",
"from langchain.callbacks import ClearMLCallbackHandler, StdOutCallbackHandler\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.llms import OpenAI\n",
"\n",
"# Setup and use the ClearML Callback\n",
@@ -93,9 +92,9 @@
" complexity_metrics=True,\n",
" stream_logs=True\n",
")\n",
"manager = CallbackManager([StdOutCallbackHandler(), clearml_callback])\n",
"callbacks = [StdOutCallbackHandler(), clearml_callback]\n",
"# Get the OpenAI model ready to go\n",
"llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
"llm = OpenAI(temperature=0, callbacks=callbacks)"
]
},
{
@@ -523,13 +522,12 @@
"from langchain.agents import AgentType\n",
"\n",
"# SCENARIO 2 - Agent with Tools\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=callbacks)\n",
"agent = initialize_agent(\n",
" tools,\n",
" llm,\n",
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
" callback_manager=manager,\n",
" verbose=True,\n",
" callbacks=callbacks,\n",
")\n",
"agent.run(\n",
" \"Who is the wife of the person who sang summer of 69?\"\n",

31
docs/ecosystem/comet_tracking.ipynb
View File

@@ -121,7 +121,6 @@
"from datetime import datetime\n",
"\n",
"from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.llms import OpenAI\n",
"\n",
"comet_callback = CometCallbackHandler(\n",
@@ -131,8 +130,8 @@
" tags=[\"llm\"],\n",
" visualizations=[\"dep\"],\n",
")\n",
"manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
"llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
"callbacks = [StdOutCallbackHandler(), comet_callback]\n",
"llm = OpenAI(temperature=0.9, callbacks=callbacks, verbose=True)\n",
"\n",
"llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\", \"Tell me a fact\"] * 3)\n",
"print(\"LLM result\", llm_result)\n",
@@ -153,7 +152,6 @@
"outputs": [],
"source": [
"from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.chains import LLMChain\n",
"from langchain.llms import OpenAI\n",
"from langchain.prompts import PromptTemplate\n",
@@ -164,15 +162,14 @@
" stream_logs=True,\n",
" tags=[\"synopsis-chain\"],\n",
")\n",
"manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
"\n",
"llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
"callbacks = [StdOutCallbackHandler(), comet_callback]\n",
"llm = OpenAI(temperature=0.9, callbacks=callbacks)\n",
"\n",
"template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
"Title: {title}\n",
"Playwright: This is a synopsis for the above play:\"\"\"\n",
"prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callbacks=callbacks)\n",
"\n",
"test_prompts = [{\"title\": \"Documentary about Bigfoot in Paris\"}]\n",
"print(synopsis_chain.apply(test_prompts))\n",
@@ -194,7 +191,6 @@
"source": [
"from langchain.agents import initialize_agent, load_tools\n",
"from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.llms import OpenAI\n",
"\n",
"comet_callback = CometCallbackHandler(\n",
@@ -203,15 +199,15 @@
" stream_logs=True,\n",
" tags=[\"agent\"],\n",
")\n",
"manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
"llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
"callbacks = [StdOutCallbackHandler(), comet_callback]\n",
"llm = OpenAI(temperature=0.9, callbacks=callbacks)\n",
"\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=callbacks)\n",
"agent = initialize_agent(\n",
" tools,\n",
" llm,\n",
" agent=\"zero-shot-react-description\",\n",
" callback_manager=manager,\n",
" callbacks=callbacks,\n",
" verbose=True,\n",
")\n",
"agent.run(\n",
@@ -255,7 +251,6 @@
"from rouge_score import rouge_scorer\n",
"\n",
"from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.chains import LLMChain\n",
"from langchain.llms import OpenAI\n",
"from langchain.prompts import PromptTemplate\n",
@@ -298,10 +293,10 @@
" tags=[\"custom_metrics\"],\n",
" custom_metrics=rouge_score.compute_metric,\n",
")\n",
"manager = CallbackManager([StdOutCallbackHandler(), comet_callback])\n",
"llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)\n",
"callbacks = [StdOutCallbackHandler(), comet_callback]\n",
"llm = OpenAI(temperature=0.9)\n",
"\n",
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template)\n",
"\n",
"test_prompts = [\n",
" {\n",
@@ -323,7 +318,7 @@
" \"\"\"\n",
" }\n",
"]\n",
"print(synopsis_chain.apply(test_prompts))\n",
"print(synopsis_chain.apply(test_prompts, callbacks=callbacks))\n",
"comet_callback.flush_tracker(synopsis_chain, finish=True)"
]
}

9
docs/ecosystem/gpt4all.md
View File

@@ -3,6 +3,7 @@
This page covers how to use the `GPT4All` wrapper within LangChain. The tutorial is divided into two parts: installation and setup, followed by usage with an example.
## Installation and Setup
- Install the Python package with `pip install pyllamacpp`
- Download a [GPT4All model](https://github.com/nomic-ai/pyllamacpp#supported-model) and place it in your desired directory
@@ -28,16 +29,16 @@ To stream the model's predictions, add in a CallbackManager.
```python
from langchain.llms import GPT4All
from langchain.callbacks.base import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
# There are many CallbackHandlers supported, such as
# from langchain.callbacks.streamlit import StreamlitCallbackHandler
callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
model = GPT4All(model="./models/gpt4all-model.bin", n_ctx=512, n_threads=8, callback_handler=callback_handler, verbose=True)
callbacks = [StreamingStdOutCallbackHandler()]
model = GPT4All(model="./models/gpt4all-model.bin", n_ctx=512, n_threads=8)
# Generate text. Tokens are streamed through the callback manager.
model("Once upon a time, ")
model("Once upon a time, ", callbacks=callbacks)
```
## Model File

14
docs/ecosystem/wandb_tracking.ipynb
View File

@@ -50,7 +50,6 @@
"source": [
"from datetime import datetime\n",
"from langchain.callbacks import WandbCallbackHandler, StdOutCallbackHandler\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.llms import OpenAI"
]
},
@@ -196,8 +195,8 @@
" name=\"llm\",\n",
" tags=[\"test\"],\n",
")\n",
"manager = CallbackManager([StdOutCallbackHandler(), wandb_callback])\n",
"llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
"callbacks = [StdOutCallbackHandler(), wandb_callback]\n",
"llm = OpenAI(temperature=0, callbacks=callbacks)"
]
},
{
@@ -484,7 +483,7 @@
"Title: {title}\n",
"Playwright: This is a synopsis for the above play:\"\"\"\n",
"prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
"synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callbacks=callbacks)\n",
"\n",
"test_prompts = [\n",
" {\n",
@@ -577,16 +576,15 @@
],
"source": [
"# SCENARIO 3 - Agent with Tools\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
"agent = initialize_agent(\n",
" tools,\n",
" llm,\n",
" agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
" callback_manager=manager,\n",
" verbose=True,\n",
")\n",
"agent.run(\n",
" \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
" \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\",\n",
" callbacks=callbacks,\n",
")\n",
"wandb_callback.flush_tracker(agent, reset=False, finish=True)"
]

