mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-05-01 23:32:39 +00:00
fix: ensure token usage recording, validate response model on stream
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
Some checks failed
Build uv cache / build-cache (3.10) (push) Has been cancelled
Build uv cache / build-cache (3.11) (push) Has been cancelled
Build uv cache / build-cache (3.12) (push) Has been cancelled
CodeQL Advanced / Analyze (actions) (push) Has been cancelled
CodeQL Advanced / Analyze (python) (push) Has been cancelled
Notify Downstream / notify-downstream (push) Has been cancelled
Check Documentation Broken Links / Check broken links (push) Has been cancelled
Build uv cache / build-cache (3.13) (push) Has been cancelled
This commit is contained in:
Greyson LaLonde
@@ -85,45 +85,10 @@ interactions:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
|
||||
are a seasoned manager with a knack for getting the best out of your team.\nYou
|
||||
are also known for your ability to delegate work to the right people, and to
|
||||
ask the right questions to get the best out of your team.\nEven though you don''t
|
||||
perform tasks by yourself, you have a lot of experience in the field, which
|
||||
allows you to properly evaluate the work of your team members.\nYour personal
|
||||
goal is: Manage the team to complete the task in the best way possible.\nYou
|
||||
ONLY have access to the following tools, and should NEVER make up tools that
|
||||
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
|
||||
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
|
||||
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
|
||||
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
|
||||
''str''}}\nTool Description: Delegate a specific task to one of the following
|
||||
coworkers: Scorer\nThe input to this tool should be the coworker, the task you
|
||||
want them to do, and ALL necessary context to execute the task, they know nothing
|
||||
about the task, so share absolute everything you know, don''t reference things
|
||||
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
|
||||
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
|
||||
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
|
||||
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
|
||||
''str''}}\nTool Description: Ask a specific question to one of the following
|
||||
coworkers: Scorer\nThe input to this tool should be the coworker, the question
|
||||
you have for them, and ALL necessary context to ask the question properly, they
|
||||
know nothing about the question, so share absolute everything you know, don''t
|
||||
reference things but instead explain them.\n\nUse the following format:\n\nThought:
|
||||
you should always think about what to do\nAction: the action to take, only one
|
||||
name of [Delegate work to coworker, Ask question to coworker], just the name,
|
||||
exactly as it''s written.\nAction Input: the input to the action, just a simple
|
||||
python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
||||
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
|
||||
I now know the final answer\nFinal Answer: the final answer to the original
|
||||
input question"}, {"role": "user", "content": "\nCurrent Task: Give me an integer
|
||||
score between 1-5 for the following title: ''The impact of AI in the future
|
||||
of work'', check examples to based your evaluation.\n\nThis is the expect criteria
|
||||
for your final answer: The score of the title.\nyou MUST return the actual complete
|
||||
content as the final answer, not a summary.\n\nBegin! This is VERY important
|
||||
to you, use the tools available and give your best Final Answer, your job depends
|
||||
on it!\n\nThought:"}], "model": "gpt-4-0125-preview", "stop": ["\nObservation:"],
|
||||
"stream": false}'
|
||||
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You are a seasoned manager with a knack for getting the best out of your team.\nYou are also known for your ability to delegate work to the right people, and to ask the right questions to get the best out of your team.\nEven though you don''t perform tasks by yourself, you have a lot of experience in the field, which allows you to properly evaluate the work of your team members.\nYour personal goal is: Manage the team to complete the task in the best way possible.\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments: {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'': {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to delegate to'', ''type'': ''str''}}\nTool Description: Delegate a specific
|
||||
task to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don''t reference things but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments: {''question'': {''description'': ''The question to ask'', ''type'': ''str''}, ''context'': {''description'': ''The context for the question'', ''type'': ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don''t reference things but instead explain them.\n\nUse the following format:\n\nThought: you
|
||||
should always think about what to do\nAction: the action to take, only one name of [Delegate work to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question"}, {"role": "user", "content": "\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work'', check examples to based your evaluation.\n\nThis is the expect criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
|
||||
"gpt-4-0125-preview", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
@@ -162,34 +127,9 @@ interactions:
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AdhdgT49oskPNVzkbb9Z6SP7ikLJi\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1734025904,\n \"model\": \"gpt-4-0125-preview\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"Thought: To give an accurate score for
|
||||
the title \\\"The impact of AI in the future of work\\\" based on the specified
|
||||
criteria, I'll need the expertise of the Scorer. They specialize in evaluating
