ClearML
ClearML 是一个机器学习/深度学习开发和生产套件，包含5个主要模块：
Experiment Manager- 自动化实验跟踪、环境和结果MLOps- 机器学习/深度 学习作业的编排、自动化和管道解决方案（K8s / 云 / 物理服务器）Data-Management- 基于对象存储（S3 / GS / Azure / NAS）的完全可微分数据管理和版本控制解决方案Model-Serving- 云就绪的可扩展模型服务解决方案！ 在5分钟内部署新的模型端点 包括由Nvidia-Triton支持的优化GPU服务支持 具有开箱即用的模型监控Fire Reports- 创建和分享支持嵌入在线内容的丰富MarkDown文档
为了正确跟踪您的LangChain实验及其结果，您可以启用ClearML集成。我们使用ClearML实验管理器，它可以整齐地跟踪和组织您所有的实验运行。
安装和设置
%pip install --upgrade --quiet clearml
%pip install --upgrade --quiet pandas
%pip install --upgrade --quiet textstat
%pip install --upgrade --quiet spacy
!python -m spacy download en_core_web_sm
获取API凭证
我们将在这个笔记本中使用一些API，以下是列表及获取方式：
- ClearML: https://app.clear.ml/settings/workspace-configuration
- OpenAI: https://platform.openai.com/account/api-keys
- SerpAPI (谷歌搜索): https://serpapi.com/dashboard
import os
os.environ["CLEARML_API_ACCESS_KEY"] = ""
os.environ["CLEARML_API_SECRET_KEY"] = ""
os.environ["OPENAI_API_KEY"] = ""
os.environ["SERPAPI_API_KEY"] = ""
回调
<!--IMPORTS:[{"imported": "ClearMLCallbackHandler", "source": "langchain_community.callbacks", "docs": "https://python.langchain.com/api_reference/community/callbacks/langchain_community.callbacks.clearml_callback.ClearMLCallbackHandler.html", "title": "ClearML"}]-->
from langchain_community.callbacks import ClearMLCallbackHandler
<!--IMPORTS:[{"imported": "StdOutCallbackHandler", "source": "langchain_core.callbacks", "docs": "https://python.langchain.com/api_reference/core/callbacks/langchain_core.callbacks.stdout.StdOutCallbackHandler.html", "title": "ClearML"}, {"imported": "OpenAI", "source": "langchain_openai", "docs": "https://python.langchain.com/api_reference/openai/llms/langchain_openai.llms.base.OpenAI.html", "title": "ClearML"}]-->
from langchain_core.callbacks import StdOutCallbackHandler
from langchain_openai import OpenAI
# Setup and use the ClearML Callback
clearml_callback = ClearMLCallbackHandler(
task_type="inference",
project_name="langchain_callback_demo",
task_name="llm",
tags=["test"],
# Change the following parameters based on the amount of detail you want tracked
visualize=True,
complexity_metrics=True,
stream_logs=True,
)
callbacks = [StdOutCallbackHandler(), clearml_callback]
# Get the OpenAI model ready to go
llm = OpenAI(temperature=0, callbacks=callbacks)
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`.