3
docs/index.rst
View File

@@ -44,6 +44,8 @@ These modules are, in increasing order of complexity:
- `Agents <./modules/agents.html>`_: Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end to end agents.
- `Callbacks <./modules/callbacks/getting_started.html>`_: It can be difficult to track all that occurs inside a chain or agent - callbacks help add a level of observability and introspection.
.. toctree::
:maxdepth: 1
@@ -57,6 +59,7 @@ These modules are, in increasing order of complexity:
./modules/memory.md
./modules/chains.md
./modules/agents.md
./modules/callbacks/getting_started.ipynb
Use Cases
----------

294
docs/modules/agents/agent_executors/examples/async_agent.ipynb
View File

@@ -28,7 +28,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 7,
"id": "da5df06c-af6f-4572-b9f5-0ab971c16487",
"metadata": {
"tags": []
@@ -42,7 +42,6 @@
"from langchain.agents import AgentType\n",
"from langchain.llms import OpenAI\n",
"from langchain.callbacks.stdout import StdOutCallbackHandler\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.tracers import LangChainTracer\n",
"from aiohttp import ClientSession\n",
"\n",
@@ -57,7 +56,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 8,
"id": "fd4c294e-b1d6-44b8-b32e-2765c017e503",
"metadata": {
"tags": []
@@ -73,16 +72,15 @@
"\u001b[32;1m\u001b[1;3m I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.\n",
"Action: Search\n",
"Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mRafael Nadal\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Rafael Nadal's age\n",
"Observation: \u001b[33;1m\u001b[1;3mRafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out the age of the winner\n",
"Action: Search\n",
"Action Input: \"Rafael Nadal age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 36 raised to the 0.334 power\n",
"Thought:\u001b[32;1m\u001b[1;3m I now need to calculate his age raised to the 0.334 power\n",
"Action: Calculator\n",
"Action Input: 36^0.334\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Rafael Nadal, aged 36, won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.3098250249682484.\u001b[0m\n",
"\n",
@@ -93,18 +91,17 @@
"\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mJason Sudeikis\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
"Observation: \u001b[33;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Harry Styles' age.\n",
"Action: Search\n",
"Action Input: \"Jason Sudeikis age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m47 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 47 raised to the 0.23 power\n",
"Action Input: \"Harry Styles age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m29 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 29 raised to the 0.23 power.\n",
"Action: Calculator\n",
"Action Input: 47^0.23\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
"Action Input: 29^0.23\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.169459462491557\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Harry Styles, Olivia Wilde's boyfriend, is 29 years old and his age raised to the 0.23 power is 2.169459462491557.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
@@ -113,17 +110,17 @@
"\u001b[32;1m\u001b[1;3m I need to find out who won the grand prix and then calculate their age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Formula 1 Grand Prix Winner\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mMax Verstappen\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Max Verstappen's age\n",
"Observation: \u001b[33;1m\u001b[1;3mMichael Schumacher (top left) and Lewis Hamilton (top right) have each won the championship a record seven times during their careers, while Sebastian Vettel ( ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out the age of the winner\n",
"Action: Search\n",
"Action Input: \"Max Verstappen Age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m25 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 25 raised to the 0.23 power\n",
"Action Input: \"Michael Schumacher age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m54 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate the age raised to the 0.23 power\n",
"Action: Calculator\n",
"Action Input: 25^0.23\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.84599359907945\u001b[0m\n",
"Action Input: 54^0.23\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.502940725307012\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Max Verstappen, 25 years old, raised to the 0.23 power is 1.84599359907945.\u001b[0m\n",
"Final Answer: Michael Schumacher, aged 54, raised to the 0.23 power is 2.502940725307012.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
@@ -132,18 +129,17 @@
"\u001b[32;1m\u001b[1;3m I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.\n",
"Action: Search\n",
"Action Input: \"US Open women's final 2019 winner\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mBianca Andreescu defeated Serena Williams in the final, 6–3, 7–5 to win the women's singles tennis title at the 2019 US Open. It was her first major title, and she became the first Canadian, as well as the first player born in the 2000s, to win a major singles title.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Bianca Andreescu's age.\n",
"Observation: \u001b[33;1m\u001b[1;3mBianca Andreescu\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out her age\n",
"Action: Search\n",
"Action Input: \"Bianca Andreescu age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m22 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the age of Bianca Andreescu and can calculate her age raised to the 0.34 power.\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate her age raised to the 0.34 power\n",
"Action: Calculator\n",
"Action Input: 22^0.34\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.8603798598506933\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Bianca Andreescu won the US Open women's final in 2019 and her age raised to the 0.34 power is 2.8603798598506933.\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.8603798598506933\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Bianca Andreescu, aged 22, won the US Open women's final in 2019 and her age raised to the 0.34 power is 2.86.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
@@ -160,35 +156,32 @@
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 53 raised to the 0.19 power\n",
"Action: Calculator\n",
"Action Input: 53^0.19\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.12624064206896\n",
"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.12624064206896\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Jay-Z is Beyonce's husband and his age raised to the 0.19 power is 2.12624064206896.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"Serial executed in 65.11 seconds.\n"
"Serial executed in 52.47 seconds.\n"
]
}
],
"source": [
"def generate_serially():\n",
" for q in questions:\n",
" llm = OpenAI(temperature=0)\n",
" tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm)\n",
" agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
" )\n",
" agent.run(q)\n",
"llm = OpenAI(temperature=0)\n",
"tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm)\n",
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")\n",
"\n",
"s = time.perf_counter()\n",
"generate_serially()\n",
"for q in questions:\n",
" agent.run(q)\n",
"elapsed = time.perf_counter() - s\n",
"print(f\"Serial executed in {elapsed:0.2f} seconds.\")"
]
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 9,
"id": "076d7b85-45ec-465d-8b31-c2ad119c3438",
"metadata": {
"tags": []
@@ -202,6 +195,9 @@
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\n",
@@ -210,182 +206,94 @@
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out who Beyonce's husband is and then calculate his age raised to the 0.19 power.\n",
"Action: Search\n",
"Action Input: \"Who is Beyonce's husband?\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mJay-Z\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out who won the grand prix and then calculate their age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Formula 1 Grand Prix Winner\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.\n",
"\u001b[32;1m\u001b[1;3m I need to find out who won the US Open women's final in 2019 and then calculate her age raised to the 0.34 power.\n",
"Action: Search\n",
"Action Input: \"US Open women's final 2019 winner\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mJason Sudeikis\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[33;1m\u001b[1;3mMax Verstappen\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[33;1m\u001b[1;3mBianca Andreescu defeated Serena Williams in the final, 6–3, 7–5 to win the women's singles tennis title at the 2019 US Open. It was her first major title, and she became the first Canadian, as well as the first player born in the 2000s, to win a major singles title.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Jason Sudeikis' age\n",
"Action: Search\n",
"Action Input: \"Jason Sudeikis age\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out Jay-Z's age\n",
"Action: Search\n",
"Action Input: \"How old is Jay-Z?\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m53 years\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mBianca Andreescu\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.\n",
"Action: Search\n",
"Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mRafael Nadal defeated Daniil Medvedev in the final, 7–5, 6–3, 5–7, 4–6, 6–4 to win the men's singles tennis title at the 2019 US Open. It was his fourth US ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out who Olivia Wilde's boyfriend is and then calculate his age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Olivia Wilde boyfriend\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out who won the grand prix and then calculate their age raised to the 0.23 power.\n",
"Action: Search\n",
"Action Input: \"Formula 1 Grand Prix Winner\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out who Beyonce's husband is and then calculate his age raised to the 0.19 power.\n",
"Action: Search\n",
"Action Input: \"Who is Beyonce's husband?\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mOlivia Wilde started dating Harry Styles after ending her years-long engagement to Jason Sudeikis — see their relationship timeline.\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[33;1m\u001b[1;3m47 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Max Verstappen's age\n",
"Observation: \u001b[33;1m\u001b[1;3mJay-Z\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[33;1m\u001b[1;3mMichael Schumacher (top left) and Lewis Hamilton (top right) have each won the championship a record seven times during their careers, while Sebastian Vettel ( ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out her age\n",
"Action: Search\n",
"Action Input: \"Max Verstappen Age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m25 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Bianca Andreescu's age.\n",
"Action Input: \"Bianca Andreescu age\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out Jay-Z's age\n",
"Action: Search\n",
"Action Input: \"Bianca Andreescu age\"\u001b[0m\n",
"Action Input: \"How old is Jay-Z?\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m53 years\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[33;1m\u001b[1;3m22 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 53 raised to the 0.19 power\n",
"Action: Calculator\n",
"Action Input: 53^0.19\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out the age of the winner\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Harry Styles' age.\n",
"Action: Search\n",
"Action Input: \"Rafael Nadal age\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to calculate 47 raised to the 0.23 power\n",
"Action Input: \"Harry Styles age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m29 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate her age raised to the 0.34 power\n",
"Action: Calculator\n",
"Action Input: 47^0.23\u001b[0m\n",
"Action Input: 22^0.34\u001b[0m\u001b[32;1m\u001b[1;3m I need to calculate 53 raised to the 0.19 power\n",
"Action: Calculator\n",
"Action Input: 53^0.19\u001b[0m\u001b[32;1m\u001b[1;3m I need to calculate 29 raised to the 0.23 power.\n",
"Action: Calculator\n",
"Action Input: 29^0.23\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out the age of the winner\n",
"Action: Search\n",
"Action Input: \"Rafael Nadal age\"\u001b[0m\u001b[32;1m\u001b[1;3m I need to find out the age of the winner\n",
"Action: Search\n",
"Action Input: \"Michael Schumacher age\"\u001b[0m\n",
"Observation: \n",
"Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 25 raised to the 0.23 power\n",
"Action: Calculator\n",
"Action Input: 25^0.23\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.12624064206896\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the age of Bianca Andreescu and can calculate her age raised to the 0.34 power.\n",
"Action: Calculator\n",
"Action Input: 22^0.34\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.84599359907945\u001b[0m\n",
"Thought:\u001b[33;1m\u001b[1;3m54 years\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.4242784855673896\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now need to calculate his age raised to the 0.334 power\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.8603798598506933\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.169459462491557\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.12624064206896\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate the age raised to the 0.334 power\n",
"Action: Calculator\n",
"Action Input: 36^0.334\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.8603798598506933\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Jay-Z is Beyonce's husband and his age raised to the 0.19 power is 2.12624064206896.\u001b[0m\n",
"\n",
"Action Input: 36^0.334\u001b[0m\u001b[32;1m\u001b[1;3m I now need to calculate the age raised to the 0.23 power\n",
"Action: Calculator\n",
"Action Input: 54^0.23\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Max Verstappen, 25 years old, raised to the 0.23 power is 1.84599359907945.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Jason Sudeikis, Olivia Wilde's boyfriend, is 47 years old and his age raised to the 0.23 power is 2.4242784855673896.\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\u001b[0m\n",
"Thought:\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 2.502940725307012\u001b[0m\n",
"Thought:\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
"Final Answer: Bianca Andreescu won the US Open women's final in 2019 and her age raised to the 0.34 power is 2.8603798598506933.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Rafael Nadal, aged 36, won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.3098250249682484.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"Concurrent executed in 12.38 seconds.\n"
"Concurrent executed in 14.49 seconds.\n"
]
}
],
"source": [
"async def generate_concurrently():\n",
" agents = []\n",
" # To make async requests in Tools more efficient, you can pass in your own aiohttp.ClientSession, \n",
" # but you must manually close the client session at the end of your program/event loop\n",
" aiosession = ClientSession()\n",
" for _ in questions:\n",
" manager = CallbackManager([StdOutCallbackHandler()])\n",
" llm = OpenAI(temperature=0, callback_manager=manager)\n",
" async_tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm, aiosession=aiosession, callback_manager=manager)\n",
" agents.append(\n",
" initialize_agent(async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, callback_manager=manager)\n",
" )\n",
" tasks = [async_agent.arun(q) for async_agent, q in zip(agents, questions)]\n",
" await asyncio.gather(*tasks)\n",
" await aiosession.close()\n",
"llm = OpenAI(temperature=0)\n",
"tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm)\n",
"agent = initialize_agent(\n",
" tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
")\n",
"\n",
"s = time.perf_counter()\n",
"# If running this outside of Jupyter, use asyncio.run(generate_concurrently())\n",
"await generate_concurrently()\n",
"# If running this outside of Jupyter, use asyncio.run or loop.run_until_complete\n",
"tasks = [agent.arun(q) for q in questions]\n",
"await asyncio.gather(*tasks)\n",
"elapsed = time.perf_counter() - s\n",
"print(f\"Concurrent executed in {elapsed:0.2f} seconds.\")"
]
},
{
"cell_type": "markdown",
"id": "97ef285c-4a43-4a4e-9698-cd52a1bc56c9",
"metadata": {},
"source": [
"## Using Tracing with Asynchronous Agents\n",
"\n",
"To use tracing with async agents, you must pass in a custom `CallbackManager` with `LangChainTracer` to each agent running asynchronously. This way, you avoid collisions while the trace is being collected."
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "44bda05a-d33e-4e91-9a71-a0f3f96aae95",
"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 find out who won the US Open men's final in 2019 and then calculate his age raised to the 0.334 power.\n",
"Action: Search\n",
"Action Input: \"US Open men's final 2019 winner\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3mRafael Nadal\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to find out Rafael Nadal's age\n",
"Action: Search\n",
"Action Input: \"Rafael Nadal age\"\u001b[0m\n",
"Observation: \u001b[33;1m\u001b[1;3m36 years\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I need to calculate 36 raised to the 0.334 power\n",
"Action: Calculator\n",
"Action Input: 36^0.334\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 3.3098250249682484\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
"Final Answer: Rafael Nadal, aged 36, won the US Open men's final in 2019 and his age raised to the 0.334 power is 3.3098250249682484.\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
}
],
"source": [
"# To make async requests in Tools more efficient, you can pass in your own aiohttp.ClientSession, \n",
"# but you must manually close the client session at the end of your program/event loop\n",
"aiosession = ClientSession()\n",
"tracer = LangChainTracer()\n",
"tracer.load_default_session()\n",
"manager = CallbackManager([StdOutCallbackHandler(), tracer])\n",
"\n",
"# Pass the manager into the llm if you want llm calls traced.\n",
"llm = OpenAI(temperature=0, callback_manager=manager)\n",
"\n",
"async_tools = load_tools([\"llm-math\", \"serpapi\"], llm=llm, aiosession=aiosession)\n",
"async_agent = initialize_agent(async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, callback_manager=manager)\n",
"await async_agent.arun(questions[0])\n",
"await aiosession.close()"
]
}
],
"metadata": {
@@ -404,7 +312,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.10.9"
}
},
"nbformat": 4,