|
||||
content, so I must delegate this task to them. I need to provide them with all
|
||||
the necessary context, including the title and the importance of giving a well-considered,
|
||||
integer score between 1-5. Since the request stresses the importance of this
|
||||
task and its implications for my job, I will make sure to communicate the urgency
|
||||
and the criteria very clearly to the Scorer.\\n\\nAction: Delegate work to coworker\\n\\nAction
|
||||
Input: {\\\"task\\\": \\\"Evaluate the title 'The impact of AI in the future
|
||||
of work' and give it an integer score between 1-5, based on your expert assessment.\\\",
|
||||
\\\"context\\\": \\\"The task is to assign a score to the given title based
|
||||
on its significance, relevance, and impactfulness regarding the future of work
|
||||
influenced by artificial intelligence. This score needs to reflect a thorough
|
||||
evaluation within the range of 1 (being the least impactful or relevant) to
|
||||
5 (being the most impactful or relevant). The assessment is highly important
|
||||
and could significantly affect our future work, so it's crucial to consider
|
||||
the current discourse on AI, its potential transformative power on industries
|
||||
and job markets, and general expectations of its future role.\\\", \\\"coworker\\\":
|
||||
\\\"Scorer\\\"}\",\n \"refusal\": null\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
631,\n \"completion_tokens\": 286,\n \"total_tokens\": 917,\n \"prompt_tokens_details\":
|
||||
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
|
||||
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
|
||||
null\n}\n"
|
||||
content: "{\n \"id\": \"chatcmpl-AdhdgT49oskPNVzkbb9Z6SP7ikLJi\",\n \"object\": \"chat.completion\",\n \"created\": 1734025904,\n \"model\": \"gpt-4-0125-preview\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: To give an accurate score for the title \\\"The impact of AI in the future of work\\\" based on the specified criteria, I'll need the expertise of the Scorer. They specialize in evaluating content, so I must delegate this task to them. I need to provide them with all the necessary context, including the title and the importance of giving a well-considered, integer score between 1-5. Since the request stresses the importance of this task and its implications for my job, I will make sure to communicate the urgency and the criteria very clearly to the Scorer.\\n\\nAction: Delegate work to coworker\\n\\nAction Input: {\\\"task\\\": \\\"Evaluate the title 'The impact of AI in the future of\
|
||||
\ work' and give it an integer score between 1-5, based on your expert assessment.\\\", \\\"context\\\": \\\"The task is to assign a score to the given title based on its significance, relevance, and impactfulness regarding the future of work influenced by artificial intelligence. This score needs to reflect a thorough evaluation within the range of 1 (being the least impactful or relevant) to 5 (being the most impactful or relevant). The assessment is highly important and could significantly affect our future work, so it's crucial to consider the current discourse on AI, its potential transformative power on industries and job markets, and general expectations of its future role.\\\", \\\"coworker\\\": \\\"Scorer\\\"}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 631,\n \"completion_tokens\": 286,\n \"total_tokens\": 917,\n \"prompt_tokens_details\": {\n \"cached_tokens\"\
|
||||
: 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
@@ -197,8 +137,6 @@ interactions:
|
||||
- 8f0f9070fd206755-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
@@ -206,11 +144,8 @@ interactions:
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=hmykq8dPVo.iRCPFLyDJJVhA3vlSAmoKNOK6szPX5ZI-1734025911-1.0.1.1-ukj3SfeY5GaS6q5LldvL5GcyN5W_on7HGUThOw9g_oKEVS8.E6bA3rTgQQZyloVkpXfJOSywGJnySVpMP.eJWA;
|
||||
path=/; expires=Thu, 12-Dec-24 18:21:51 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
- __cf_bm=hmykq8dPVo.iRCPFLyDJJVhA3vlSAmoKNOK6szPX5ZI-1734025911-1.0.1.1-ukj3SfeY5GaS6q5LldvL5GcyN5W_on7HGUThOw9g_oKEVS8.E6bA3rTgQQZyloVkpXfJOSywGJnySVpMP.eJWA; path=/; expires=Thu, 12-Dec-24 18:21:51 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
@@ -244,33 +179,9 @@ interactions:
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an
|
||||
expert scorer, specialized in scoring titles.\nYour personal goal is: Score
|
||||
the title\nYou ONLY have access to the following tools, and should NEVER make
|
||||
up tools that are not listed here:\n\nTool Name: scoring_examples\nTool Arguments:
|
||||
{}\nTool Description: Useful examples for scoring titles.\n\nUse the following
|
||||
format:\n\nThought: you should always think about what to do\nAction: the action
|
||||
to take, only one name of [scoring_examples], just the name, exactly as it''s
|
||||
written.\nAction Input: the input to the action, just a simple python dictionary,
|
||||
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
|
||||
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
|
||||
I now know the final answer\nFinal Answer: the final answer to the original
|
||||
input question"}, {"role": "user", "content": "\nCurrent Task: Evaluate the
|
||||
title ''The impact of AI in the future of work'' and give it an integer score
|
||||
between 1-5, based on your expert assessment.\n\nThis is the expect criteria
|
||||
for your final answer: Your best answer to your coworker asking you this, accounting
|
||||
for the context shared.\nyou MUST return the actual complete content as the
|
||||
final answer, not a summary.\n\nThis is the context you''re working with:\nThe
|
||||
task is to assign a score to the given title based on its significance, relevance,
|
||||
and impactfulness regarding the future of work influenced by artificial intelligence.
|
||||
This score needs to reflect a thorough evaluation within the range of 1 (being
|
||||
the least impactful or relevant) to 5 (being the most impactful or relevant).