场景1：仅一个大型语言模型
首先，让我们运行一个大型语言模型几次，并在ClearML中捕获生成的提示-回答对话。
# SCENARIO 1 - LLM
llm_result = llm.generate(["Tell me a joke", "Tell me a poem"] * 3)
# After every generation run, use flush to make sure all the metrics
# prompts and other output are properly saved separately
clearml_callback.flush_tracker(langchain_asset=llm, name="simple_sequential")
{'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'}
{'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'}
{'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'}
{'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'}
{'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'}
{'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'}
{'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}
{'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}
{'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}
{'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}
{'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}
{'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}
{'action_records': action name step starts ends errors text_ctr chain_starts \
0 on_llm_start OpenAI 1 1 0 0 0 0
1 on_llm_start OpenAI 1 1 0 0 0 0
2 on_llm_start OpenAI 1 1 0 0 0 0
3 on_llm_start OpenAI 1 1 0 0 0 0
4 on_llm_start OpenAI 1 1 0 0 0 0
5 on_llm_start OpenAI 1 1 0 0 0 0
6 on_llm_end NaN 2 1 1 0 0 0
7 on_llm_end NaN 2 1 1 0 0 0
8 on_llm_end NaN 2 1 1 0 0 0
9 on_llm_end NaN 2 1 1 0 0 0
10 on_llm_end NaN 2 1 1 0 0 0
11 on_llm_end NaN 2 1 1 0 0 0
12 on_llm_start OpenAI 3 2 1 0 0 0
13 on_llm_start OpenAI 3 2 1 0 0 0
14 on_llm_start OpenAI 3 2 1 0 0 0
15 on_llm_start OpenAI 3 2 1 0 0 0
16 on_llm_start OpenAI 3 2 1 0 0 0
17 on_llm_start OpenAI 3 2 1 0 0 0
18 on_llm_end NaN 4 2 2 0 0 0
19 on_llm_end NaN 4 2 2 0 0 0
20 on_llm_end NaN 4 2 2 0 0 0
21 on_llm_end NaN 4 2 2 0 0 0
22 on_llm_end NaN 4 2 2 0 0 0
23 on_llm_end NaN 4 2 2 0 0 0
chain_ends llm_starts ... difficult_words linsear_write_formula \
0 0 1 ... NaN NaN
1 0 1 ... NaN NaN
2 0 1 ... NaN NaN
3 0 1 ... NaN NaN
4 0 1 ... NaN NaN
5 0 1 ... NaN NaN
6 0 1 ... 0.0 5.5
7 0 1 ... 2.0 6.5
8 0 1 ... 0.0 5.5
9 0 1 ... 2.0 6.5
10 0 1 ... 0.0 5.5
11 0 1 ... 2.0 6.5
12 0 2 ... NaN NaN
13 0 2 ... NaN NaN
14 0 2 ... NaN NaN
15 0 2 ... NaN NaN
16 0 2 ... NaN NaN
17 0 2 ... NaN NaN
18 0 2 ... 0.0 5.5
19 0 2 ... 2.0 6.5
20 0 2 ... 0.0 5.5
21 0 2 ... 2.0 6.5
22 0 2 ... 0.0 5.5
23 0 2 ... 2.0 6.5
gunning_fog text_standard fernandez_huerta szigriszt_pazos \
0 NaN NaN NaN NaN
1 NaN NaN NaN NaN
2 NaN NaN NaN NaN
3 NaN NaN NaN NaN
4 NaN NaN NaN NaN
5 NaN NaN NaN NaN
6 5.20 5th and 6th grade 133.58 131.54
7 8.28 6th and 7th grade 115.58 112.37
8 5.20 5th and 6th grade 133.58 131.54
9 8.28 6th and 7th grade 115.58 112.37
10 5.20 5th and 6th grade 133.58 131.54
11 8.28 6th and 7th grade 115.58 112.37
12 NaN NaN NaN NaN
13 NaN NaN NaN NaN
14 NaN NaN NaN NaN
15 NaN NaN NaN NaN
16 NaN NaN NaN NaN
17 NaN NaN NaN NaN
18 5.20 5th and 6th grade 133.58 131.54
19 8.28 6th and 7th grade 115.58 112.37
20 5.20 5th and 6th grade 133.58 131.54
21 8.28 6th and 7th grade 115.58 112.37
22 5.20 5th and 6th grade 133.58 131.54
23 8.28 6th and 7th grade 115.58 112.37