1
docs/modules/agents/agents/custom_agent_with_tool_retrieval.ipynb
View File

@@ -373,6 +373,7 @@
"metadata": {},
"outputs": [],
"source": [
"tools = get_tools(\"whats the weather?\")\n",
"tool_names = [tool.name for tool in tools]\n",
"agent = LLMSingleActionAgent(\n",
" llm_chain=llm_chain, \n",

3
docs/modules/agents/tools/examples/arxiv.ipynb
View File

@@ -75,6 +75,7 @@
}
],
"source": [
"\n",
"arxiv = ArxivAPIWrapper()\n",
"docs = arxiv.run(\"1605.08386\")\n",
"docs"
@@ -163,7 +164,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
"version": "3.10.6"
}
},
"nbformat": 4,

5
docs/modules/agents/tools/examples/gradio_tools.ipynb
View File

@@ -69,7 +69,8 @@
}
],
"source": [
"StableDiffusionTool().langchain.run(\"Please create a photo of a dog riding a skateboard\")"
"local_file_path = StableDiffusionTool().langchain.run(\"Please create a photo of a dog riding a skateboard\")\n",
"local_file_path"
]
},
{
@@ -89,7 +90,7 @@
"metadata": {},
"outputs": [],
"source": [
"im = Image.open(\"/Users/harrisonchase/workplace/langchain/docs/modules/agents/tools/examples/b61c1dd9-47e2-46f1-a47c-20d27640993d/tmp4ap48vnm.jpg\")"
"im = Image.open(local_file_path)"
]
},
{

10
docs/modules/agents/tools/examples/python.ipynb
View File

@@ -19,6 +19,7 @@
"metadata": {},
"outputs": [],
"source": [
"from langchain.agents import Tool\n",
"from langchain.utilities import PythonREPL"
]
},
@@ -59,7 +60,14 @@
"id": "54fc1f03",
"metadata": {},
"outputs": [],
"source": []
"source": [
"# You can create the tool to pass to an agent\n",
"repl_tool = Tool(\n",
" name=\"python_repl\",\n",
" description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
" func=python_repl\n",
")"
]
}
],
"metadata": {

10
docs/modules/agents/tools/examples/serpapi.ipynb
View File

@@ -102,7 +102,15 @@
"id": "e0a1dc1c",
"metadata": {},
"outputs": [],
"source": []
"source": [
"from langchain.agents import Tool\n",
"# You can create the tool to pass to an agent\n",
"repl_tool = Tool(\n",
" name=\"python_repl\",\n",
" description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
" func=search.run,\n",
")"
]
}
],
"metadata": {

880
docs/modules/callbacks/getting_started.ipynb
View File

File diff suppressed because it is too large Load Diff

30
docs/modules/chains/examples/llm_bash.ipynb
View File

@@ -10,7 +10,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 9,
"metadata": {},
"outputs": [
{
@@ -37,7 +37,7 @@
"'Hello World\\n'"
]
},
"execution_count": 1,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -50,7 +50,7 @@
"\n",
"text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
"\n",
"bash_chain = LLMBashChain(llm=llm, verbose=True)\n",
"bash_chain = LLMBashChain.from_llm(llm, verbose=True)\n",
"\n",
"bash_chain.run(text)"
]
@@ -65,11 +65,12 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts.prompt import PromptTemplate\n",
"from langchain.chains.llm_bash.prompt import BashOutputParser\n",
"\n",
"_PROMPT_TEMPLATE = \"\"\"If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put \"#!/bin/bash\" in your answer. Make sure to reason step by step, using this format:\n",
"Question: \"copy the files in the directory named 'target' into a new directory at the same level as target called 'myNewDirectory'\"\n",
@@ -88,12 +89,12 @@
"That is the format. Begin!\n",
"Question: {question}\"\"\"\n",
"\n",
"PROMPT = PromptTemplate(input_variables=[\"question\"], template=_PROMPT_TEMPLATE)"
"PROMPT = PromptTemplate(input_variables=[\"question\"], template=_PROMPT_TEMPLATE, output_parser=BashOutputParser())"
]
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -120,13 +121,13 @@
"'Hello World\\n'"
]
},
"execution_count": 3,
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"bash_chain = LLMBashChain(llm=llm, prompt=PROMPT, verbose=True)\n",
"bash_chain = LLMBashChain.from_llm(llm, prompt=PROMPT, verbose=True)\n",
"\n",
"text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
"\n",
@@ -134,7 +135,6 @@
]
},
{
"attachments": {},
"cell_type": "markdown",
"metadata": {},
"source": [
@@ -145,7 +145,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 12,
"metadata": {},
"outputs": [
{
@@ -177,7 +177,7 @@
"'api.ipynb\\t\\t\\tllm_summarization_checker.ipynb\\r\\nconstitutional_chain.ipynb\\tmoderation.ipynb\\r\\nllm_bash.ipynb\\t\\t\\topenai_openapi.yaml\\r\\nllm_checker.ipynb\\t\\topenapi.ipynb\\r\\nllm_math.ipynb\\t\\t\\tpal.ipynb\\r\\nllm_requests.ipynb\\t\\tsqlite.ipynb'"
]
},
"execution_count": 4,
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -187,7 +187,7 @@
"\n",
"\n",
"persistent_process = BashProcess(persistent=True)\n",
"bash_chain = LLMBashChain.from_bash_process(llm=llm, bash_process=persistent_process, verbose=True)\n",
"bash_chain = LLMBashChain.from_llm(llm, bash_process=persistent_process, verbose=True)\n",
"\n",
"text = \"List the current directory then move up a level.\"\n",
"\n",
@@ -196,7 +196,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 13,
"metadata": {},
"outputs": [
{
@@ -224,7 +224,7 @@
"'examples\\t\\tgetting_started.ipynb\\tindex_examples\\r\\ngeneric\\t\\t\\thow_to_guides.rst'"
]
},
"execution_count": 5,
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
@@ -258,7 +258,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.16"
"version": "3.9.1"
}
},
"nbformat": 4,

22
docs/modules/chains/examples/llm_checker.ipynb
View File

@@ -23,28 +23,16 @@
"\n",
"\n",
"\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
"\u001b[1mChain 0\u001b[0m:\n",
"{'statement': '\\nNone. Mammals do not lay eggs.'}\n",
"\n",
"\u001b[1mChain 1\u001b[0m:\n",
"{'assertions': '\\n• Mammals reproduce using live birth\\n• Mammals do not lay eggs\\n• Animals that lay eggs are not mammals'}\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\u001b[1mChain 2\u001b[0m:\n",
"{'checked_assertions': '\\n1. True\\n\\n2. True\\n\\n3. False - Mammals are a class of animals that includes animals that lay eggs, such as monotremes (platypus and echidna).'}\n",
"\n",
"\u001b[1mChain 3\u001b[0m:\n",
"{'revised_statement': ' Monotremes, such as the platypus and echidna, lay the biggest eggs of any mammal.'}\n",
"\n",
"\n",
"\u001b[1m> Finished SequentialChain chain.\u001b[0m\n",
"\n",
"\u001b[1m> Finished LLMCheckerChain chain.\u001b[0m\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' Monotremes, such as the platypus and echidna, lay the biggest eggs of any mammal.'"
"' No mammal lays the biggest eggs. The Elephant Bird, which was a species of giant bird, laid the largest eggs of any bird.'"
]
},
"execution_count": 1,
@@ -60,7 +48,7 @@
"\n",
"text = \"What type of mammal lays the biggest eggs?\"\n",
"\n",
"checker_chain = LLMCheckerChain(llm=llm, verbose=True)\n",
"checker_chain = LLMCheckerChain.from_llm(llm, verbose=True)\n",
"\n",
"checker_chain.run(text)"
]
@@ -89,7 +77,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