|
||||
The assessment is highly important and could significantly affect our future
|
||||
work, so it''s crucial to consider the current discourse on AI, its potential
|
||||
transformative power on industries and job markets, and general expectations
|
||||
of its future role.\n\nBegin! This is VERY important to you, use the tools available
|
||||
and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
|
||||
"gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
|
||||
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: scoring_examples\nTool Arguments: {}\nTool Description: Useful examples for scoring titles.\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [scoring_examples], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question"}, {"role": "user", "content": "\nCurrent Task: Evaluate the title ''The impact of AI in the future of work'' and
|
||||
give it an integer score between 1-5, based on your expert assessment.\n\nThis is the expect criteria for your final answer: Your best answer to your coworker asking you this, accounting for the context shared.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\nThe task is to assign a score to the given title based on its significance, relevance, and impactfulness regarding the future of work influenced by artificial intelligence. This score needs to reflect a thorough evaluation within the range of 1 (being the least impactful or relevant) to 5 (being the most impactful or relevant). The assessment is highly important and could significantly affect our future work, so it''s crucial to consider the current discourse on AI, its potential transformative power on industries and job markets, and general expectations of its future role.\n\nBegin! This is VERY important to you, use the tools available and give your
|
||||
best Final Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
@@ -283,8 +194,7 @@ interactions:
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000;
|
||||
__cf_bm=hmykq8dPVo.iRCPFLyDJJVhA3vlSAmoKNOK6szPX5ZI-1734025911-1.0.1.1-ukj3SfeY5GaS6q5LldvL5GcyN5W_on7HGUThOw9g_oKEVS8.E6bA3rTgQQZyloVkpXfJOSywGJnySVpMP.eJWA
|
||||
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000; __cf_bm=hmykq8dPVo.iRCPFLyDJJVhA3vlSAmoKNOK6szPX5ZI-1734025911-1.0.1.1-ukj3SfeY5GaS6q5LldvL5GcyN5W_on7HGUThOw9g_oKEVS8.E6bA3rTgQQZyloVkpXfJOSywGJnySVpMP.eJWA
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
@@ -310,21 +220,8 @@ interactions:
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AdhdoOZnBz23d3UiqKLBUQwmrMkSo\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1734025912,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"I need to evaluate the title \\\"The
|
||||
impact of AI in the future of work\\\" based on its significance, relevance,
|
||||
and impactfulness, considering the current discourse on AI and its transformative
|
||||
role in industries and job markets.\\n\\nAction: scoring_examples \\nAction
|
||||
Input: {\\\"title\\\": \\\"The impact of AI in the future of work\\\"} \",\n
|
||||
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
|
||||
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 400,\n \"completion_tokens\":
|
||||
67,\n \"total_tokens\": 467,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
||||
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
||||
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
|
||||
\"fp_6fc10e10eb\"\n}\n"
|
||||
content: "{\n \"id\": \"chatcmpl-AdhdoOZnBz23d3UiqKLBUQwmrMkSo\",\n \"object\": \"chat.completion\",\n \"created\": 1734025912,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"I need to evaluate the title \\\"The impact of AI in the future of work\\\" based on its significance, relevance, and impactfulness, considering the current discourse on AI and its transformative role in industries and job markets.\\n\\nAction: scoring_examples \\nAction Input: {\\\"title\\\": \\\"The impact of AI in the future of work\\\"} \",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 400,\n \"completion_tokens\": 67,\n \"total_tokens\": 467,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\"\
|
||||
: {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_6fc10e10eb\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
@@ -332,8 +229,6 @@ interactions:
|
||||
- 8f0f909d8ca16755-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
@@ -406,48 +301,10 @@ interactions:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an
|
||||
expert scorer, specialized in scoring titles.\nYour personal goal is: Score
|
||||
the title\nYou ONLY have access to the following tools, and should NEVER make
|
||||
up tools that are not listed here:\n\nTool Name: scoring_examples\nTool Arguments:
|
||||
{}\nTool Description: Useful examples for scoring titles.\n\nUse the following
|
||||
format:\n\nThought: you should always think about what to do\nAction: the action
|
||||
to take, only one name of [scoring_examples], just the name, exactly as it''s
|
||||
written.\nAction Input: the input to the action, just a simple python dictionary,
|
||||
enclosed in curly braces, using \" to wrap keys and values.\nObservation: the
|
||||
result of the action\n\nOnce all necessary information is gathered:\n\nThought:
|
||||
I now know the final answer\nFinal Answer: the final answer to the original
|
||||
input question"}, {"role": "user", "content": "\nCurrent Task: Evaluate the
|
||||
title ''The impact of AI in the future of work'' and give it an integer score
|
||||
between 1-5, based on your expert assessment.\n\nThis is the expect criteria
|
||||
for your final answer: Your best answer to your coworker asking you this, accounting
|
||||
for the context shared.\nyou MUST return the actual complete content as the
|
||||
final answer, not a summary.\n\nThis is the context you''re working with:\nThe
|
||||
task is to assign a score to the given title based on its significance, relevance,
|
||||
and impactfulness regarding the future of work influenced by artificial intelligence.
|
||||
This score needs to reflect a thorough evaluation within the range of 1 (being
|
||||
the least impactful or relevant) to 5 (being the most impactful or relevant).
