forked from Archives/langchain
Harrison Chase
1 year ago
committed by
GitHub
parent
fe804d2a01
commit
33a001933a
@ -0,0 +1,588 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ClearML Integration\n",
|
||||
"\n",
|
||||
"In order to properly keep track of your langchain experiments and their results, you can enable the ClearML integration. ClearML is an experiment manager that neatly tracks and organizes all your experiment runs.\n",
|
||||
"\n",
|
||||
"<a target=\"_blank\" href=\"https://colab.research.google.com/github/hwchase17/langchain/blob/master/docs/ecosystem/clearml_tracking.ipynb\">\n",
|
||||
" <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
|
||||
"</a>"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Getting API Credentials\n",
|
||||
"\n",
|
||||
"We'll be using quite some APIs in this notebook, here is a list and where to get them:\n",
|
||||
"\n",
|
||||
"- ClearML: https://app.clear.ml/settings/workspace-configuration\n",
|
||||
"- OpenAI: https://platform.openai.com/account/api-keys\n",
|
||||
"- SerpAPI (google search): https://serpapi.com/dashboard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"os.environ[\"CLEARML_API_ACCESS_KEY\"] = \"\"\n",
|
||||
"os.environ[\"CLEARML_API_SECRET_KEY\"] = \"\"\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
|
||||
"os.environ[\"SERPAPI_API_KEY\"] = \"\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Setting Up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install clearml\n",
|
||||
"!pip install pandas\n",
|
||||
"!pip install textstat\n",
|
||||
"!pip install spacy\n",
|
||||
"!python -m spacy download en_core_web_sm"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"The clearml callback is currently in beta and is subject to change based on updates to `langchain`. Please report any issues to https://github.com/allegroai/clearml/issues with the tag `langchain`.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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",
|
||||
"clearml_callback = ClearMLCallbackHandler(\n",
|
||||
" task_type=\"inference\",\n",
|
||||
" project_name=\"langchain_callback_demo\",\n",
|
||||
" task_name=\"llm\",\n",
|
||||
" tags=[\"test\"],\n",
|
||||
" # Change the following parameters based on the amount of detail you want tracked\n",
|
||||
" visualize=True,\n",
|
||||
" complexity_metrics=True,\n",
|
||||
" stream_logs=True\n",
|
||||
")\n",
|
||||
"manager = CallbackManager([StdOutCallbackHandler(), clearml_callback])\n",
|
||||
"# Get the OpenAI model ready to go\n",
|
||||
"llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Scenario 1: Just an LLM\n",
|
||||
"\n",
|
||||
"First, let's just run a single LLM a few times and capture the resulting prompt-answer conversation in ClearML"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
|
||||
"{'action_records': action name step starts ends errors text_ctr chain_starts \\\n",
|
||||
"0 on_llm_start OpenAI 1 1 0 0 0 0 \n",
|
||||
"1 on_llm_start OpenAI 1 1 0 0 0 0 \n",
|
||||
"2 on_llm_start OpenAI 1 1 0 0 0 0 \n",
|
||||
"3 on_llm_start OpenAI 1 1 0 0 0 0 \n",
|
||||
"4 on_llm_start OpenAI 1 1 0 0 0 0 \n",
|
||||
"5 on_llm_start OpenAI 1 1 0 0 0 0 \n",
|
||||
"6 on_llm_end NaN 2 1 1 0 0 0 \n",
|
||||
"7 on_llm_end NaN 2 1 1 0 0 0 \n",
|
||||
"8 on_llm_end NaN 2 1 1 0 0 0 \n",
|
||||
"9 on_llm_end NaN 2 1 1 0 0 0 \n",
|
||||
"10 on_llm_end NaN 2 1 1 0 0 0 \n",
|
||||
"11 on_llm_end NaN 2 1 1 0 0 0 \n",
|
||||
"12 on_llm_start OpenAI 3 2 1 0 0 0 \n",
|
||||
"13 on_llm_start OpenAI 3 2 1 0 0 0 \n",
|
||||
"14 on_llm_start OpenAI 3 2 1 0 0 0 \n",
|
||||
"15 on_llm_start OpenAI 3 2 1 0 0 0 \n",
|
||||
"16 on_llm_start OpenAI 3 2 1 0 0 0 \n",
|
||||
"17 on_llm_start OpenAI 3 2 1 0 0 0 \n",
|
||||
"18 on_llm_end NaN 4 2 2 0 0 0 \n",
|
||||
"19 on_llm_end NaN 4 2 2 0 0 0 \n",
|
||||
"20 on_llm_end NaN 4 2 2 0 0 0 \n",
|
||||
"21 on_llm_end NaN 4 2 2 0 0 0 \n",
|
||||
"22 on_llm_end NaN 4 2 2 0 0 0 \n",
|
||||
"23 on_llm_end NaN 4 2 2 0 0 0 \n",
|
||||
"\n",
|
||||
" chain_ends llm_starts ... difficult_words linsear_write_formula \\\n",
|
||||
"0 0 1 ... NaN NaN \n",
|
||||
"1 0 1 ... NaN NaN \n",
|
||||
"2 0 1 ... NaN NaN \n",
|
||||
"3 0 1 ... NaN NaN \n",
|
||||
"4 0 1 ... NaN NaN \n",
|
||||
"5 0 1 ... NaN NaN \n",
|
||||
"6 0 1 ... 0.0 5.5 \n",
|
||||
"7 0 1 ... 2.0 6.5 \n",
|
||||
"8 0 1 ... 0.0 5.5 \n",
|
||||
"9 0 1 ... 2.0 6.5 \n",
|
||||
"10 0 1 ... 0.0 5.5 \n",
|
||||
"11 0 1 ... 2.0 6.5 \n",
|
||||
"12 0 2 ... NaN NaN \n",
|
||||
"13 0 2 ... NaN NaN \n",
|
||||
"14 0 2 ... NaN NaN \n",
|
||||
"15 0 2 ... NaN NaN \n",
|
||||
"16 0 2 ... NaN NaN \n",
|
||||
"17 0 2 ... NaN NaN \n",
|
||||
"18 0 2 ... 0.0 5.5 \n",
|
||||
"19 0 2 ... 2.0 6.5 \n",
|
||||
"20 0 2 ... 0.0 5.5 \n",
|
||||
"21 0 2 ... 2.0 6.5 \n",
|
||||
"22 0 2 ... 0.0 5.5 \n",
|
||||
"23 0 2 ... 2.0 6.5 \n",
|
||||
"\n",
|
||||
" gunning_fog text_standard fernandez_huerta szigriszt_pazos \\\n",
|
||||
"0 NaN NaN NaN NaN \n",
|
||||
"1 NaN NaN NaN NaN \n",
|
||||
"2 NaN NaN NaN NaN \n",
|
||||
"3 NaN NaN NaN NaN \n",
|
||||
"4 NaN NaN NaN NaN \n",
|
||||
"5 NaN NaN NaN NaN \n",
|
||||
"6 5.20 5th and 6th grade 133.58 131.54 \n",
|
||||
"7 8.28 6th and 7th grade 115.58 112.37 \n",
|
||||
"8 5.20 5th and 6th grade 133.58 131.54 \n",
|
||||
"9 8.28 6th and 7th grade 115.58 112.37 \n",
|
||||
"10 5.20 5th and 6th grade 133.58 131.54 \n",
|
||||
"11 8.28 6th and 7th grade 115.58 112.37 \n",
|
||||
"12 NaN NaN NaN NaN \n",
|
||||
"13 NaN NaN NaN NaN \n",
|
||||
"14 NaN NaN NaN NaN \n",
|
||||
"15 NaN NaN NaN NaN \n",
|
||||
"16 NaN NaN NaN NaN \n",
|
||||
"17 NaN NaN NaN NaN \n",
|
||||
"18 5.20 5th and 6th grade 133.58 131.54 \n",
|
||||
"19 8.28 6th and 7th grade 115.58 112.37 \n",
|
||||
"20 5.20 5th and 6th grade 133.58 131.54 \n",
|
||||
"21 8.28 6th and 7th grade 115.58 112.37 \n",
|
||||
"22 5.20 5th and 6th grade 133.58 131.54 \n",
|
||||
"23 8.28 6th and 7th grade 115.58 112.37 \n",
|
||||
"\n",
|