116
docs/modules/chains/examples/llm_math.ipynb
View File

@@ -12,7 +12,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 4,
"id": "44e9ba31",
"metadata": {},
"outputs": [
@@ -24,23 +24,22 @@
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"What is 13 raised to the .3432 power?\u001b[32;1m\u001b[1;3m\n",
"```python\n",
"import math\n",
"print(math.pow(13, .3432))\n",
"```text\n",
"13 ** .3432\n",
"```\n",
"...numexpr.evaluate(\"13 ** .3432\")...\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Answer: 2.4116004626599237\\n'"
"'Answer: 2.4116004626599237'"
]
},
"execution_count": 1,
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
@@ -49,102 +48,7 @@
"from langchain import OpenAI, LLMMathChain\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"llm_math = LLMMathChain(llm=llm, verbose=True)\n",
"\n",
"llm_math.run(\"What is 13 raised to the .3432 power?\")"
]
},
{
"cell_type": "markdown",
"id": "2bdd5fc6",
"metadata": {},
"source": [
"## Customize Prompt\n",
"You can also customize the prompt that is used. Here is an example prompting it to use numpy"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "76be17b0",
"metadata": {},
"outputs": [],
"source": [
"from langchain.prompts.prompt import PromptTemplate\n",
"\n",
"_PROMPT_TEMPLATE = \"\"\"You are GPT-3, and you can't do math.\n",
"\n",
"You can do basic math, and your memorization abilities are impressive, but you can't do any complex calculations that a human could not do in their head. You also have an annoying tendency to just make up highly specific, but wrong, answers.\n",
"\n",
"So we hooked you up to a Python 3 kernel, and now you can execute code. If you execute code, you must print out the final answer using the print function. You MUST use the python package numpy to answer your question. You must import numpy as np.\n",
"\n",
"\n",
"Question: ${{Question with hard calculation.}}\n",
"```python\n",
"${{Code that prints what you need to know}}\n",
"print(${{code}})\n",
"```\n",
"```output\n",
"${{Output of your code}}\n",
"```\n",
"Answer: ${{Answer}}\n",
"\n",
"Begin.\n",
"\n",
"Question: What is 37593 * 67?\n",
"\n",
"```python\n",
"import numpy as np\n",
"print(np.multiply(37593, 67))\n",
"```\n",
"```output\n",
"2518731\n",
"```\n",
"Answer: 2518731\n",
"\n",
"Question: {question}\"\"\"\n",
"\n",
"PROMPT = PromptTemplate(input_variables=[\"question\"], template=_PROMPT_TEMPLATE)"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "0c42faa0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"What is 13 raised to the .3432 power?\u001b[32;1m\u001b[1;3m\n",
"\n",
"```python\n",
"import numpy as np\n",
"print(np.power(13, .3432))\n",
"```\n",
"\u001b[0m\n",
"Answer: \u001b[33;1m\u001b[1;3m2.4116004626599237\n",
"\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Answer: 2.4116004626599237\\n'"
]
},
"execution_count": 25,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"llm_math = LLMMathChain(llm=llm, prompt=PROMPT, verbose=True)\n",
"llm_math = LLMMathChain.from_llm(llm, verbose=True)\n",
"\n",
"llm_math.run(\"What is 13 raised to the .3432 power?\")"
]
@@ -152,7 +56,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "0c62951b",
"id": "e978bb8e",
"metadata": {},
"outputs": [],
"source": []
@@ -174,7 +78,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