|
||||
The assessment is highly important and could significantly affect our future
|
||||
work, so it''s crucial to consider the current discourse on AI, its potential
|
||||
transformative power on industries and job markets, and general expectations
|
||||
of its future role.\n\nBegin! This is VERY important to you, use the tools available
|
||||
and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role":
|
||||
"assistant", "content": "I need to evaluate the title \"The impact of AI in
|
||||
the future of work\" based on its significance, relevance, and impactfulness,
|
||||
considering the current discourse on AI and its transformative role in industries
|
||||
and job markets.\n\nAction: scoring_examples \nAction Input: {\"title\": \"The
|
||||
impact of AI in the future of work\"} \nObservation: \nI encountered an error
|
||||
while trying to use the tool. This was the error: Error.\n Tool scoring_examples
|
||||
accepts these inputs: Tool Name: scoring_examples\nTool Arguments: {}\nTool
|
||||
Description: Useful examples for scoring titles..\nMoving on then. I MUST either
|
||||
use a tool (use one at time) OR give my best final answer not both at the same
|
||||
time. To Use the following format:\n\nThought: you should always think about
|
||||
what to do\nAction: the action to take, should be one of [scoring_examples]\nAction
|
||||
Input: the input to the action, dictionary enclosed in curly braces\nObservation:
|
||||
the result of the action\n... (this Thought/Action/Action Input/Result can repeat
|
||||
N times)\nThought: I now can give a great answer\nFinal Answer: Your final answer
|
||||
must be the great and the most complete as possible, it must be outcome described"}],
|
||||
"model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
|
||||
body: '{"messages": [{"role": "system", "content": "You are Scorer. You''re an expert scorer, specialized in scoring titles.\nYour personal goal is: Score the title\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: scoring_examples\nTool Arguments: {}\nTool Description: Useful examples for scoring titles.\n\nUse the following format:\n\nThought: you should always think about what to do\nAction: the action to take, only one name of [scoring_examples], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question"}, {"role": "user", "content": "\nCurrent Task: Evaluate the title ''The impact of AI in the future of work'' and
|
||||
give it an integer score between 1-5, based on your expert assessment.\n\nThis is the expect criteria for your final answer: Your best answer to your coworker asking you this, accounting for the context shared.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nThis is the context you''re working with:\nThe task is to assign a score to the given title based on its significance, relevance, and impactfulness regarding the future of work influenced by artificial intelligence. This score needs to reflect a thorough evaluation within the range of 1 (being the least impactful or relevant) to 5 (being the most impactful or relevant). The assessment is highly important and could significantly affect our future work, so it''s crucial to consider the current discourse on AI, its potential transformative power on industries and job markets, and general expectations of its future role.\n\nBegin! This is VERY important to you, use the tools available and give your
|
||||
best Final Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I need to evaluate the title \"The impact of AI in the future of work\" based on its significance, relevance, and impactfulness, considering the current discourse on AI and its transformative role in industries and job markets.\n\nAction: scoring_examples \nAction Input: {\"title\": \"The impact of AI in the future of work\"} \nObservation: \nI encountered an error while trying to use the tool. This was the error: Error.\n Tool scoring_examples accepts these inputs: Tool Name: scoring_examples\nTool Arguments: {}\nTool Description: Useful examples for scoring titles..\nMoving on then. I MUST either use a tool (use one at time) OR give my best final answer not both at the same time. To Use the following format:\n\nThought: you should always think about what to do\nAction: the action to take, should be one of [scoring_examples]\nAction Input: the input to the action, dictionary enclosed in curly
|
||||
braces\nObservation: the result of the action\n... (this Thought/Action/Action Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal Answer: Your final answer must be the great and the most complete as possible, it must be outcome described"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
@@ -460,8 +317,7 @@ interactions:
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000;
|
||||
__cf_bm=hmykq8dPVo.iRCPFLyDJJVhA3vlSAmoKNOK6szPX5ZI-1734025911-1.0.1.1-ukj3SfeY5GaS6q5LldvL5GcyN5W_on7HGUThOw9g_oKEVS8.E6bA3rTgQQZyloVkpXfJOSywGJnySVpMP.eJWA
|
||||
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000; __cf_bm=hmykq8dPVo.iRCPFLyDJJVhA3vlSAmoKNOK6szPX5ZI-1734025911-1.0.1.1-ukj3SfeY5GaS6q5LldvL5GcyN5W_on7HGUThOw9g_oKEVS8.E6bA3rTgQQZyloVkpXfJOSywGJnySVpMP.eJWA
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
@@ -487,39 +343,9 @@ interactions:
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-Adhdp5Oq2gpRyz7oIh2YzjmLoX4RB\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1734025913,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"Thought: Since I cannot use the tool
|
||||
to score the title, I will need to perform a manual evaluation based on my expertise
|
||||
in scoring titles and the context provided. \\n\\nThe title \\\"The impact of
|
||||
AI in the future of work\\\" is highly relevant given the current state of discourse
|
||||
surrounding artificial intelligence and its rapid integration into various industries.