||||
" gutierrez_polini crawford gulpease_index osman \n",
|
||||
"0 NaN NaN NaN NaN \n",
|
||||
"1 NaN NaN NaN NaN \n",
|
||||
"2 NaN NaN NaN NaN \n",
|
||||
"3 NaN NaN NaN NaN \n",
|
||||
"4 NaN NaN NaN NaN \n",
|
||||
"5 NaN NaN NaN NaN \n",
|
||||
"6 62.30 -0.2 79.8 116.91 \n",
|
||||
"7 54.83 1.4 72.1 100.17 \n",
|
||||
"8 62.30 -0.2 79.8 116.91 \n",
|
||||
"9 54.83 1.4 72.1 100.17 \n",
|
||||
"10 62.30 -0.2 79.8 116.91 \n",
|
||||
"11 54.83 1.4 72.1 100.17 \n",
|
||||
"12 NaN NaN NaN NaN \n",
|
||||
"13 NaN NaN NaN NaN \n",
|
||||
"14 NaN NaN NaN NaN \n",
|
||||
"15 NaN NaN NaN NaN \n",
|
||||
"16 NaN NaN NaN NaN \n",
|
||||
"17 NaN NaN NaN NaN \n",
|
||||
"18 62.30 -0.2 79.8 116.91 \n",
|
||||
"19 54.83 1.4 72.1 100.17 \n",
|
||||
"20 62.30 -0.2 79.8 116.91 \n",
|
||||
"21 54.83 1.4 72.1 100.17 \n",
|
||||
"22 62.30 -0.2 79.8 116.91 \n",
|
||||
"23 54.83 1.4 72.1 100.17 \n",
|
||||
"\n",
|
||||
"[24 rows x 39 columns], 'session_analysis': prompt_step prompts name output_step \\\n",
|
||||
"0 1 Tell me a joke OpenAI 2 \n",
|
||||
"1 1 Tell me a poem OpenAI 2 \n",
|
||||
"2 1 Tell me a joke OpenAI 2 \n",
|
||||
"3 1 Tell me a poem OpenAI 2 \n",
|
||||
"4 1 Tell me a joke OpenAI 2 \n",
|
||||
"5 1 Tell me a poem OpenAI 2 \n",
|
||||
"6 3 Tell me a joke OpenAI 4 \n",
|
||||
"7 3 Tell me a poem OpenAI 4 \n",
|
||||
"8 3 Tell me a joke OpenAI 4 \n",
|
||||
"9 3 Tell me a poem OpenAI 4 \n",
|
||||
"10 3 Tell me a joke OpenAI 4 \n",
|
||||
"11 3 Tell me a poem OpenAI 4 \n",
|
||||
"\n",
|
||||
" output \\\n",
|
||||
"0 \\n\\nQ: What did the fish say when it hit the w... \n",
|
||||
"1 \\n\\nRoses are red,\\nViolets are blue,\\nSugar i... \n",
|
||||
"2 \\n\\nQ: What did the fish say when it hit the w... \n",
|
||||
"3 \\n\\nRoses are red,\\nViolets are blue,\\nSugar i... \n",
|
||||
"4 \\n\\nQ: What did the fish say when it hit the w... \n",
|
||||
"5 \\n\\nRoses are red,\\nViolets are blue,\\nSugar i... \n",
|
||||
"6 \\n\\nQ: What did the fish say when it hit the w... \n",
|
||||
"7 \\n\\nRoses are red,\\nViolets are blue,\\nSugar i... \n",
|
||||
"8 \\n\\nQ: What did the fish say when it hit the w... \n",
|
||||
"9 \\n\\nRoses are red,\\nViolets are blue,\\nSugar i... \n",
|
||||
"10 \\n\\nQ: What did the fish say when it hit the w... \n",
|
||||
"11 \\n\\nRoses are red,\\nViolets are blue,\\nSugar i... \n",
|
||||
"\n",
|
||||
" token_usage_total_tokens token_usage_prompt_tokens \\\n",
|
||||
"0 162 24 \n",
|
||||
"1 162 24 \n",
|
||||
"2 162 24 \n",
|
||||
"3 162 24 \n",
|
||||
"4 162 24 \n",
|
||||
"5 162 24 \n",
|
||||
"6 162 24 \n",
|
||||
"7 162 24 \n",
|
||||
"8 162 24 \n",
|
||||
"9 162 24 \n",
|
||||
"10 162 24 \n",
|
||||
"11 162 24 \n",
|
||||
"\n",
|
||||
" token_usage_completion_tokens flesch_reading_ease flesch_kincaid_grade \\\n",
|
||||
"0 138 109.04 1.3 \n",
|
||||
"1 138 83.66 4.8 \n",
|
||||
"2 138 109.04 1.3 \n",
|
||||
"3 138 83.66 4.8 \n",
|
||||
"4 138 109.04 1.3 \n",
|
||||
"5 138 83.66 4.8 \n",
|
||||
"6 138 109.04 1.3 \n",
|
||||
"7 138 83.66 4.8 \n",
|
||||
"8 138 109.04 1.3 \n",
|
||||
"9 138 83.66 4.8 \n",
|
||||
"10 138 109.04 1.3 \n",
|
||||
"11 138 83.66 4.8 \n",
|
||||
"\n",
|
||||
" ... difficult_words linsear_write_formula gunning_fog \\\n",
|
||||
"0 ... 0 5.5 5.20 \n",
|
||||
"1 ... 2 6.5 8.28 \n",
|
||||
"2 ... 0 5.5 5.20 \n",
|
||||
"3 ... 2 6.5 8.28 \n",
|
||||
"4 ... 0 5.5 5.20 \n",
|
||||
"5 ... 2 6.5 8.28 \n",
|
||||
"6 ... 0 5.5 5.20 \n",
|
||||
"7 ... 2 6.5 8.28 \n",
|
||||
"8 ... 0 5.5 5.20 \n",
|
||||
"9 ... 2 6.5 8.28 \n",
|
||||
"10 ... 0 5.5 5.20 \n",
|
||||
"11 ... 2 6.5 8.28 \n",
|
||||
"\n",
|
||||
" text_standard fernandez_huerta szigriszt_pazos gutierrez_polini \\\n",
|
||||
"0 5th and 6th grade 133.58 131.54 62.30 \n",
|
||||
"1 6th and 7th grade 115.58 112.37 54.83 \n",
|
||||
"2 5th and 6th grade 133.58 131.54 62.30 \n",
|
||||
"3 6th and 7th grade 115.58 112.37 54.83 \n",
|
||||
"4 5th and 6th grade 133.58 131.54 62.30 \n",
|
||||
"5 6th and 7th grade 115.58 112.37 54.83 \n",
|
||||
"6 5th and 6th grade 133.58 131.54 62.30 \n",
|
||||
"7 6th and 7th grade 115.58 112.37 54.83 \n",
|
||||
"8 5th and 6th grade 133.58 131.54 62.30 \n",
|
||||
"9 6th and 7th grade 115.58 112.37 54.83 \n",
|
||||
"10 5th and 6th grade 133.58 131.54 62.30 \n",
|
||||
"11 6th and 7th grade 115.58 112.37 54.83 \n",
|
||||
"\n",
|
||||
" crawford gulpease_index osman \n",
|
||||
"0 -0.2 79.8 116.91 \n",
|
||||
"1 1.4 72.1 100.17 \n",
|
||||
"2 -0.2 79.8 116.91 \n",
|
||||
"3 1.4 72.1 100.17 \n",
|
||||
"4 -0.2 79.8 116.91 \n",
|
||||
"5 1.4 72.1 100.17 \n",
|
||||
"6 -0.2 79.8 116.91 \n",
|
||||
"7 1.4 72.1 100.17 \n",
|
||||
"8 -0.2 79.8 116.91 \n",
|
||||
"9 1.4 72.1 100.17 \n",
|
||||
"10 -0.2 79.8 116.91 \n",
|
||||
"11 1.4 72.1 100.17 \n",
|
||||
"\n",
|
||||
"[12 rows x 24 columns]}\n",
|
||||
"2023-03-29 14:00:25,948 - clearml.Task - INFO - Completed model upload to https://files.clear.ml/langchain_callback_demo/llm.988bd727b0e94a29a3ac0ee526813545/models/simple_sequential\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# SCENARIO 1 - LLM\n",
|
||||
"llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"] * 3)\n",
|
||||
"# After every generation run, use flush to make sure all the metrics\n",
|
||||
"# prompts and other output are properly saved separately\n",
|
||||
"clearml_callback.flush_tracker(langchain_asset=llm, name=\"simple_sequential\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"At this point you can already go to https://app.clear.ml and take a look at the resulting ClearML Task that was created.\n",
|
||||
"\n",
|
||||
"Among others, you should see that this notebook is saved along with any git information. The model JSON that contains the used parameters is saved as an artifact, there are also console logs and under the plots section, you'll find tables that represent the flow of the chain.\n",
|
||||
"\n",
|
||||
"Finally, if you enabled visualizations, these are stored as HTML files under debug samples."