61
docs/modules/chains/examples/llm_summarization_checker.ipynb
View File

@@ -221,11 +221,11 @@
"\n",
"• The light from these galaxies has been traveling for over 13 billion years to reach us. - True \n",
"\n",
"• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. - False. The first exoplanet was discovered in 1992, but the first images of exoplanets were taken by the Hubble Space Telescope in 1995. \n",
"• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. - False. The first exoplanet was discovered in 1992, but the first images of exoplanets were taken by the Hubble Space Telescope in 2004. \n",
"\n",
"• Exoplanets were first discovered in 1992. - True \n",
"\n",
"• The JWST has allowed us to see exoplanets in greater detail. - Undetermined. It is too early to tell as the JWST has not been launched yet.\n",
"• The JWST has allowed us to see exoplanets in greater detail. - Undetermined. The JWST has not yet been launched, so it is not yet known how much detail it will be able to provide.\n",
"\"\"\"\n",
"\n",
"Original Summary:\n",
@@ -296,11 +296,11 @@
"\n",
"• The light from these galaxies has been traveling for over 13 billion years to reach us. - True \n",
"\n",
"• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. - False. The first exoplanet was discovered in 1992, but the first images of exoplanets were taken by the Hubble Space Telescope in 1995. \n",
"• JWST has provided us with the first images of exoplanets, which are planets outside of our own solar system. - False. The first exoplanet was discovered in 1992, but the first images of exoplanets were taken by the Hubble Space Telescope in 2004. \n",
"\n",
"• Exoplanets were first discovered in 1992. - True \n",
"\n",
"• The JWST has allowed us to see exoplanets in greater detail. - Undetermined. It is too early to tell as the JWST has not been launched yet.\n",
"• The JWST has allowed us to see exoplanets in greater detail. - Undetermined. The JWST has not yet been launched, so it is not yet known how much detail it will be able to provide.\n",
"\"\"\"\n",
"Result:\u001b[0m\n",
"\n",
@@ -312,7 +312,7 @@
"Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):\n",
"• In 2023, The JWST will spot a number of galaxies nicknamed \"green peas.\" They were given this name because they are small, round, and green, like peas.\n",
"• The telescope will capture images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.\n",
"• Exoplanets, which are planets outside of our own solar system, were first discovered in 1992. The JWST will allow us to see them in greater detail than ever before.\n",
"• Exoplanets, which are planets outside of our own solar system, were first discovered in 1992. The JWST will allow us to see them in greater detail when it is launched in 2023.\n",
"These discoveries can spark a child's imagination about the infinite wonders of the universe.\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
@@ -321,7 +321,7 @@
{
"data": {
"text/plain": [
"'Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):\\n• In 2023, The JWST will spot a number of galaxies nicknamed \"green peas.\" They were given this name because they are small, round, and green, like peas.\\n• The telescope will capture images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.\\n• Exoplanets, which are planets outside of our own solar system, were first discovered in 1992. The JWST will allow us to see them in greater detail than ever before.\\nThese discoveries can spark a child\\'s imagination about the infinite wonders of the universe.'"
"'Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):\\n• In 2023, The JWST will spot a number of galaxies nicknamed \"green peas.\" They were given this name because they are small, round, and green, like peas.\\n• The telescope will capture images of galaxies that are over 13 billion years old. This means that the light from these galaxies has been traveling for over 13 billion years to reach us.\\n• Exoplanets, which are planets outside of our own solar system, were first discovered in 1992. The JWST will allow us to see them in greater detail when it is launched in 2023.\\nThese discoveries can spark a child\\'s imagination about the infinite wonders of the universe.'"
]
},
"execution_count": 1,
@@ -334,7 +334,7 @@
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"checker_chain = LLMSummarizationCheckerChain(llm=llm, verbose=True, max_checks=2)\n",
"checker_chain = LLMSummarizationCheckerChain.from_llm(llm, verbose=True, max_checks=2)\n",
"text = \"\"\"\n",
"Your 9-year old might like these recent discoveries made by The James Webb Space Telescope (JWST):\n",
"• In 2023, The JWST spotted a number of galaxies nicknamed \"green peas.\" They were given this name because they are small, round, and green, like peas.\n",
@@ -407,7 +407,8 @@
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.\n",
"\n",
"Checked Assertions:\"\"\"\n",
"Checked Assertions:\n",
"\"\"\"\n",
"\n",
"- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True\n",
"\n",
@@ -428,7 +429,8 @@
"- It is considered the northern branch of the Norwegian Sea. True\n",
"\"\"\"\n",
"\n",
"Original Summary:\"\"\"\n",
"Original Summary:\n",
"\"\"\"\n",
"The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. It is the smallest of the five oceans and is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea.\n",
"\"\"\"\n",
"\n",
@@ -443,7 +445,7 @@
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true of false.\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true or false.\n",
"\n",
"If all of the assertions are true, return \"True\". If any of the assertions are false, return \"False\".\n",
"\n",
@@ -555,7 +557,8 @@
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.\n",
"\n",
"Checked Assertions:\"\"\"\n",
"Checked Assertions:\n",
"\"\"\"\n",
"\n",
"- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True\n",
"\n",
@@ -574,7 +577,8 @@
"- It is considered the northern branch of the Norwegian Sea. False - It is considered the northern branch of the Atlantic Ocean.\n",
"\"\"\"\n",
"\n",
"Original Summary:\"\"\"\n",
"Original Summary:\n",
"\"\"\"\n",
"\n",
"The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea.\n",
"\"\"\"\n",
@@ -583,14 +587,20 @@
"\n",
"The output should have the same structure and formatting as the original summary.\n",
"\n",
"Summary:\u001b[0m\n",
"Summary:\u001b[0m\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n",
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true of false.\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true or false.\n",
"\n",
"If all of the assertions are true, return \"True\". If any of the assertions are false, return \"False\".\n",
"\n",
@@ -701,7 +711,8 @@
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true of false. If the answer is false, a suggestion is given for a correction.\n",
"\n",
"Checked Assertions:\"\"\"\n",
"Checked Assertions:\n",
"\"\"\"\n",
"\n",
"- The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. True\n",
"\n",
@@ -718,7 +729,8 @@
"- It is considered the northern branch of the Atlantic Ocean. False - The Greenland Sea is considered part of the Arctic Ocean, not the Atlantic Ocean.\n",
"\"\"\"\n",
"\n",
"Original Summary:\"\"\"\n",
"Original Summary:\n",
"\"\"\"\n",
"\n",
"\n",
"The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is an arm of the Arctic Ocean. It is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the country of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Atlantic Ocean.\n",
@@ -735,7 +747,7 @@
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true of false.\n",
"\u001b[32;1m\u001b[1;3mBelow are some assertions that have been fact checked and are labeled as true or false.\n",
"\n",
"If all of the assertions are true, return \"True\". If any of the assertions are false, return \"False\".\n",
"\n",
@@ -813,14 +825,14 @@
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"checker_chain = LLMSummarizationCheckerChain(llm=llm, verbose=True, max_checks=3)\n",
"checker_chain = LLMSummarizationCheckerChain.from_llm(llm, verbose=True, max_checks=3)\n",
"text = \"The Greenland Sea is an outlying portion of the Arctic Ocean located between Iceland, Norway, the Svalbard archipelago and Greenland. It has an area of 465,000 square miles and is one of five oceans in the world, alongside the Pacific Ocean, Atlantic Ocean, Indian Ocean, and the Southern Ocean. It is the smallest of the five oceans and is covered almost entirely by water, some of which is frozen in the form of glaciers and icebergs. The sea is named after the island of Greenland, and is the Arctic Ocean's main outlet to the Atlantic. It is often frozen over so navigation is limited, and is considered the northern branch of the Norwegian Sea.\"\n",
"checker_chain.run(text)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 3,
"metadata": {},
"outputs": [
{
@@ -1077,7 +1089,7 @@
"'Birds are not mammals, but they are a class of their own. They lay eggs, unlike mammals which give birth to live young.'"
]
},
"execution_count": 2,
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
@@ -1087,17 +1099,10 @@
"from langchain.llms import OpenAI\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"checker_chain = LLMSummarizationCheckerChain(llm=llm, max_checks=3, verbose=True)\n",
"checker_chain = LLMSummarizationCheckerChain.from_llm(llm, max_checks=3, verbose=True)\n",
"text = \"Mammals can lay eggs, birds can lay eggs, therefore birds are mammals.\"\n",
"checker_chain.run(text)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {

32
docs/modules/chains/examples/pal.ipynb
View File

@@ -28,7 +28,7 @@
"metadata": {},
"outputs": [],
"source": [
"llm = OpenAI(model_name='code-davinci-002', temperature=0, max_tokens=512)"
"llm = OpenAI(temperature=0, max_tokens=512)"
]
},
{
@@ -63,7 +63,9 @@
"cell_type": "code",
"execution_count": 4,
"id": "3ef64b27",
"metadata": {},
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
@@ -71,17 +73,17 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mdef solution():\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mdef solution():\n",
" \"\"\"Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?\"\"\"\n",
" cindy_pets = 4\n",
" marcia_pets = cindy_pets + 2\n",
" jan_pets = marcia_pets * 3\n",
" total_pets = cindy_pets + marcia_pets + jan_pets\n",
" result = total_pets\n",
" return result\u001B[0m\n",
" return result\u001b[0m\n",
"\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
@@ -139,8 +141,8 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m# Put objects into a list to record ordering\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
"objects = []\n",
"objects += [('booklet', 'blue')] * 2\n",
"objects += [('booklet', 'purple')] * 2\n",
@@ -151,9 +153,9 @@
"\n",
"# Count number of purple objects\n",
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
"answer = num_purple\u001B[0m\n",
"answer = num_purple\u001b[0m\n",
"\n",
"\u001B[1m> Finished PALChain chain.\u001B[0m\n"
"\u001b[1m> Finished PALChain chain.\u001b[0m\n"
]
},
{
@@ -212,8 +214,8 @@
"text": [
"\n",
"\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m# Put objects into a list to record ordering\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
"objects = []\n",
"objects += [('booklet', 'blue')] * 2\n",
"objects += [('booklet', 'purple')] * 2\n",
@@ -224,9 +226,9 @@
"\n",
"# Count number of purple objects\n",
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
"answer = num_purple\u001B[0m\n",
"answer = num_purple\u001b[0m\n",
"\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
"\u001b[1m> Finished chain.\u001b[0m\n"
]
}
],
@@ -280,7 +282,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.9"
"version": "3.9.1"
}
},
"nbformat": 4,