gutierrez_polini crawford gulpease_index osman
0 NaN NaN NaN NaN
1 NaN NaN NaN NaN
2 NaN NaN NaN NaN
3 NaN NaN NaN NaN
4 NaN NaN NaN NaN
5 NaN NaN NaN NaN
6 62.30 -0.2 79.8 116.91
7 54.83 1.4 72.1 100.17
8 62.30 -0.2 79.8 116.91
9 54.83 1.4 72.1 100.17
10 62.30 -0.2 79.8 116.91
11 54.83 1.4 72.1 100.17
12 NaN NaN NaN NaN
13 NaN NaN NaN NaN
14 NaN NaN NaN NaN
15 NaN NaN NaN NaN
16 NaN NaN NaN NaN
17 NaN NaN NaN NaN
18 62.30 -0.2 79.8 116.91
19 54.83 1.4 72.1 100.17
20 62.30 -0.2 79.8 116.91
21 54.83 1.4 72.1 100.17
22 62.30 -0.2 79.8 116.91
23 54.83 1.4 72.1 100.17
[24 rows x 39 columns], 'session_analysis': prompt_step prompts name output_step \
0 1 Tell me a joke OpenAI 2
1 1 Tell me a poem OpenAI 2
2 1 Tell me a joke OpenAI 2
3 1 Tell me a poem OpenAI 2
4 1 Tell me a joke OpenAI 2
5 1 Tell me a poem OpenAI 2
6 3 Tell me a joke OpenAI 4
7 3 Tell me a poem OpenAI 4
8 3 Tell me a joke OpenAI 4
9 3 Tell me a poem OpenAI 4
10 3 Tell me a joke OpenAI 4
11 3 Tell me a poem OpenAI 4
output \
0 \n\nQ: What did the fish say when it hit the w...
1 \n\nRoses are red,\nViolets are blue,\nSugar i...
2 \n\nQ: What did the fish say when it hit the w...
3 \n\nRoses are red,\nViolets are blue,\nSugar i...
4 \n\nQ: What did the fish say when it hit the w...
5 \n\nRoses are red,\nViolets are blue,\nSugar i...
6 \n\nQ: What did the fish say when it hit the w...
7 \n\nRoses are red,\nViolets are blue,\nSugar i...
8 \n\nQ: What did the fish say when it hit the w...
9 \n\nRoses are red,\nViolets are blue,\nSugar i...
10 \n\nQ: What did the fish say when it hit the w...
11 \n\nRoses are red,\nViolets are blue,\nSugar i...
token_usage_total_tokens token_usage_prompt_tokens \
0 162 24
1 162 24
2 162 24
3 162 24
4 162 24
5 162 24
6 162 24
7 162 24
8 162 24
9 162 24
10 162 24
11 162 24
token_usage_completion_tokens flesch_reading_ease flesch_kincaid_grade \
0 138 109.04 1.3
1 138 83.66 4.8
2 138 109.04 1.3
3 138 83.66 4.8
4 138 109.04 1.3
5 138 83.66 4.8
6 138 109.04 1.3
7 138 83.66 4.8
8 138 109.04 1.3
9 138 83.66 4.8
10 138 109.04 1.3
11 138 83.66 4.8
... difficult_words linsear_write_formula gunning_fog \
0 ... 0 5.5 5.20
1 ... 2 6.5 8.28
2 ... 0 5.5 5.20
3 ... 2 6.5 8.28
4 ... 0 5.5 5.20
5 ... 2 6.5 8.28
6 ... 0 5.5 5.20
7 ... 2 6.5 8.28
8 ... 0 5.5 5.20
9 ... 2 6.5 8.28
10 ... 0 5.5 5.20
11 ... 2 6.5 8.28
text_standard fernandez_huerta szigriszt_pazos gutierrez_polini \
0 5th and 6th grade 133.58 131.54 62.30
1 6th and 7th grade 115.58 112.37 54.83
2 5th and 6th grade 133.58 131.54 62.30
3 6th and 7th grade 115.58 112.37 54.83
4 5th and 6th grade 133.58 131.54 62.30
5 6th and 7th grade 115.58 112.37 54.83
6 5th and 6th grade 133.58 131.54 62.30
7 6th and 7th grade 115.58 112.37 54.83
8 5th and 6th grade 133.58 131.54 62.30
9 6th and 7th grade 115.58 112.37 54.83
10 5th and 6th grade 133.58 131.54 62.30
11 6th and 7th grade 115.58 112.37 54.83
crawford gulpease_index osman
0 -0.2 79.8 116.91
1 1.4 72.1 100.17
2 -0.2 79.8 116.91
3 1.4 72.1 100.17
4 -0.2 79.8 116.91
5 1.4 72.1 100.17
6 -0.2 79.8 116.91
7 1.4 72.1 100.17
8 -0.2 79.8 116.91
9 1.4 72.1 100.17
10 -0.2 79.8 116.91
11 1.4 72.1 100.17
[12 rows x 24 columns]}