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Scenario 2: Creating a agent with tools\n",
|
||||
"\n",
|
||||
"To show a more advanced workflow, let's create an agent with access to tools. The way ClearML tracks the results is not different though, only the table will look slightly different as there are other types of actions taken when compared to the earlier, simpler example.\n",
|
||||
"\n",
|
||||
"You can now also see the use of the `finish=True` keyword, which will fully close the ClearML Task, instead of just resetting the parameters and prompts for a new conversation."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"{'action': 'on_chain_start', 'name': 'AgentExecutor', 'step': 1, 'starts': 1, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 0, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'input': 'Who is the wife of the person who sang summer of 69?'}\n",
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 2, 'starts': 2, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought:'}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 189, 'token_usage_completion_tokens': 34, 'token_usage_total_tokens': 223, 'model_name': 'text-davinci-003', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 91.61, 'flesch_kincaid_grade': 3.8, 'smog_index': 0.0, 'coleman_liau_index': 3.41, 'automated_readability_index': 3.5, 'dale_chall_readability_score': 6.06, 'difficult_words': 2, 'linsear_write_formula': 5.75, 'gunning_fog': 5.4, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 121.07, 'szigriszt_pazos': 119.5, 'gutierrez_polini': 54.91, 'crawford': 0.9, 'gulpease_index': 72.7, 'osman': 92.16}\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out who sang summer of 69 and then find out who their wife is.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Who sang summer of 69\"\u001b[0m{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who sang summer of 69', 'log': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'step': 4, 'starts': 3, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 1, 'tool_ends': 0, 'agent_ends': 0}\n",
|
||||
"{'action': 'on_tool_start', 'input_str': 'Who sang summer of 69', 'name': 'Search', 'description': 'A search engine. Useful for when you need to answer questions about current events. Input should be a search query.', 'step': 5, 'starts': 4, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 0, 'agent_ends': 0}\n",
|
||||
"\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mBryan Adams - Summer Of 69 (Official Music Video).\u001b[0m\n",
|
||||
"Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams - Summer Of 69 (Official Music Video).', 'step': 6, 'starts': 4, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0}\n",
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 7, 'starts': 5, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"\\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\\nThought:'}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 242, 'token_usage_completion_tokens': 28, 'token_usage_total_tokens': 270, 'model_name': 'text-davinci-003', 'step': 8, 'starts': 5, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'text': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 94.66, 'flesch_kincaid_grade': 2.7, 'smog_index': 0.0, 'coleman_liau_index': 4.73, 'automated_readability_index': 4.0, 'dale_chall_readability_score': 7.16, 'difficult_words': 2, 'linsear_write_formula': 4.25, 'gunning_fog': 4.2, 'text_standard': '4th and 5th grade', 'fernandez_huerta': 124.13, 'szigriszt_pazos': 119.2, 'gutierrez_polini': 52.26, 'crawford': 0.7, 'gulpease_index': 74.7, 'osman': 84.2}\n",
|
||||
"\u001b[32;1m\u001b[1;3m I need to find out who Bryan Adams is married to.\n",
|
||||
"Action: Search\n",
|
||||
"Action Input: \"Who is Bryan Adams married to\"\u001b[0m{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who is Bryan Adams married to', 'log': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'step': 9, 'starts': 6, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 3, 'tool_ends': 1, 'agent_ends': 0}\n",
|
||||
"{'action': 'on_tool_start', 'input_str': 'Who is Bryan Adams married to', 'name': 'Search', 'description': 'A search engine. Useful for when you need to answer questions about current events. Input should be a search query.', 'step': 10, 'starts': 7, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 1, 'agent_ends': 0}\n",
|
||||
"\n",
|
||||
"Observation: \u001b[36;1m\u001b[1;3mBryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...\u001b[0m\n",
|
||||
"Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...', 'step': 11, 'starts': 7, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0}\n",
|
||||
"{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 12, 'starts': 8, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"\\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\\nThought: I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"\\nObservation: Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...\\nThought:'}\n",
|
||||
"{'action': 'on_llm_end', 'token_usage_prompt_tokens': 314, 'token_usage_completion_tokens': 18, 'token_usage_total_tokens': 332, 'model_name': 'text-davinci-003', 'step': 13, 'starts': 8, 'ends': 5, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'text': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 81.29, 'flesch_kincaid_grade': 3.7, 'smog_index': 0.0, 'coleman_liau_index': 5.75, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 7.37, 'difficult_words': 1, 'linsear_write_formula': 2.5, 'gunning_fog': 2.8, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 115.7, 'szigriszt_pazos': 110.84, 'gutierrez_polini': 49.79, 'crawford': 0.7, 'gulpease_index': 85.4, 'osman': 83.14}\n",
|
||||
"\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
|
||||
"Final Answer: Bryan Adams has never been married.\u001b[0m\n",
|
||||