|
||||
The title effectively captures a significant topic\u2014how AI will shape the
|
||||
future of employment, job roles, and organizational structure.\\n\\nEvaluating
|
||||
its significance, the title could attract attention from professionals, scholars,
|
||||
and businesses interested in understanding the implications of AI on work environments
|
||||
and labor markets. It addresses both the potential benefits and challenges posed
|
||||
by AI, making it a crucial discussion point in contemporary and future work
|
||||
scenarios.\\n\\nFurthermore, its impactfulness lies in its ability to reflect
|
||||
concern over the potential job displacement caused by automation versus the
|
||||
new opportunities that AI might create. It also aligns with ongoing debates
|
||||
around the ethical use of AI in workplaces, further enhancing its relevance.\\n\\nConsidering
|
||||
all these factors, I would assign the title a score of 5 for its profound significance,
|
||||
relevance, and impactfulness concerning the future of work influenced by AI.\\n\\nThought:
|
||||
I now know the final answer\\nFinal Answer: The title \\\"The impact of AI in
|
||||
the future of work\\\" scores a 5 based on its significance, relevance, and
|
||||
impactfulness. It effectively addresses a crucial topic that is highly relevant
|
||||
in today's discourse on artificial intelligence and its transformative role
|
||||
in industries and job markets. This title is pivotal for understanding the future
|
||||
implications of AI on employment and work environments.\",\n \"refusal\":
|
||||
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 651,\n \"completion_tokens\":
|
||||
313,\n \"total_tokens\": 964,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
||||
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
||||
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
|
||||
\"fp_6fc10e10eb\"\n}\n"
|
||||
content: "{\n \"id\": \"chatcmpl-Adhdp5Oq2gpRyz7oIh2YzjmLoX4RB\",\n \"object\": \"chat.completion\",\n \"created\": 1734025913,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: Since I cannot use the tool to score the title, I will need to perform a manual evaluation based on my expertise in scoring titles and the context provided. \\n\\nThe title \\\"The impact of AI in the future of work\\\" is highly relevant given the current state of discourse surrounding artificial intelligence and its rapid integration into various industries. The title effectively captures a significant topic—how AI will shape the future of employment, job roles, and organizational structure.\\n\\nEvaluating its significance, the title could attract attention from professionals, scholars, and businesses interested in understanding the implications of AI on work environments and labor\
|
||||
\ markets. It addresses both the potential benefits and challenges posed by AI, making it a crucial discussion point in contemporary and future work scenarios.\\n\\nFurthermore, its impactfulness lies in its ability to reflect concern over the potential job displacement caused by automation versus the new opportunities that AI might create. It also aligns with ongoing debates around the ethical use of AI in workplaces, further enhancing its relevance.\\n\\nConsidering all these factors, I would assign the title a score of 5 for its profound significance, relevance, and impactfulness concerning the future of work influenced by AI.\\n\\nThought: I now know the final answer\\nFinal Answer: The title \\\"The impact of AI in the future of work\\\" scores a 5 based on its significance, relevance, and impactfulness. It effectively addresses a crucial topic that is highly relevant in today's discourse on artificial intelligence and its transformative role in industries and job markets. This\
|
||||
\ title is pivotal for understanding the future implications of AI on employment and work environments.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 651,\n \"completion_tokens\": 313,\n \"total_tokens\": 964,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_6fc10e10eb\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
@@ -527,8 +353,6 @@ interactions:
|
||||
- 8f0f90a5fa396755-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
@@ -568,68 +392,11 @@ interactions:
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
|
||||
are a seasoned manager with a knack for getting the best out of your team.\nYou
|
||||
are also known for your ability to delegate work to the right people, and to
|
||||
ask the right questions to get the best out of your team.\nEven though you don''t
|
||||
perform tasks by yourself, you have a lot of experience in the field, which
|
||||
allows you to properly evaluate the work of your team members.\nYour personal
|
||||
goal is: Manage the team to complete the task in the best way possible.\nYou
|
||||
ONLY have access to the following tools, and should NEVER make up tools that
|
||||
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
|
||||
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
|
||||
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
|
||||
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
|
||||
''str''}}\nTool Description: Delegate a specific task to one of the following
|
||||
coworkers: Scorer\nThe input to this tool should be the coworker, the task you
|
||||
want them to do, and ALL necessary context to execute the task, they know nothing
|
||||
about the task, so share absolute everything you know, don''t reference things
|
||||
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
|
||||
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
|
||||
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
|
||||
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
|
||||
''str''}}\nTool Description: Ask a specific question to one of the following
|
||||
coworkers: Scorer\nThe input to this tool should be the coworker, the question
|
||||
you have for them, and ALL necessary context to ask the question properly, they
|
||||
know nothing about the question, so share absolute everything you know, don''t
|
||||
reference things but instead explain them.\n\nUse the following format:\n\nThought:
|
||||
you should always think about what to do\nAction: the action to take, only one
|
||||
name of [Delegate work to coworker, Ask question to coworker], just the name,
|
||||
exactly as it''s written.\nAction Input: the input to the action, just a simple
|
||||
python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
|
||||
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
|
||||
I now know the final answer\nFinal Answer: the final answer to the original
|
||||
input question"}, {"role": "user", "content": "\nCurrent Task: Give me an integer
|
||||
score between 1-5 for the following title: ''The impact of AI in the future
|
||||
of work'', check examples to based your evaluation.\n\nThis is the expect criteria
|
||||
for your final answer: The score of the title.\nyou MUST return the actual complete
|
||||
content as the final answer, not a summary.\n\nBegin! This is VERY important
|
||||
to you, use the tools available and give your best Final Answer, your job depends
|
||||
on it!\n\nThought:"}, {"role": "assistant", "content": "Thought: To give an
|
||||
accurate score for the title \"The impact of AI in the future of work\" based
|
||||
on the specified criteria, I''ll need the expertise of the Scorer. They specialize
|
||||
in evaluating content, so I must delegate this task to them. I need to provide
|
||||
them with all the necessary context, including the title and the importance
|
||||
of giving a well-considered, integer score between 1-5. Since the request stresses
|
||||
the importance of this task and its implications for my job, I will make sure
|
||||
to communicate the urgency and the criteria very clearly to the Scorer.\n\nAction:
|
||||
Delegate work to coworker\n\nAction Input: {\"task\": \"Evaluate the title ''The
|
||||
impact of AI in the future of work'' and give it an integer score between 1-5,
|
||||
based on your expert assessment.\", \"context\": \"The task is to assign a score
|
||||
to the given title based on its significance, relevance, and impactfulness regarding
|
||||
the future of work influenced by artificial intelligence. This score needs to
|
||||
reflect a thorough evaluation within the range of 1 (being the least impactful
|
||||
or relevant) to 5 (being the most impactful or relevant). The assessment is
|
||||
highly important and could significantly affect our future work, so it''s crucial
|
||||
to consider the current discourse on AI, its potential transformative power
|
||||
on industries and job markets, and general expectations of its future role.\",
|
||||
\"coworker\": \"Scorer\"}\nObservation: The title \"The impact of AI in the
|
||||
future of work\" scores a 5 based on its significance, relevance, and impactfulness.