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
此时，您可以前往 https://app.clear.ml 查看已创建的ClearML任务。
在其他信息中，您应该看到这个笔记本已保存，并包含任何git 信息。包含使用参数的模型JSON作为工件保存，还有控制台日志，在图表部分，您会找到表示链流的表格。
最后，如果您启用了可视化，这些将作为HTML文件存储在调试样本中。
场景 2：创建一个带工具的代理
为了展示一个更高级的工作流程，让我们创建一个可以访问工具的代理。ClearML 跟踪结果的方式并没有不同，只是与之前更简单的示例相比，表格看起来会稍有不同，因为采取了其他类型的操作。
您现在还可以看到使用 finish=True 关键字的情况，这将完全关闭 ClearML 任务，而不仅仅是重置参数和提示以进行新的对话。
<!--IMPORTS:[{"imported": "AgentType", "source": "langchain.agents", "docs": "https://python.langchain.com/api_reference/langchain/agents/langchain.agents.agent_types.AgentType.html", "title": "ClearML"}, {"imported": "initialize_agent", "source": "langchain.agents", "docs": "https://python.langchain.com/api_reference/langchain/agents/langchain.agents.initialize.initialize_agent.html", "title": "ClearML"}, {"imported": "load_tools", "source": "langchain.agents", "docs": "https://python.langchain.com/api_reference/community/agent_toolkits/langchain_community.agent_toolkits.load_tools.load_tools.html", "title": "ClearML"}]-->
from langchain.agents import AgentType, initialize_agent, load_tools
# SCENARIO 2 - Agent with Tools
tools = load_tools(["serpapi", "llm-math"], llm=llm, callbacks=callbacks)
agent = initialize_agent(
tools,
llm,
agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
callbacks=callbacks,
)
agent.run("Who is the wife of the person who sang summer of 69?")
clearml_callback.flush_tracker(
langchain_asset=agent, name="Agent with Tools", finish=True
)
[1m> Entering new AgentExecutor chain...[0m
{'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?'}
{'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:'}
{'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}
[32;1m[1;3m I need to find out who sang summer of 69 and then find out who their wife is.
Action: Search
Action Input: "Who sang summer of 69"[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}
{'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}
Observation: [36;1m[1;3mBryan Adams - Summer Of 69 (Official Music Video).[0m
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}
{'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:'}
{'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}
[32;1m[1;3m I need to find out who Bryan Adams is married to.
Action: Search
Action Input: "Who is Bryan Adams married to"[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}
{'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}
Observation: [36;1m[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 ...[0m
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}
{'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:'}
{'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}
[32;1m[1;3m I now know the final answer.
Final Answer: Bryan Adams has never been married.[0m
{'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}
[1m> Finished chain.[0m
{'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}
{'action_records': action name step starts ends errors text_ctr \
0 on_llm_start OpenAI 1 1 0 0 0
1 on_llm_start OpenAI 1 1 0 0 0
2 on_llm_start OpenAI 1 1 0 0 0
3 on_llm_start OpenAI 1 1 0 0 0
4 on_llm_start OpenAI 1 1 0 0 0
.. ... ... ... ... ... ... ...