"{'action': 'on_agent_finish', 'output': 'Bryan Adams has never been married.', 'log': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'step': 14, 'starts': 8, 'ends': 6, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 1}\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n",
|
||||
"{'action': 'on_chain_end', 'outputs': 'Bryan Adams has never been married.', 'step': 15, 'starts': 8, 'ends': 7, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 1, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 1}\n",
|
||||
"{'action_records': action name step starts ends errors text_ctr \\\n",
|
||||
"0 on_llm_start OpenAI 1 1 0 0 0 \n",
|
||||
"1 on_llm_start OpenAI 1 1 0 0 0 \n",
|
||||
"2 on_llm_start OpenAI 1 1 0 0 0 \n",
|
||||
"3 on_llm_start OpenAI 1 1 0 0 0 \n",
|
||||
"4 on_llm_start OpenAI 1 1 0 0 0 \n",
|
||||
".. ... ... ... ... ... ... ... \n",
|
||||
"66 on_tool_end NaN 11 7 4 0 0 \n",
|
||||
"67 on_llm_start OpenAI 12 8 4 0 0 \n",
|
||||
"68 on_llm_end NaN 13 8 5 0 0 \n",
|
||||
"69 on_agent_finish NaN 14 8 6 0 0 \n",
|
||||
"70 on_chain_end NaN 15 8 7 0 0 \n",
|
||||
"\n",
|
||||
" chain_starts chain_ends llm_starts ... gulpease_index osman input \\\n",
|
||||
"0 0 0 1 ... NaN NaN NaN \n",
|
||||
"1 0 0 1 ... NaN NaN NaN \n",
|
||||
"2 0 0 1 ... NaN NaN NaN \n",
|
||||
"3 0 0 1 ... NaN NaN NaN \n",
|
||||
"4 0 0 1 ... NaN NaN NaN \n",
|
||||
".. ... ... ... ... ... ... ... \n",
|
||||
"66 1 0 2 ... NaN NaN NaN \n",
|
||||
"67 1 0 3 ... NaN NaN NaN \n",
|
||||
"68 1 0 3 ... 85.4 83.14 NaN \n",
|
||||
"69 1 0 3 ... NaN NaN NaN \n",
|
||||
"70 1 1 3 ... NaN NaN NaN \n",
|
||||
"\n",
|
||||
" tool tool_input log \\\n",
|
||||
"0 NaN NaN NaN \n",
|
||||
"1 NaN NaN NaN \n",
|
||||
"2 NaN NaN NaN \n",
|
||||
"3 NaN NaN NaN \n",
|
||||
"4 NaN NaN NaN \n",
|
||||
".. ... ... ... \n",
|
||||
"66 NaN NaN NaN \n",
|
||||
"67 NaN NaN NaN \n",
|
||||
"68 NaN NaN NaN \n",
|
||||
"69 NaN NaN I now know the final answer.\\nFinal Answer: B... \n",
|
||||
"70 NaN NaN NaN \n",
|
||||
"\n",
|
||||
" input_str description output \\\n",
|
||||
"0 NaN NaN NaN \n",
|
||||
"1 NaN NaN NaN \n",
|
||||
"2 NaN NaN NaN \n",
|
||||
"3 NaN NaN NaN \n",
|
||||
"4 NaN NaN NaN \n",
|
||||
".. ... ... ... \n",
|
||||
"66 NaN NaN Bryan Adams has never married. In the 1990s, h... \n",
|
||||
"67 NaN NaN NaN \n",
|
||||
"68 NaN NaN NaN \n",
|
||||
"69 NaN NaN Bryan Adams has never been married. \n",
|
||||
"70 NaN NaN NaN \n",
|
||||
"\n",
|
||||
" outputs \n",
|
||||
"0 NaN \n",
|
||||
"1 NaN \n",
|
||||
"2 NaN \n",
|
||||
"3 NaN \n",
|
||||
"4 NaN \n",
|
||||
".. ... \n",
|
||||
"66 NaN \n",
|
||||
"67 NaN \n",
|
||||
"68 NaN \n",
|
||||
"69 NaN \n",
|
||||
"70 Bryan Adams has never been married. \n",
|
||||
"\n",
|
||||
"[71 rows x 47 columns], 'session_analysis': prompt_step prompts name \\\n",
|
||||
"0 2 Answer the following questions as best you can... OpenAI \n",
|
||||
"1 7 Answer the following questions as best you can... OpenAI \n",
|
||||
"2 12 Answer the following questions as best you can... OpenAI \n",
|
||||
"\n",
|
||||
" output_step output \\\n",
|
||||
"0 3 I need to find out who sang summer of 69 and ... \n",
|
||||
"1 8 I need to find out who Bryan Adams is married... \n",
|
||||
"2 13 I now know the final answer.\\nFinal Answer: B... \n",
|
||||
"\n",
|
||||
" token_usage_total_tokens token_usage_prompt_tokens \\\n",
|
||||
"0 223 189 \n",
|
||||
"1 270 242 \n",
|
||||
"2 332 314 \n",
|
||||
"\n",
|
||||
" token_usage_completion_tokens flesch_reading_ease flesch_kincaid_grade \\\n",
|
||||
"0 34 91.61 3.8 \n",
|
||||
"1 28 94.66 2.7 \n",
|
||||
"2 18 81.29 3.7 \n",
|
||||
"\n",
|
||||
" ... difficult_words linsear_write_formula gunning_fog \\\n",
|
||||
"0 ... 2 5.75 5.4 \n",
|
||||
"1 ... 2 4.25 4.2 \n",
|
||||
"2 ... 1 2.50 2.8 \n",
|
||||
"\n",
|
||||
" text_standard fernandez_huerta szigriszt_pazos gutierrez_polini \\\n",
|
||||
"0 3rd and 4th grade 121.07 119.50 54.91 \n",
|
||||
"1 4th and 5th grade 124.13 119.20 52.26 \n",
|
||||
"2 3rd and 4th grade 115.70 110.84 49.79 \n",
|
||||
"\n",
|
||||
" crawford gulpease_index osman \n",
|
||||
"0 0.9 72.7 92.16 \n",
|
||||
"1 0.7 74.7 84.20 \n",
|
||||
"2 0.7 85.4 83.14 \n",
|
||||
"\n",
|
||||
"[3 rows x 24 columns]}\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Could not update last created model in Task 988bd727b0e94a29a3ac0ee526813545, Task status 'completed' cannot be updated\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.agents import initialize_agent, load_tools\n",
|
||||
"\n",
|
||||
"# SCENARIO 2 - Agent with Tools\n",
|
||||
"tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
|
||||
"agent = initialize_agent(\n",
|
||||
" tools,\n",
|
||||
" llm,\n",
|
||||
" agent=\"zero-shot-react-description\",\n",
|
||||
" callback_manager=manager,\n",
|
||||
" verbose=True,\n",
|
||||
")\n",
|
||||
"agent.run(\n",
|
||||
" \"Who is the wife of the person who sang summer of 69?\"\n",
|
||||
")\n",
|
||||
"clearml_callback.flush_tracker(langchain_asset=agent, name=\"Agent with Tools\", finish=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Tips and Next Steps\n",
|
||||
"\n",
|
||||
"- Make sure you always use a unique `name` argument for the `clearml_callback.flush_tracker` function. If not, the model parameters used for a run will override the previous run!\n",
|
||||
"\n",
|
||||
"- If you close the ClearML Callback using `clearml_callback.flush_tracker(..., finish=True)` the Callback cannot be used anymore. Make a new one if you want to keep logging.\n",
|
||||
"\n",
|
||||
"- Check out the rest of the open source ClearML ecosystem, there is a data version manager, a remote execution agent, automated pipelines and much more!\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": ".venv",
|
||||
"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"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a53ebf4a859167383b364e7e7521d0add3c2dbbdecce4edf676e8c4634ff3fbb"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@ -0,0 +1,515 @@