14
docs/modules/chains/examples/sqlite.ipynb
View File

@@ -73,7 +73,7 @@
"metadata": {},
"outputs": [],
"source": [
"db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)"
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
]
},
{
@@ -175,7 +175,7 @@
"metadata": {},
"outputs": [],
"source": [
"db_chain = SQLDatabaseChain(llm=llm, database=db, prompt=PROMPT, verbose=True)"
"db_chain = SQLDatabaseChain.from_llm(llm, db, prompt=PROMPT, verbose=True)"
]
},
{
@@ -230,7 +230,7 @@
"metadata": {},
"outputs": [],
"source": [
"db_chain = SQLDatabaseChain(llm=llm, database=db, prompt=PROMPT, verbose=True, return_intermediate_steps=True)"
"db_chain = SQLDatabaseChain.from_llm(llm, db, prompt=PROMPT, verbose=True, return_intermediate_steps=True)"
]
},
{
@@ -285,7 +285,7 @@
"metadata": {},
"outputs": [],
"source": [
"db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True, top_k=3)"
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True, top_k=3)"
]
},
{
@@ -407,7 +407,7 @@
"metadata": {},
"outputs": [],
"source": [
"db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)"
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
]
},
{
@@ -569,7 +569,7 @@
}
],
"source": [
"db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
"db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)\n",
"db_chain.run(\"What are some example tracks by Bach?\")"
]
},
@@ -681,7 +681,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.10"
"version": "3.9.1"
}
},
"nbformat": 4,

199
docs/modules/chains/generic/custom_chain.ipynb Normal file
View File

@@ -0,0 +1,199 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "593f7553-7038-498e-96d4-8255e5ce34f0",
"metadata": {},
"source": [
"# Creating a custom Chain\n",
"\n",
"To implement your own custom chain you can subclass `Chain` and implement the following methods:"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "c19c736e-ca74-4726-bb77-0a849bcc2960",
"metadata": {
"tags": [],
"vscode": {
"languageId": "python"
}
},
"outputs": [],
"source": [
"from __future__ import annotations\n",
"\n",
"from typing import Any, Dict, List, Optional\n",
"\n",
"from pydantic import Extra\n",
"\n",
"from langchain.base_language import BaseLanguageModel\n",
"from langchain.callbacks.manager import (\n",
" AsyncCallbackManagerForChainRun,\n",
" CallbackManagerForChainRun,\n",
")\n",
"from langchain.chains.base import Chain\n",
"from langchain.prompts.base import BasePromptTemplate\n",
"\n",
"\n",
"class MyCustomChain(Chain):\n",
" \"\"\"\n",
" An example of a custom chain.\n",
" \"\"\"\n",
"\n",
" prompt: BasePromptTemplate\n",
" \"\"\"Prompt object to use.\"\"\"\n",
" llm: BaseLanguageModel\n",
" output_key: str = \"text\" #: :meta private:\n",
"\n",
" class Config:\n",
" \"\"\"Configuration for this pydantic object.\"\"\"\n",
"\n",
" extra = Extra.forbid\n",
" arbitrary_types_allowed = True\n",
"\n",
" @property\n",
" def input_keys(self) -> List[str]:\n",
" \"\"\"Will be whatever keys the prompt expects.\n",
"\n",
" :meta private:\n",
" \"\"\"\n",
" return self.prompt.input_variables\n",
"\n",
" @property\n",
" def output_keys(self) -> List[str]:\n",
" \"\"\"Will always return text key.\n",
"\n",
" :meta private:\n",
" \"\"\"\n",
" return [self.output_key]\n",
"\n",
" def _call(\n",
" self,\n",
" inputs: Dict[str, Any],\n",
" run_manager: Optional[CallbackManagerForChainRun] = None,\n",
" ) -> Dict[str, str]:\n",
" # Your custom chain logic goes here\n",
" # This is just an example that mimics LLMChain\n",
" prompt_value = self.prompt.format_prompt(**inputs)\n",
" \n",
" # Whenever you call a language model, or another chain, you should pass\n",
" # a callback manager to it. This allows the inner run to be tracked by\n",
" # any callbacks that are registered on the outer run.\n",
" # You can always obtain a callback manager for this by calling\n",
" # `run_manager.get_child()` as shown below.\n",
" response = self.llm.generate_prompt(\n",
" [prompt_value],\n",
" callbacks=run_manager.get_child() if run_manager else None\n",
" )\n",
"\n",
" # If you want to log something about this run, you can do so by calling\n",
" # methods on the `run_manager`, as shown below. This will trigger any\n",
" # callbacks that are registered for that event.\n",
" if run_manager:\n",
" run_manager.on_text(\"Log something about this run\")\n",
" \n",
" return {self.output_key: response.generations[0][0].text}\n",
"\n",
" async def _acall(\n",
" self,\n",
" inputs: Dict[str, Any],\n",
" run_manager: Optional[AsyncCallbackManagerForChainRun] = None,\n",
" ) -> Dict[str, str]:\n",
" # Your custom chain logic goes here\n",
" # This is just an example that mimics LLMChain\n",
" prompt_value = self.prompt.format_prompt(**inputs)\n",
" \n",
" # Whenever you call a language model, or another chain, you should pass\n",
" # a callback manager to it. This allows the inner run to be tracked by\n",
" # any callbacks that are registered on the outer run.\n",
" # You can always obtain a callback manager for this by calling\n",
" # `run_manager.get_child()` as shown below.\n",
" response = await self.llm.agenerate_prompt(\n",
" [prompt_value],\n",
" callbacks=run_manager.get_child() if run_manager else None\n",
" )\n",
"\n",
" # If you want to log something about this run, you can do so by calling\n",
" # methods on the `run_manager`, as shown below. This will trigger any\n",
" # callbacks that are registered for that event.\n",
" if run_manager:\n",
" await run_manager.on_text(\"Log something about this run\")\n",
" \n",
" return {self.output_key: response.generations[0][0].text}\n",
"\n",
" @property\n",
" def _chain_type(self) -> str:\n",
" return \"my_custom_chain\"\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "18361f89",
"metadata": {
"vscode": {
"languageId": "python"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new MyCustomChain chain...\u001b[0m\n",
"Log something about this run\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"'Why did the callback function feel lonely? Because it was always waiting for someone to call it back!'"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"from langchain.callbacks.stdout import StdOutCallbackHandler\n",
"from langchain.chat_models.openai import ChatOpenAI\n",
"from langchain.prompts.prompt import PromptTemplate\n",
"\n",
"\n",
"chain = MyCustomChain(\n",
" prompt=PromptTemplate.from_template('tell us a joke about {topic}'),\n",
" llm=ChatOpenAI()\n",
")\n",
"\n",
"chain.run({'topic': 'callbacks'}, callbacks=[StdOutCallbackHandler()])"
]
}
],
"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
}

3
docs/modules/chains/index_examples/chat_vector_db.ipynb
View File

@@ -589,7 +589,6 @@
"outputs": [],
"source": [
"from langchain.chains.llm import LLMChain\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
"from langchain.chains.question_answering import load_qa_chain\n",
@@ -597,7 +596,7 @@
"# Construct a ConversationalRetrievalChain with a streaming llm for combine docs\n",
"# and a separate, non-streaming llm for question generation\n",
"llm = OpenAI(temperature=0)\n",
"streaming_llm = OpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"streaming_llm = OpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"\n",
"question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
"doc_chain = load_qa_chain(streaming_llm, chain_type=\"stuff\", prompt=QA_PROMPT)\n",