|
||||
It effectively addresses a crucial topic that is highly relevant in today''s
|
||||
discourse on artificial intelligence and its transformative role in industries
|
||||
and job markets. This title is pivotal for understanding the future implications
|
||||
of AI on employment and work environments."}], "model": "gpt-4-0125-preview",
|
||||
"stop": ["\nObservation:"], "stream": false}'
|
||||
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You are a seasoned manager with a knack for getting the best out of your team.\nYou are also known for your ability to delegate work to the right people, and to ask the right questions to get the best out of your team.\nEven though you don''t perform tasks by yourself, you have a lot of experience in the field, which allows you to properly evaluate the work of your team members.\nYour personal goal is: Manage the team to complete the task in the best way possible.\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments: {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'': {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to delegate to'', ''type'': ''str''}}\nTool Description: Delegate a specific
|
||||
task to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don''t reference things but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments: {''question'': {''description'': ''The question to ask'', ''type'': ''str''}, ''context'': {''description'': ''The context for the question'', ''type'': ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don''t reference things but instead explain them.\n\nUse the following format:\n\nThought: you
|
||||
should always think about what to do\nAction: the action to take, only one name of [Delegate work to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple python dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n\nOnce all necessary information is gathered:\n\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question"}, {"role": "user", "content": "\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work'', check examples to based your evaluation.\n\nThis is the expect criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role":
|
||||
"assistant", "content": "Thought: To give an accurate score for the title \"The impact of AI in the future of work\" based on the specified criteria, I''ll need the expertise of the Scorer. They specialize in evaluating content, so I must delegate this task to them. I need to provide them with all the necessary context, including the title and the importance of giving a well-considered, integer score between 1-5. Since the request stresses the importance of this task and its implications for my job, I will make sure to communicate the urgency and the criteria very clearly to the Scorer.\n\nAction: Delegate work to coworker\n\nAction Input: {\"task\": \"Evaluate the title ''The impact of AI in the future of work'' and give it an integer score between 1-5, based on your expert assessment.\", \"context\": \"The task is to assign a score to the given title based on its significance, relevance, and impactfulness regarding the future of work influenced by artificial intelligence. This score
|
||||
needs to reflect a thorough evaluation within the range of 1 (being the least impactful or relevant) to 5 (being the most impactful or relevant). The assessment is highly important and could significantly affect our future work, so it''s crucial to consider the current discourse on AI, its potential transformative power on industries and job markets, and general expectations of its future role.\", \"coworker\": \"Scorer\"}\nObservation: The title \"The impact of AI in the future of work\" scores a 5 based on its significance, relevance, and impactfulness. It effectively addresses a crucial topic that is highly relevant in today''s discourse on artificial intelligence and its transformative role in industries and job markets. This title is pivotal for understanding the future implications of AI on employment and work environments."}], "model": "gpt-4-0125-preview", "stop": ["\nObservation:"], "stream": false}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
@@ -642,8 +409,7 @@ interactions:
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000;
|
||||
__cf_bm=hmykq8dPVo.iRCPFLyDJJVhA3vlSAmoKNOK6szPX5ZI-1734025911-1.0.1.1-ukj3SfeY5GaS6q5LldvL5GcyN5W_on7HGUThOw9g_oKEVS8.E6bA3rTgQQZyloVkpXfJOSywGJnySVpMP.eJWA
|
||||
- _cfuvid=FasG_74jjKfEtA2Mjn2iKdu62tv3zosBxYNYTk1E12M-1734025911900-0.0.1.1-604800000; __cf_bm=hmykq8dPVo.iRCPFLyDJJVhA3vlSAmoKNOK6szPX5ZI-1734025911-1.0.1.1-ukj3SfeY5GaS6q5LldvL5GcyN5W_on7HGUThOw9g_oKEVS8.E6bA3rTgQQZyloVkpXfJOSywGJnySVpMP.eJWA
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
@@ -669,18 +435,7 @@ interactions:
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-Adhduvx929aETP7FXGXyUZWKGhHgH\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1734025918,\n \"model\": \"gpt-4-0125-preview\",\n
|
||||
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
|
||||
\"assistant\",\n \"content\": \"Thought: I now know the final answer\\n\\nFinal
|
||||
Answer: The score of the title \\\"The impact of AI in the future of work\\\"
|
||||
is 5.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
|
||||
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 996,\n \"completion_tokens\":
|
||||
32,\n \"total_tokens\": 1028,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
|
||||
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
|
||||
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
|
||||
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
|
||||
null\n}\n"
|
||||