|
||||
import tempfile
|
||||
from copy import deepcopy
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional, Sequence, Union
|
||||
|
||||
from langchain.callbacks.base import BaseCallbackHandler
|
||||
from langchain.callbacks.utils import (
|
||||
BaseMetadataCallbackHandler,
|
||||
flatten_dict,
|
||||
hash_string,
|
||||
import_pandas,
|
||||
import_spacy,
|
||||
import_textstat,
|
||||
load_json,
|
||||
)
|
||||
from langchain.schema import AgentAction, AgentFinish, LLMResult
|
||||
|
||||
|
||||
def import_clearml() -> Any:
|
||||
try:
|
||||
import clearml # noqa: F401
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"To use the clearml callback manager you need to have the `clearml` python "
|
||||
"package installed. Please install it with `pip install clearml`"
|
||||
)
|
||||
return clearml
|
||||
|
||||
|
||||
class ClearMLCallbackHandler(BaseMetadataCallbackHandler, BaseCallbackHandler):
|
||||
"""Callback Handler that logs to ClearML.
|
||||
|
||||
Parameters:
|
||||
job_type (str): The type of clearml task such as "inference", "testing" or "qc"
|
||||
project_name (str): The clearml project name
|
||||
tags (list): Tags to add to the task
|
||||
task_name (str): Name of the clearml task
|
||||
visualize (bool): Whether to visualize the run.
|
||||
complexity_metrics (bool): Whether to log complexity metrics
|
||||
stream_logs (bool): Whether to stream callback actions to ClearML
|
||||
|
||||
This handler will utilize the associated callback method and formats
|
||||
the input of each callback function with metadata regarding the state of LLM run,
|
||||
and adds the response to the list of records for both the {method}_records and
|
||||
action. It then logs the response to the ClearML console.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
task_type: Optional[str] = "inference",
|
||||
project_name: Optional[str] = "langchain_callback_demo",
|
||||
tags: Optional[Sequence] = None,
|
||||
task_name: Optional[str] = None,
|
||||
visualize: bool = False,
|
||||
complexity_metrics: bool = False,
|
||||
stream_logs: bool = False,
|
||||
) -> None:
|
||||
"""Initialize callback handler."""
|
||||
|
||||
clearml = import_clearml()
|
||||
spacy = import_spacy()
|
||||
super().__init__()
|
||||
|
||||
self.task_type = task_type
|
||||
self.project_name = project_name
|
||||
self.tags = tags
|
||||
self.task_name = task_name
|
||||
self.visualize = visualize
|
||||
self.complexity_metrics = complexity_metrics
|
||||
self.stream_logs = stream_logs
|
||||
|
||||
self.temp_dir = tempfile.TemporaryDirectory()
|
||||
|
||||
# Check if ClearML task already exists (e.g. in pipeline)
|
||||
if clearml.Task.current_task():
|
||||
self.task = clearml.Task.current_task()
|
||||
else:
|
||||
self.task = clearml.Task.init( # type: ignore
|
||||
task_type=self.task_type,
|
||||
project_name=self.project_name,
|
||||
tags=self.tags,
|
||||
task_name=self.task_name,
|
||||
output_uri=True,
|
||||
)
|
||||
self.logger = self.task.get_logger()
|
||||
warning = (
|
||||
"The clearml callback is currently in beta and is subject to change "
|
||||
"based on updates to `langchain`. Please report any issues to "
|
||||
"https://github.com/allegroai/clearml/issues with the tag `langchain`."
|
||||
)
|
||||
self.logger.report_text(warning, level=30, print_console=True)
|
||||
self.callback_columns: list = []
|
||||
self.action_records: list = []
|
||||
self.complexity_metrics = complexity_metrics
|
||||
self.visualize = visualize
|
||||
self.nlp = spacy.load("en_core_web_sm")
|
||||
|
||||
def _init_resp(self) -> Dict:
|
||||
return {k: None for k in self.callback_columns}
|
||||
|
||||
def on_llm_start(
|
||||
self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
|
||||
) -> None:
|
||||
"""Run when LLM starts."""
|
||||
self.step += 1
|
||||
self.llm_starts += 1
|
||||
self.starts += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update({"action": "on_llm_start"})
|
||||
resp.update(flatten_dict(serialized))
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
for prompt in prompts:
|
||||
prompt_resp = deepcopy(resp)
|
||||
prompt_resp["prompts"] = prompt
|
||||
self.on_llm_start_records.append(prompt_resp)
|
||||
self.action_records.append(prompt_resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(prompt_resp)
|
||||
|
||||
def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
|
||||
"""Run when LLM generates a new token."""
|
||||
self.step += 1
|
||||
self.llm_streams += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update({"action": "on_llm_new_token", "token": token})
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
self.on_llm_token_records.append(resp)
|
||||
self.action_records.append(resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(resp)
|
||||
|
||||
def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
|
||||
"""Run when LLM ends running."""
|
||||
self.step += 1
|
||||
self.llm_ends += 1
|
||||
self.ends += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update({"action": "on_llm_end"})
|
||||
resp.update(flatten_dict(response.llm_output or {}))
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
for generations in response.generations:
|
||||
for generation in generations:
|
||||
generation_resp = deepcopy(resp)
|
||||
generation_resp.update(flatten_dict(generation.dict()))
|
||||
generation_resp.update(self.analyze_text(generation.text))
|
||||
self.on_llm_end_records.append(generation_resp)
|
||||
self.action_records.append(generation_resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(generation_resp)
|
||||
|
||||
def on_llm_error(
|
||||
self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
|
||||
) -> None:
|
||||
"""Run when LLM errors."""
|
||||
self.step += 1
|
||||
self.errors += 1
|
||||
|
||||
def on_chain_start(
|
||||
self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
|
||||
) -> None:
|
||||
"""Run when chain starts running."""