66 on_tool_end NaN 11 7 4 0 0
67 on_llm_start OpenAI 12 8 4 0 0
68 on_llm_end NaN 13 8 5 0 0
69 on_agent_finish NaN 14 8 6 0 0
70 on_chain_end NaN 15 8 7 0 0
chain_starts chain_ends llm_starts ... gulpease_index osman input \
0 0 0 1 ... NaN NaN NaN
1 0 0 1 ... NaN NaN NaN
2 0 0 1 ... NaN NaN NaN
3 0 0 1 ... NaN NaN NaN
4 0 0 1 ... NaN NaN NaN
.. ... ... ... ... ... ... ...
66 1 0 2 ... NaN NaN NaN
67 1 0 3 ... NaN NaN NaN
68 1 0 3 ... 85.4 83.14 NaN
69 1 0 3 ... NaN NaN NaN
70 1 1 3 ... NaN NaN NaN
tool tool_input log \
0 NaN NaN NaN
1 NaN NaN NaN
2 NaN NaN NaN
3 NaN NaN NaN
4 NaN NaN NaN
.. ... ... ...
66 NaN NaN NaN
67 NaN NaN NaN
68 NaN NaN NaN
69 NaN NaN I now know the final answer.\nFinal Answer: B...
70 NaN NaN NaN
input_str description output \
0 NaN NaN NaN
1 NaN NaN NaN
2 NaN NaN NaN
3 NaN NaN NaN
4 NaN NaN NaN
.. ... ... ...
66 NaN NaN Bryan Adams has never married. In the 1990s, h...
67 NaN NaN NaN
68 NaN NaN NaN
69 NaN NaN Bryan Adams has never been married.
70 NaN NaN NaN
outputs
0 NaN
1 NaN
2 NaN
3 NaN
4 NaN
.. ...
66 NaN
67 NaN
68 NaN
69 NaN
70 Bryan Adams has never been married.
[71 rows x 47 columns], 'session_analysis': prompt_step prompts name \
0 2 Answer the following questions as best you can... OpenAI
1 7 Answer the following questions as best you can... OpenAI
2 12 Answer the following questions as best you can... OpenAI
output_step output \
0 3 I need to find out who sang summer of 69 and ...
1 8 I need to find out who Bryan Adams is married...
2 13 I now know the final answer.\nFinal Answer: B...
token_usage_total_tokens token_usage_prompt_tokens \
0 223 189
1 270 242
2 332 314
token_usage_completion_tokens flesch_reading_ease flesch_kincaid_grade \
0 34 91.61 3.8
1 28 94.66 2.7
2 18 81.29 3.7
... difficult_words linsear_write_formula gunning_fog \
0 ... 2 5.75 5.4
1 ... 2 4.25 4.2
2 ... 1 2.50 2.8
text_standard fernandez_huerta szigriszt_pazos gutierrez_polini \
0 3rd and 4th grade 121.07 119.50 54.91
1 4th and 5th grade 124.13 119.20 52.26
2 3rd and 4th grade 115.70 110.84 49.79
crawford gulpease_index osman
0 0.9 72.7 92.16
1 0.7 74.7 84.20
2 0.7 85.4 83.14
[3 rows x 24 columns]}
``````output
Could not update last created model in Task 988bd727b0e94a29a3ac0ee526813545, Task status 'completed' cannot be updated
提示和后续步骤
-
确保您始终为
clearml_callback.flush_tracker函数使用唯一的name参数。如果不这样做，运行中使用的模型参数将覆盖之前的运行！ -
如果您使用
clearml_callback.flush_tracker(..., finish=True)关闭 ClearML 回调，则该回调将不再可用。如果您想继续记录，请创建一个新的回调。 -
查看其余的开源 ClearML 生态系统，那里有数据版本管理器、远程执行代理、自动化管道等等！