content: "{\n \"id\": \"chatcmpl-Adhduvx929aETP7FXGXyUZWKGhHgH\",\n \"object\": \"chat.completion\",\n \"created\": 1734025918,\n \"model\": \"gpt-4-0125-preview\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now know the final answer\\n\\nFinal Answer: The score of the title \\\"The impact of AI in the future of work\\\" is 5.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 996,\n \"completion_tokens\": 32,\n \"total_tokens\": 1028,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
@@ -688,8 +443,6 @@ interactions:
|
||||
- 8f0f90c5693c6755-ATL
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
@@ -729,65 +482,11 @@ interactions:
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You
|
||||
are a seasoned manager with a knack for getting the best out of your team.\nYou
|
||||
are also known for your ability to delegate work to the right people, and to
|
||||
ask the right questions to get the best out of your team.\nEven though you don''t
|
||||
perform tasks by yourself, you have a lot of experience in the field, which
|
||||
allows you to properly evaluate the work of your team members.\nYour personal
|
||||
goal is: Manage the team to complete the task in the best way possible.\nYou
|
||||
ONLY have access to the following tools, and should NEVER make up tools that
|
||||
are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments:
|
||||
{''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'':
|
||||
{''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'':
|
||||
{''description'': ''The role/name of the coworker to delegate to'', ''type'':
|
||||
''str''}}\nTool Description: Delegate a specific task to one of the following
|
||||
coworkers: Scorer\nThe input to this tool should be the coworker, the task you
|
||||
want them to do, and ALL necessary context to execute the task, they know nothing
|
||||
about the task, so share absolutely everything you know, don''t reference things
|
||||
but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments:
|
||||
{''question'': {''description'': ''The question to ask'', ''type'': ''str''},
|
||||
''context'': {''description'': ''The context for the question'', ''type'': ''str''},
|
||||
''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'':
|
||||
''str''}}\nTool Description: Ask a specific question to one of the following
|
||||
coworkers: Scorer\nThe input to this tool should be the coworker, the question
|
||||
you have for them, and ALL necessary context to ask the question properly, they
|
||||
know nothing about the question, so share absolutely everything you know, don''t
|
||||
reference things but instead explain them.\n\nIMPORTANT: Use the following format
|
||||
in your response:\n\n```\nThought: you should always think about what to do\nAction:
|
||||
the action to take, only one name of [Delegate work to coworker, Ask question
|
||||
to coworker], just the name, exactly as it''s written.\nAction Input: the input
|
||||
to the action, just a simple JSON object, enclosed in curly braces, using \"
|
||||
to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
|
||||
all necessary information is gathered, return the following format:\n\n```\nThought:
|
||||
I now know the final answer\nFinal Answer: the final answer to the original
|
||||
input question\n```"}, {"role": "user", "content": "\nCurrent Task: Give me
|
||||
an integer score between 1-5 for the following title: ''The impact of AI in
|
||||
the future of work'', check examples to based your evaluation.\n\nThis is the
|
||||
expected criteria for your final answer: The score of the title.\nyou MUST return
|
||||
the actual complete content as the final answer, not a summary.\n\nBegin! This
|
||||
is VERY important to you, use the tools available and give your best Final Answer,
|
||||
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "Thought:
|
||||
To give an accurate score for the title \"The impact of AI in the future of
|
||||
work\" based on the specified criteria, I''ll need the expertise of the Scorer.
|
||||
They specialize in evaluating content, so I must delegate this task to them.
|
||||
I need to provide them with all the necessary context, including the title and
|
||||
the importance of giving a well-considered, integer score between 1-5. Since
|
||||
the request stresses the importance of this task and its implications for my
|
||||
job, I will make sure to communicate the urgency and the criteria very clearly
|
||||
to the Scorer.\n\nAction: Delegate work to coworker\n\nAction Input: {\"task\":
|
||||
\"Evaluate the title ''The impact of AI in the future of work'' and give it
|
||||
an integer score between 1-5, based on your expert assessment.\", \"context\":
|
||||
\"The task is to assign a score to the given title based on its significance,
|
||||
relevance, and impactfulness regarding the future of work influenced by artificial
|
||||
intelligence. This score needs to reflect a thorough evaluation within the range
|
||||
of 1 (being the least impactful or relevant) to 5 (being the most impactful
|
||||
or relevant). The assessment is highly important and could significantly affect
|
||||
our future work, so it''s crucial to consider the current discourse on AI, its
|
||||
potential transformative power on industries and job markets, and general expectations
|
||||
of its future role.\", \"coworker\": \"Scorer\"}\nObservation: The score of
|
||||
the title \"The impact of AI in the future of work\" is 5."}], "model": "gpt-4-0125-preview",
|
||||
"stop": ["\nObservation:"]}'
|
||||