|
||||
self.step += 1
|
||||
self.chain_starts += 1
|
||||
self.starts += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update({"action": "on_chain_start"})
|
||||
resp.update(flatten_dict(serialized))
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
chain_input = inputs["input"]
|
||||
|
||||
if isinstance(chain_input, str):
|
||||
input_resp = deepcopy(resp)
|
||||
input_resp["input"] = chain_input
|
||||
self.on_chain_start_records.append(input_resp)
|
||||
self.action_records.append(input_resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(input_resp)
|
||||
elif isinstance(chain_input, list):
|
||||
for inp in chain_input:
|
||||
input_resp = deepcopy(resp)
|
||||
input_resp.update(inp)
|
||||
self.on_chain_start_records.append(input_resp)
|
||||
self.action_records.append(input_resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(input_resp)
|
||||
else:
|
||||
raise ValueError("Unexpected data format provided!")
|
||||
|
||||
def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
|
||||
"""Run when chain ends running."""
|
||||
self.step += 1
|
||||
self.chain_ends += 1
|
||||
self.ends += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update({"action": "on_chain_end", "outputs": outputs["output"]})
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
self.on_chain_end_records.append(resp)
|
||||
self.action_records.append(resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(resp)
|
||||
|
||||
def on_chain_error(
|
||||
self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
|
||||
) -> None:
|
||||
"""Run when chain errors."""
|
||||
self.step += 1
|
||||
self.errors += 1
|
||||
|
||||
def on_tool_start(
|
||||
self, serialized: Dict[str, Any], input_str: str, **kwargs: Any
|
||||
) -> None:
|
||||
"""Run when tool starts running."""
|
||||
self.step += 1
|
||||
self.tool_starts += 1
|
||||
self.starts += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update({"action": "on_tool_start", "input_str": input_str})
|
||||
resp.update(flatten_dict(serialized))
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
self.on_tool_start_records.append(resp)
|
||||
self.action_records.append(resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(resp)
|
||||
|
||||
def on_tool_end(self, output: str, **kwargs: Any) -> None:
|
||||
"""Run when tool ends running."""
|
||||
self.step += 1
|
||||
self.tool_ends += 1
|
||||
self.ends += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update({"action": "on_tool_end", "output": output})
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
self.on_tool_end_records.append(resp)
|
||||
self.action_records.append(resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(resp)
|
||||
|
||||
def on_tool_error(
|
||||
self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
|
||||
) -> None:
|
||||
"""Run when tool errors."""
|
||||
self.step += 1
|
||||
self.errors += 1
|
||||
|
||||
def on_text(self, text: str, **kwargs: Any) -> None:
|
||||
"""
|
||||
Run when agent is ending.
|
||||
"""
|
||||
self.step += 1
|
||||
self.text_ctr += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update({"action": "on_text", "text": text})
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
self.on_text_records.append(resp)
|
||||
self.action_records.append(resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(resp)
|
||||
|
||||
def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> None:
|
||||
"""Run when agent ends running."""
|
||||
self.step += 1
|
||||
self.agent_ends += 1
|
||||
self.ends += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update(
|
||||
{
|
||||
"action": "on_agent_finish",
|
||||
"output": finish.return_values["output"],
|
||||
"log": finish.log,
|
||||
}
|
||||
)
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
|
||||
self.on_agent_finish_records.append(resp)
|
||||
self.action_records.append(resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(resp)
|
||||
|
||||
def on_agent_action(self, action: AgentAction, **kwargs: Any) -> Any:
|
||||
"""Run on agent action."""
|
||||
self.step += 1
|
||||
self.tool_starts += 1
|
||||
self.starts += 1
|
||||
|
||||
resp = self._init_resp()
|
||||
resp.update(
|
||||
{
|
||||
"action": "on_agent_action",
|
||||
"tool": action.tool,
|
||||
"tool_input": action.tool_input,
|
||||
"log": action.log,
|
||||
}
|
||||
)
|
||||
resp.update(self.get_custom_callback_meta())
|
||||
self.on_agent_action_records.append(resp)
|
||||
self.action_records.append(resp)
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(resp)
|
||||
|
||||
def analyze_text(self, text: str) -> dict:
|
||||
"""Analyze text using textstat and spacy.
|
||||
|
||||
Parameters:
|
||||
text (str): The text to analyze.
|
||||
|
||||
Returns:
|
||||
(dict): A dictionary containing the complexity metrics.
|
||||
"""
|
||||
resp = {}
|
||||
textstat = import_textstat()
|
||||
spacy = import_spacy()
|
||||
if self.complexity_metrics:
|
||||
text_complexity_metrics = {
|
||||
"flesch_reading_ease": textstat.flesch_reading_ease(text),
|
||||
"flesch_kincaid_grade": textstat.flesch_kincaid_grade(text),
|
||||
"smog_index": textstat.smog_index(text),
|
||||
"coleman_liau_index": textstat.coleman_liau_index(text),
|
||||
"automated_readability_index": textstat.automated_readability_index(
|
||||
text
|
||||
),
|
||||
"dale_chall_readability_score": textstat.dale_chall_readability_score(
|
||||
text
|
||||
),
|
||||
"difficult_words": textstat.difficult_words(text),
|
||||
"linsear_write_formula": textstat.linsear_write_formula(text),
|
||||
"gunning_fog": textstat.gunning_fog(text),
|
||||
"text_standard": textstat.text_standard(text),
|
||||
"fernandez_huerta": textstat.fernandez_huerta(text),
|
||||
"szigriszt_pazos": textstat.szigriszt_pazos(text),
|
||||
"gutierrez_polini": textstat.gutierrez_polini(text),
|
||||
"crawford": textstat.crawford(text),
|
||||
"gulpease_index": textstat.gulpease_index(text),
|
||||
"osman": textstat.osman(text),
|
||||
}
|
||||
resp.update(text_complexity_metrics)
|
||||
|
||||
if self.visualize and self.nlp and self.temp_dir.name is not None:
|
||||
doc = self.nlp(text)
|
||||
|
||||
dep_out = spacy.displacy.render( # type: ignore
|
||||
doc, style="dep", jupyter=False, page=True
|
||||
)
|
||||
dep_output_path = Path(
|
||||
self.temp_dir.name, hash_string(f"dep-{text}") + ".html"
|
||||
)
|
||||
dep_output_path.open("w", encoding="utf-8").write(dep_out)
|
||||
|
||||
ent_out = spacy.displacy.render( # type: ignore
|
||||
doc, style="ent", jupyter=False, page=True
|
||||
)
|
||||
ent_output_path = Path(
|
||||
self.temp_dir.name, hash_string(f"ent-{text}") + ".html"
|
||||
)
|
||||
ent_output_path.open("w", encoding="utf-8").write(ent_out)
|
||||
|
||||
self.logger.report_media(
|
||||
"Dependencies Plot", text, local_path=dep_output_path
|
||||
)
|
||||
self.logger.report_media("Entities Plot", text, local_path=ent_output_path)
|
||||
|
||||
return resp
|
||||
|
||||
def _create_session_analysis_df(self) -> Any:
|
||||
"""Create a dataframe with all the information from the session."""
