andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 16:48:30 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

experimenting to see if unique content is an issue with knowledge

Browse Source
This commit is contained in:
Brandon Hancock
2024-12-12 12:53:10 -05:00
parent 69ab290f13
commit 4448cf8463
2 changed files with 735 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/agent_test.py
View File

@@ -1595,19 +1595,15 @@ def test_agent_execute_task_with_ollama():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_with_knowledge_sources():
# Create a knowledge source with some content
content = "Brandon's favorite color is blue and he likes Mexican food."
string_source = StringKnowledgeSource(
content=content, metadata={"preference": "personal"}
)
content = "Brandon's favorite color is red and he likes Mexican food."
string_source = StringKnowledgeSource(content=content)
with patch(
"crewai.knowledge.storage.knowledge_storage.KnowledgeStorage"
) as MockKnowledge:
mock_knowledge_instance = MockKnowledge.return_value
mock_knowledge_instance.sources = [string_source]
mock_knowledge_instance.query.return_value = [
{"content": content, "metadata": {"preference": "personal"}}
]
mock_knowledge_instance.query.return_value = [{"content": content}]
agent = Agent(
role="Information Agent",
@@ -1628,4 +1624,4 @@ def test_agent_with_knowledge_sources():
result = crew.kickoff()
# Assert that the agent provides the correct information
assert "blue" in result.raw.lower()
assert "red" in result.raw.lower()

731
tests/cassettes/test_increment_tool_errors.yaml Normal file
View File

@@ -0,0 +1,731 @@
interactions:
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '3083'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 12 Dec 2024 17:51:49 GMT
status:
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}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2994'
content-type:
- application/json
cookie:
- _cfuvid=MmeN9oHWrBLThkEJdaSFHBfWe95JvA8iFnnt7CC92tk-1732107842102-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.10
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"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f0f9070fd206755-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Dec 2024 17:51:51 GMT
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
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '7000'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1999280'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 21ms
x-request-id:
- req_77f5ddcc16e659a308d96671e0ebdded
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}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2112'
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
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.10
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"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f0f909d8ca16755-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Dec 2024 17:51:53 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1099'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999498'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_61412618dc60f9f52215463e4416bdaa
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |
CqYBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSfgoSChBjcmV3YWkudGVs
ZW1ldHJ5EmgKEKVP/jWcz2tSenrJssmLMfwSCDf4c3vyfnKbKhBUb29sIFVzYWdlIEVycm9yMAE5
8IAzf2F/EBhBmHBGf2F/EBhKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC44Ni4wegIYAYUBAAEAAA==
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '169'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Thu, 12 Dec 2024 17:51:54 GMT
status:
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}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '3325'
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
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.10
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"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f0f90a5fa396755-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Dec 2024 17:51:58 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '4850'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999210'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_8974594f8b3ba52b6bb30a6a1870f1fb
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}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '4843'
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
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.10
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"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f0f90c5693c6755-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 12 Dec 2024 17:51:59 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '1402'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '2000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '1998832'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 35ms
x-request-id:
- req_c065668c78262d2781db5b3b04f70dba
http_version: HTTP/1.1
status_code: 200
version: 1