body: '{"messages": [{"role": "system", "content": "You are Crew Manager. You are a seasoned manager with a knack for getting the best out of your team.\nYou are also known for your ability to delegate work to the right people, and to ask the right questions to get the best out of your team.\nEven though you don''t perform tasks by yourself, you have a lot of experience in the field, which allows you to properly evaluate the work of your team members.\nYour personal goal is: Manage the team to complete the task in the best way possible.\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: Delegate work to coworker\nTool Arguments: {''task'': {''description'': ''The task to delegate'', ''type'': ''str''}, ''context'': {''description'': ''The context for the task'', ''type'': ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to delegate to'', ''type'': ''str''}}\nTool Description: Delegate a specific
|
||||
task to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolutely everything you know, don''t reference things but instead explain them.\nTool Name: Ask question to coworker\nTool Arguments: {''question'': {''description'': ''The question to ask'', ''type'': ''str''}, ''context'': {''description'': ''The context for the question'', ''type'': ''str''}, ''coworker'': {''description'': ''The role/name of the coworker to ask'', ''type'': ''str''}}\nTool Description: Ask a specific question to one of the following coworkers: Scorer\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolutely everything you know, don''t reference things but instead explain them.\n\nIMPORTANT: Use the following format
|
||||
in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [Delegate work to coworker, Ask question to coworker], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question\n```"}, {"role": "user", "content": "\nCurrent Task: Give me an integer score between 1-5 for the following title: ''The impact of AI in the future of work'', check examples to based your evaluation.\n\nThis is the expected criteria for your final answer: The score of the title.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available
|
||||
and give your best Final Answer, your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "Thought: To give an accurate score for the title \"The impact of AI in the future of work\" based on the specified criteria, I''ll need the expertise of the Scorer. They specialize in evaluating content, so I must delegate this task to them. I need to provide them with all the necessary context, including the title and the importance of giving a well-considered, integer score between 1-5. Since the request stresses the importance of this task and its implications for my job, I will make sure to communicate the urgency and the criteria very clearly to the Scorer.\n\nAction: Delegate work to coworker\n\nAction Input: {\"task\": \"Evaluate the title ''The impact of AI in the future of work'' and give it an integer score between 1-5, based on your expert assessment.\", \"context\": \"The task is to assign a score to the given title based on its significance, relevance, and impactfulness
|
||||
regarding the future of work influenced by artificial intelligence. This score needs to reflect a thorough evaluation within the range of 1 (being the least impactful or relevant) to 5 (being the most impactful or relevant). The assessment is highly important and could significantly affect our future work, so it''s crucial to consider the current discourse on AI, its potential transformative power on industries and job markets, and general expectations of its future role.\", \"coworker\": \"Scorer\"}\nObservation: The score of the title \"The impact of AI in the future of work\" is 5."}], "model": "gpt-4-0125-preview", "stop": ["\nObservation:"]}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
@@ -829,23 +528,13 @@ interactions:
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAAwAAAP//jJJNaxsxEIbv/hWDznaIE9t19uYWUkLTQiG3OiyydnZXtlajSLN2m+D/
|
||||
XqSNvZs2hV4E0jPvq/l6GQEIXYgMhKolq8aZyafl5nq7emqWz9+/bO8/Pu9n3+4VL+nz01e8FeOo
|
||||
oM0WFZ9UF4oaZ5A12Q4rj5Ixuk4/zBfTxXw6nSfQUIEmyirHk9nkcno1nziPe42HV2VNWmEQGfwY
|
||||
AQC8pDPmaAv8KTK4HJ9eGgxBViiycxCA8GTii5Ah6MDSshj3UJFltCnth5raquYM7sDSAXbx4Bqh
|
||||
1FYakDYc0K/t2t6m+yrdM3ioEYIij0BlCmfNBmEtItCNk4ojWd2Btp1dy20XfSC/WwvQAeYXw5w8
|
||||
lm2QsSe2NWYApLXEMvY0dePxlRzP9RuqnKdN+EMqSm11qHOPMpCNtQYmJxI9jgAeU5/bN60TzlPj
|
||||
OGfaYfruZnHV+Yl+tD29PkEmlmagupmN3/HLC2SpTRhMSiipaix6aT9W2RaaBmA0qPrvbN7z7irX
|
||||
tvof+x4ohY6xyJ3HQqu3FfdhHuPm/yvs3OWUsAjo91phzhp9nESBpWxNt5Mi/AqMTV5qW6F3XqfF
|
||||
jJMcHUe/AQAA//8DAErhO7yXAwAA
|
||||
string: "{\n \"id\": \"chatcmpl-C8b3jAqm8zQKjLBzv4NLct8oGqMeF\",\n \"object\": \"chat.completion\",\n \"created\": 1756165115,\n \"model\": \"gpt-4-0125-preview\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now know the final answer\\n\\nFinal Answer: The score of the title \\\"The impact of AI in the future of work\\\" is 5.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 962,\n \"completion_tokens\": 32,\n \"total_tokens\": 994,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\"\
|
||||
,\n \"system_fingerprint\": null\n}\n"
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 974eec827a978486-SJC
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
@@ -853,11 +542,8 @@ interactions:
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=r95s2Hh1kHgI6PI08wwTySLyufxeDnmixIX5GVDEyoA-1756165116-1.0.1.1-X5dML3NG4uvFgDnjqJ4pQWbB9MyxJisxAZJlRivMc7T1f83cCNBH_cy5fJjn4XjKks_UKUUj5PvBGifu2gLkaiqYYWvbSjrhjKseuPN8.Q4;
|
||||
path=/; expires=Tue, 26-Aug-25 00:08:36 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=lnKPmS3pW0Tw6qE4ZI8cf4lyVDuLg7ZNxmzxi7CqlME-1756165116673-0.0.1.1-604800000;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
- __cf_bm=r95s2Hh1kHgI6PI08wwTySLyufxeDnmixIX5GVDEyoA-1756165116-1.0.1.1-X5dML3NG4uvFgDnjqJ4pQWbB9MyxJisxAZJlRivMc7T1f83cCNBH_cy5fJjn4XjKks_UKUUj5PvBGifu2gLkaiqYYWvbSjrhjKseuPN8.Q4; path=/; expires=Tue, 26-Aug-25 00:08:36 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
- _cfuvid=lnKPmS3pW0Tw6qE4ZI8cf4lyVDuLg7ZNxmzxi7CqlME-1756165116673-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
Transfer-Encoding:
|
||||
|
||||
Reference in New Issue
Block a user