|
||||
pd = import_pandas()
|
||||
on_llm_start_records_df = pd.DataFrame(self.on_llm_start_records)
|
||||
on_llm_end_records_df = pd.DataFrame(self.on_llm_end_records)
|
||||
|
||||
llm_input_prompts_df = (
|
||||
on_llm_start_records_df[["step", "prompts", "name"]]
|
||||
.dropna(axis=1)
|
||||
.rename({"step": "prompt_step"}, axis=1)
|
||||
)
|
||||
complexity_metrics_columns = []
|
||||
visualizations_columns: List = []
|
||||
|
||||
if self.complexity_metrics:
|
||||
complexity_metrics_columns = [
|
||||
"flesch_reading_ease",
|
||||
"flesch_kincaid_grade",
|
||||
"smog_index",
|
||||
"coleman_liau_index",
|
||||
"automated_readability_index",
|
||||
"dale_chall_readability_score",
|
||||
"difficult_words",
|
||||
"linsear_write_formula",
|
||||
"gunning_fog",
|
||||
"text_standard",
|
||||
"fernandez_huerta",
|
||||
"szigriszt_pazos",
|
||||
"gutierrez_polini",
|
||||
"crawford",
|
||||
"gulpease_index",
|
||||
"osman",
|
||||
]
|
||||
|
||||
llm_outputs_df = (
|
||||
on_llm_end_records_df[
|
||||
[
|
||||
"step",
|
||||
"text",
|
||||
"token_usage_total_tokens",
|
||||
"token_usage_prompt_tokens",
|
||||
"token_usage_completion_tokens",
|
||||
]
|
||||
+ complexity_metrics_columns
|
||||
+ visualizations_columns
|
||||
]
|
||||
.dropna(axis=1)
|
||||
.rename({"step": "output_step", "text": "output"}, axis=1)
|
||||
)
|
||||
session_analysis_df = pd.concat([llm_input_prompts_df, llm_outputs_df], axis=1)
|
||||
# session_analysis_df["chat_html"] = session_analysis_df[
|
||||
# ["prompts", "output"]
|
||||
# ].apply(
|
||||
# lambda row: construct_html_from_prompt_and_generation(
|
||||
# row["prompts"], row["output"]
|
||||
# ),
|
||||
# axis=1,
|
||||
# )
|
||||
return session_analysis_df
|
||||
|
||||
def flush_tracker(
|
||||
self,
|
||||
name: Optional[str] = None,
|
||||
langchain_asset: Any = None,
|
||||
finish: bool = False,
|
||||
) -> None:
|
||||
"""Flush the tracker and setup the session.
|
||||
|
||||
Everything after this will be a new table.
|
||||
|
||||
Args:
|
||||
name: Name of the preformed session so far so it is identifyable
|
||||
langchain_asset: The langchain asset to save.
|
||||
finish: Whether to finish the run.
|
||||
|
||||
Returns:
|
||||
None
|
||||
"""
|
||||
pd = import_pandas()
|
||||
clearml = import_clearml()
|
||||
|
||||
# Log the action records
|
||||
self.logger.report_table(
|
||||
"Action Records", name, table_plot=pd.DataFrame(self.action_records)
|
||||
)
|
||||
|
||||
# Session analysis
|
||||
session_analysis_df = self._create_session_analysis_df()
|
||||
self.logger.report_table(
|
||||
"Session Analysis", name, table_plot=session_analysis_df
|
||||
)
|
||||
|
||||
if self.stream_logs:
|
||||
self.logger.report_text(
|
||||
{
|
||||
"action_records": pd.DataFrame(self.action_records),
|
||||
"session_analysis": session_analysis_df,
|
||||
}
|
||||
)
|
||||
|
||||
if langchain_asset:
|
||||
langchain_asset_path = Path(self.temp_dir.name, "model.json")
|
||||
try:
|
||||
langchain_asset.save(langchain_asset_path)
|
||||
# Create output model and connect it to the task
|
||||
output_model = clearml.OutputModel(
|
||||
task=self.task, config_text=load_json(langchain_asset_path)
|
||||
)
|
||||
output_model.update_weights(
|
||||
weights_filename=str(langchain_asset_path),
|
||||
auto_delete_file=False,
|
||||
target_filename=name,
|
||||
)
|
||||
except ValueError:
|
||||
langchain_asset.save_agent(langchain_asset_path)
|
||||
output_model = clearml.OutputModel(
|
||||
task=self.task, config_text=load_json(langchain_asset_path)
|
||||
)
|
||||
output_model.update_weights(
|
||||
weights_filename=str(langchain_asset_path),
|
||||
auto_delete_file=False,
|
||||
target_filename=name,
|
||||
)
|
||||
except NotImplementedError as e:
|
||||
print("Could not save model.")
|
||||
print(repr(e))
|
||||
pass
|
||||
|
||||
# Cleanup after adding everything to ClearML
|
||||
self.task.flush(wait_for_uploads=True)
|
||||
self.temp_dir.cleanup()
|
||||
self.temp_dir = tempfile.TemporaryDirectory()
|
||||
self.reset_callback_meta()
|
||||
|
||||
if finish:
|
||||
self.task.close()
|
||||
@ -0,0 +1,253 @@
|
||||
import hashlib
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, Iterable, Tuple, Union
|
||||
|
||||
|
||||
def import_spacy() -> Any:
|
||||
try:
|
||||
import spacy
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"This callback manager requires the `spacy` python "
|
||||
"package installed. Please install it with `pip install spacy`"
|
||||
)
|
||||
return spacy
|
||||
|
||||
|
||||
def import_pandas() -> Any:
|
||||
try:
|
||||
import pandas
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"This callback manager requires the `pandas` python "
|
||||
"package installed. Please install it with `pip install pandas`"
|
||||
)
|
||||
return pandas
|
||||
|
||||
|
||||
def import_textstat() -> Any:
|
||||
try:
|
||||
import textstat
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"This callback manager requires the `textstat` python "
|
||||
"package installed. Please install it with `pip install textstat`"
|
||||
)
|
||||
return textstat
|
||||
|
||||
|
||||
def _flatten_dict(
|
||||
nested_dict: Dict[str, Any], parent_key: str = "", sep: str = "_"
|
||||
) -> Iterable[Tuple[str, Any]]:
|
||||
"""
|
||||
Generator that yields flattened items from a nested dictionary for a flat dict.
|
||||
|
||||
Parameters:
|
||||
nested_dict (dict): The nested dictionary to flatten.
|
||||
parent_key (str): The prefix to prepend to the keys of the flattened dict.
|
||||
sep (str): The separator to use between the parent key and the key of the
|
||||
flattened dictionary.
|
||||
|
||||
Yields:
|
||||
(str, any): A key-value pair from the flattened dictionary.
|
||||
"""
|
||||
for key, value in nested_dict.items():
|
||||
new_key = parent_key + sep + key if parent_key else key
|
||||
if isinstance(value, dict):
|
||||
yield from _flatten_dict(value, new_key, sep)
|
||||
else:
|
||||
yield new_key, value
|
||||
|
||||
|
||||
def flatten_dict(
|
||||
nested_dict: Dict[str, Any], parent_key: str = "", sep: str = "_"
|
||||
) -> Dict[str, Any]:
|
||||
"""Flattens a nested dictionary into a flat dictionary.
|
||||
|
||||
Parameters:
|
||||
nested_dict (dict): The nested dictionary to flatten.
|
||||
parent_key (str): The prefix to prepend to the keys of the flattened dict.