3
docs/modules/models/chat/examples/streaming.ipynb
View File

@@ -80,9 +80,8 @@
}
],
"source": [
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"chat = ChatOpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])"
]
},

3
docs/modules/models/chat/getting_started.ipynb
View File

@@ -373,9 +373,8 @@
}
],
"source": [
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"chat = ChatOpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])\n"
]
},

25
docs/modules/models/llms/examples/custom_llm.ipynb
View File

@@ -22,18 +22,20 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 6,
"id": "a65696a0",
"metadata": {},
"outputs": [],
"source": [
"from langchain.llms.base import LLM\n",
"from typing import Optional, List, Mapping, Any"
"from typing import Any, List, Mapping, Optional\n",
"\n",
"from langchain.callbacks.manager import CallbackManagerForLLMRun\n",
"from langchain.llms.base import LLM"
]
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 7,
"id": "d5ceff02",
"metadata": {},
"outputs": [],
@@ -46,7 +48,12 @@
" def _llm_type(self) -> str:\n",
" return \"custom\"\n",
" \n",
" def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:\n",
" def _call(\n",
" self,\n",
" prompt: str,\n",
" stop: Optional[List[str]] = None,\n",
" run_manager: Optional[CallbackManagerForLLMRun] = None,\n",
" ) -> str:\n",
" if stop is not None:\n",
" raise ValueError(\"stop kwargs are not permitted.\")\n",
" return prompt[:self.n]\n",
@@ -67,7 +74,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 8,
"id": "10e5ece6",
"metadata": {},
"outputs": [],
@@ -77,7 +84,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 9,
"id": "8cd49199",
"metadata": {},
"outputs": [
@@ -87,7 +94,7 @@
"'This is a '"
]
},
"execution_count": 4,
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
@@ -106,7 +113,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 10,
"id": "9c33fa19",
"metadata": {},
"outputs": [

17
docs/modules/models/llms/examples/streaming_llm.ipynb
View File

@@ -12,7 +12,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "4ac0ff54-540a-4f2b-8d9a-b590fec7fe07",
"metadata": {
"tags": []
@@ -21,14 +21,13 @@
"source": [
"from langchain.llms import OpenAI, Anthropic\n",
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
"from langchain.schema import HumanMessage"
]
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"id": "77f60a4b-f786-41f2-972e-e5bb8a48dcd5",
"metadata": {
"tags": []
@@ -79,7 +78,7 @@
}
],
"source": [
"llm = OpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"llm = OpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"resp = llm(\"Write me a song about sparkling water.\")"
]
},
@@ -95,7 +94,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"id": "a35373f1-9ee6-4753-a343-5aee749b8527",
"metadata": {
"tags": []
@@ -136,7 +135,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": null,
"id": "22665f16-e05b-473c-a4bd-ad75744ea024",
"metadata": {
"tags": []
@@ -191,7 +190,7 @@
}
],
"source": [
"chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"chat = ChatOpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])"
]
},
@@ -205,7 +204,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"id": "eadae4ba-9f21-4ec8-845d-dd43b0edc2dc",
"metadata": {
"tags": []
@@ -245,7 +244,7 @@
}
],
"source": [
"llm = Anthropic(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
"llm = Anthropic(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0)\n",
"llm(\"Write me a song about sparkling water.\")"
]
}

5
docs/modules/models/llms/integrations/gpt4all.ipynb
View File

@@ -40,7 +40,6 @@
"source": [
"from langchain import PromptTemplate, LLMChain\n",
"from langchain.llms import GPT4All\n",
"from langchain.callbacks.base import CallbackManager\n",
"from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler"
]
},
@@ -124,9 +123,9 @@
"outputs": [],
"source": [
"# Callbacks support token-wise streaming\n",
"callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])\n",
"callbacks = [StreamingStdOutCallbackHandler()]\n",
"# Verbose is required to pass to the callback manager\n",
"llm = GPT4All(model=local_path, callback_manager=callback_manager, verbose=True)"
"llm = GPT4All(model=local_path, callbacks=callbacks, verbose=True)"
]
},
{

14
docs/tracing.md
View File

@@ -6,16 +6,15 @@ 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](./tracing/local_installation.md)
- [Cloud Hosted Setup](./tracing/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."
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.
![](tracing/homepage.png)
@@ -35,7 +34,7 @@ We can keep on clicking further and further down to explore deeper and deeper.
![](tracing/explore.png)
We can also click on the "Explore" button of the top level run to dive even 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.
![](tracing/explore_trace.png)
@@ -46,11 +45,12 @@ For example, here is the lowest level trace with the exact inputs/outputs to the
![](tracing/explore_llm.png)
## 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_HANDLER"] = "langchain"
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.
```

257
docs/tracing/agent_with_tracing.ipynb
View File

@@ -5,7 +5,14 @@
"id": "5371a9bb",
"metadata": {},
"source": [
"# Tracing Walkthrough"
"# 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."
]
},
{
@@ -18,24 +25,22 @@
"outputs": [],
"source": [
"import os\n",
"os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\"\n",
"\n",
"## Uncomment this if using hosted setup.\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 this if you want traces to be recorded to \"my_session\" instead of default.\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 this if using hosted version. Replace \"my_api_key\" with your actual API Key.\n",
"\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"
]
@@ -73,8 +78,7 @@
"\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\n",
"\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",
@@ -104,7 +108,9 @@
"cell_type": "code",
"execution_count": 4,
"id": "4829eb1d",
"metadata": {},
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
@@ -113,52 +119,11 @@
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mQuestion: What is 2 raised to .123243 power?\n",
"Thought: I need a calculator to solve this problem.\n",
"Action:\n",
"```\n",
"{\n",
" \"action\": \"calculator\",\n",
" \"action_input\": \"2^0.123243\"\n",
"}\n",
"```\n",
"\u001b[0m\n",
"Observation: calculator is not a valid tool, try another one.\n",
"\u001b[32;1m\u001b[1;3mI made a mistake, I need to use the correct tool for this question.\n",
"Action:\n",
"```\n",
"{\n",
" \"action\": \"calculator\",\n",
" \"action_input\": \"2^0.123243\"\n",
"}\n",
"```\n",
"\n",
"\u001b[0m\n",
"Observation: calculator is not a valid tool, try another one.\n",
"\u001b[32;1m\u001b[1;3mI made a mistake, the tool name is actually \"calc\" instead of \"calculator\".\n",
"Action:\n",
"```\n",
"{\n",
" \"action\": \"calc\",\n",
" \"action_input\": \"2^0.123243\"\n",
"}\n",
"```\n",
"\n",
"\u001b[0m\n",
"Observation: calc is not a valid tool, try another one.\n",
"\u001b[32;1m\u001b[1;3mI made another mistake, the tool name is actually \"Calculator\" instead of \"calc\".\n",
"Action:\n",
"```\n",
"{\n",
" \"action\": \"Calculator\",\n",
" \"action_input\": \"2^0.123243\"\n",
"}\n",
"```\n",
"\n",
"\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mThe final answer is 1.0891804557407723.\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"
@@ -186,8 +151,182 @@
},
{
"cell_type": "code",
"execution_count": null,
"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",
"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": "code",
"execution_count": null,
"id": "4e46c85b-2ac0-4661-abed-9c2bf3036820",
"metadata": {},
"outputs": [],
"source": []
@@ -209,7 +348,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.1"
"version": "3.10.9"
}
},
"nbformat": 4,