|
||||
sep (str): The separator to use between the parent key and the key of the
|
||||
flattened dictionary.
|
||||
|
||||
Returns:
|
||||
(dict): A flat dictionary.
|
||||
|
||||
"""
|
||||
flat_dict = {k: v for k, v in _flatten_dict(nested_dict, parent_key, sep)}
|
||||
return flat_dict
|
||||
|
||||
|
||||
def hash_string(s: str) -> str:
|
||||
"""Hash a string using sha1.
|
||||
|
||||
Parameters:
|
||||
s (str): The string to hash.
|
||||
|
||||
Returns:
|
||||
(str): The hashed string.
|
||||
"""
|
||||
return hashlib.sha1(s.encode("utf-8")).hexdigest()
|
||||
|
||||
|
||||
def load_json(json_path: Union[str, Path]) -> str:
|
||||
"""Load json file to a string.
|
||||
|
||||
Parameters:
|
||||
json_path (str): The path to the json file.
|
||||
|
||||
Returns:
|
||||
(str): The string representation of the json file.
|
||||
"""
|
||||
with open(json_path, "r") as f:
|
||||
data = f.read()
|
||||
return data
|
||||
|
||||
|
||||
class BaseMetadataCallbackHandler:
|
||||
"""This class handles the metadata and associated function states for callbacks.
|
||||
|
||||
Attributes:
|
||||
step (int): The current step.
|
||||
starts (int): The number of times the start method has been called.
|
||||
ends (int): The number of times the end method has been called.
|
||||
errors (int): The number of times the error method has been called.
|
||||
text_ctr (int): The number of times the text method has been called.
|
||||
ignore_llm_ (bool): Whether to ignore llm callbacks.
|
||||
ignore_chain_ (bool): Whether to ignore chain callbacks.
|
||||
ignore_agent_ (bool): Whether to ignore agent callbacks.
|
||||
always_verbose_ (bool): Whether to always be verbose.
|
||||
chain_starts (int): The number of times the chain start method has been called.
|
||||
chain_ends (int): The number of times the chain end method has been called.
|
||||
llm_starts (int): The number of times the llm start method has been called.
|
||||
llm_ends (int): The number of times the llm end method has been called.
|
||||
llm_streams (int): The number of times the text method has been called.
|
||||
tool_starts (int): The number of times the tool start method has been called.
|
||||
tool_ends (int): The number of times the tool end method has been called.
|
||||
agent_ends (int): The number of times the agent end method has been called.
|
||||
on_llm_start_records (list): A list of records of the on_llm_start method.
|
||||
on_llm_token_records (list): A list of records of the on_llm_token method.
|
||||
on_llm_end_records (list): A list of records of the on_llm_end method.
|
||||
on_chain_start_records (list): A list of records of the on_chain_start method.
|
||||
on_chain_end_records (list): A list of records of the on_chain_end method.
|
||||
on_tool_start_records (list): A list of records of the on_tool_start method.
|
||||
on_tool_end_records (list): A list of records of the on_tool_end method.
|
||||
on_agent_finish_records (list): A list of records of the on_agent_end method.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self.step = 0
|
||||
|
||||
self.starts = 0
|
||||
self.ends = 0
|
||||
self.errors = 0
|
||||
self.text_ctr = 0
|
||||
|
||||
self.ignore_llm_ = False
|
||||
self.ignore_chain_ = False
|
||||
self.ignore_agent_ = False
|
||||
self.always_verbose_ = False
|
||||
|
||||
self.chain_starts = 0
|
||||
self.chain_ends = 0
|
||||
|
||||
self.llm_starts = 0
|
||||
self.llm_ends = 0
|
||||
self.llm_streams = 0
|
||||
|
||||
self.tool_starts = 0
|
||||
self.tool_ends = 0
|
||||
|
||||
self.agent_ends = 0
|
||||
|
||||
self.on_llm_start_records: list = []
|
||||
self.on_llm_token_records: list = []
|
||||
self.on_llm_end_records: list = []
|
||||
|
||||
self.on_chain_start_records: list = []
|
||||
self.on_chain_end_records: list = []
|
||||
|
||||
self.on_tool_start_records: list = []
|
||||
self.on_tool_end_records: list = []
|
||||
|
||||
self.on_text_records: list = []
|
||||
self.on_agent_finish_records: list = []
|
||||
self.on_agent_action_records: list = []
|
||||
|
||||
@property
|
||||
def always_verbose(self) -> bool:
|
||||
"""Whether to call verbose callbacks even if verbose is False."""
|
||||
return self.always_verbose_
|
||||
|
||||
@property
|
||||
def ignore_llm(self) -> bool:
|
||||
"""Whether to ignore LLM callbacks."""
|
||||
return self.ignore_llm_
|
||||
|
||||
@property
|
||||
def ignore_chain(self) -> bool:
|
||||
"""Whether to ignore chain callbacks."""
|
||||
return self.ignore_chain_
|
||||
|
||||
@property
|
||||
def ignore_agent(self) -> bool:
|
||||
"""Whether to ignore agent callbacks."""
|
||||
return self.ignore_agent_
|
||||
|
||||
def get_custom_callback_meta(self) -> Dict[str, Any]:
|
||||
return {
|
||||
"step": self.step,
|
||||
"starts": self.starts,
|
||||
"ends": self.ends,
|
||||
"errors": self.errors,
|
||||
"text_ctr": self.text_ctr,
|
||||
"chain_starts": self.chain_starts,
|
||||
"chain_ends": self.chain_ends,
|
||||
"llm_starts": self.llm_starts,
|
||||
"llm_ends": self.llm_ends,
|
||||
"llm_streams": self.llm_streams,
|
||||
"tool_starts": self.tool_starts,
|
||||
"tool_ends": self.tool_ends,
|
||||
"agent_ends": self.agent_ends,
|
||||
}
|
||||
|
||||
def reset_callback_meta(self) -> None:
|
||||
"""Reset the callback metadata."""
|
||||
self.step = 0
|
||||
|
||||
self.starts = 0
|
||||
self.ends = 0
|
||||
self.errors = 0
|
||||
self.text_ctr = 0
|
||||
|
||||
self.ignore_llm_ = False
|
||||
self.ignore_chain_ = False
|
||||
self.ignore_agent_ = False
|
||||
self.always_verbose_ = False
|
||||
|
||||
self.chain_starts = 0
|
||||
self.chain_ends = 0
|
||||
|
||||
self.llm_starts = 0
|
||||
self.llm_ends = 0
|
||||
self.llm_streams = 0
|
||||
|
||||
self.tool_starts = 0
|
||||
self.tool_ends = 0
|
||||
|
||||
self.agent_ends = 0
|
||||
|
||||
self.on_llm_start_records = []
|
||||
self.on_llm_token_records = []
|
||||
self.on_llm_end_records = []
|
||||
|
||||
self.on_chain_start_records = []
|
||||
self.on_chain_end_records = []
|
||||
|
||||
self.on_tool_start_records = []
|
||||
self.on_tool_end_records = []
|
||||
|
||||
self.on_text_records = []
|
||||
self.on_agent_finish_records = []
|
||||
self.on_agent_action_records = []
|
||||
return None
|
||||
Loading…
Reference in New Issue