andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Adding VCr and cassetes

Browse Source
This commit is contained in:
João Moura
2023-12-27 16:16:43 -03:00
parent b8974c1f91
commit 6b2234fcef
12 changed files with 4600 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

251
tests/agent_tools/cassettes/test_ask_question.yaml Normal file
View File

@@ -0,0 +1,251 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re
an expert researcher, specialized in technology\n\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou
have access to the following tools:\n\n\n\nTo use a tool, please use the exact
following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
action to take, should be one of []\nAction Input: the input to the action\nObservation:
the result of the action\n```\n\nWhen you have a response for your task, or
if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
is the summary of your work so far:\n The human asks the AI for its opinion
on AI agents, based on the impression that the AI dislikes them. The AI clarifies
that it doesn''t hold personal sentiments towards AI or any technology, but
instead analyzes them objectively. The AI finds AI agents a fascinating domain
of research with great potential for task automation and optimization across
industries, but acknowledges they present challenges such as ethical considerations
around privacy and decision-making.\nBegin! This is VERY important to you, your
job depends on it!\n\nCurrent Task: do you hate AI Agents?\n\nThis is the context
you are working with:\nI heard you LOVE them\n\n"}], "model": "gpt-4", "n":
1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1494'
content-type:
- application/json
cookie:
- __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
_cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8Xx2vMXN4WCrWeeO4DOAowhb3oeDJ\",\n \"object\":
\"chat.completion\",\n \"created\": 1703102489,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\nFinal
Answer: As an AI, I don't possess feelings or emotions, so I don't love or hate
anything. However, I can provide detailed analysis and research on AI agents.
They are a fascinating field of study with the potential to revolutionize many
industries, although they also present certain challenges and ethical considerations.\"\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 291,\n \"completion_tokens\":
75,\n \"total_tokens\": 366\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 838a7a3efab6a4b0-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 20 Dec 2023 20:01:35 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '6060'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299652'
x-ratelimit-remaining-tokens_usage_based:
- '299652'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 69ms
x-ratelimit-reset-tokens_usage_based:
- 69ms
x-request-id:
- 3ad0d047d5260434816f61ec105bdbb8
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI for its opinion on AI
agents, based on the impression that the AI dislikes them. The AI clarifies
that it doesn''t hold personal sentiments towards AI or any technology, but
instead analyzes them objectively. The AI finds AI agents a fascinating domain
of research with great potential for task automation and optimization across
industries, but acknowledges they present challenges such as ethical considerations
around privacy and decision-making.\n\nNew lines of conversation:\nHuman: do
you hate AI Agents?\n\nThis is the context you are working with:\nI heard you
LOVE them\nAI: As an AI, I don''t possess feelings or emotions, so I don''t
love or hate anything. However, I can provide detailed analysis and research
on AI agents. They are a fascinating field of study with the potential to revolutionize
many industries, although they also present certain challenges and ethical considerations.\n\nNew
summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1726'
content-type:
- application/json
cookie:
- __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
_cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8Xx32X5innWZd8vEETP1jZMLH3b1O\",\n \"object\":
\"chat.completion\",\n \"created\": 1703102496,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI for its opinion
on AI agents, based on the impression that the AI dislikes them. The AI clarifies
that it doesn't hold personal sentiments towards AI or any technology, but instead
analyzes them objectively. The AI finds AI agents a fascinating domain of research
with great potential for task automation and optimization across industries,
but acknowledges they present challenges such as ethical considerations around
privacy and decision-making. When asked again if it hates or loves AI agents,
the AI reiterates that it doesn't possess feelings or emotions, but can provide
detailed analysis and research on AI agents.\"\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
300,\n \"completion_tokens\": 117,\n \"total_tokens\": 417\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 838a7a67ecaca4b0-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 20 Dec 2023 20:01:41 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '5610'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299585'
x-ratelimit-remaining-tokens_usage_based:
- '299585'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 83ms
x-ratelimit-reset-tokens_usage_based:
- 83ms
x-request-id:
- 5b0b96506faa544c5d35b52286a3389c
http_version: HTTP/1.1
status_code: 200
version: 1

250
tests/agent_tools/cassettes/test_delegate_work.yaml Normal file
View File

@@ -0,0 +1,250 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re
an expert researcher, specialized in technology\n\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou
have access to the following tools:\n\n\n\nTo use a tool, please use the exact
following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
action to take, should be one of []\nAction Input: the input to the action\nObservation:
the result of the action\n```\n\nWhen you have a response for your task, or
if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
is the summary of your work so far:\n \nBegin! This is VERY important to
you, your job depends on it!\n\nCurrent Task: share your take on AI Agents\n\nThis
is the context you are working with:\nI heard you hate them\n\n"}], "model":
"gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1030'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8Xx2cQWLZ8Nd34HGmbQluyZWlD58b\",\n \"object\":
\"chat.completion\",\n \"created\": 1703102470,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\nFinal
Answer: I apologize if my previous statements have given you the impression
that I hate AI agents. As a technology researcher, I don't hold personal sentiments
towards AI or any other technology. Rather, I analyze them objectively based
on their capabilities, applications, and implications. AI agents, in particular,
are a fascinating domain of research. They hold tremendous potential in automating
and optimizing various tasks across industries. However, like any other technology,
they come with their own set of challenges, such as ethical considerations around
privacy and decision-making. My objective is to understand these technologies
in depth and provide a balanced view.\"\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
211,\n \"completion_tokens\": 134,\n \"total_tokens\": 345\n },\n \"system_fingerprint\":
null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 838a79c59ea7a4b0-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 20 Dec 2023 20:01:23 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
path=/; expires=Wed, 20-Dec-23 20:31:23 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '12923'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299769'
x-ratelimit-remaining-tokens_usage_based:
- '299769'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 46ms
x-ratelimit-reset-tokens_usage_based:
- 46ms
x-request-id:
- 6468cdd7ae76aea910c72a503a58b8da
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "user", "content": "Progressively summarize the
lines of conversation provided, adding onto the previous summary returning a
new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
of artificial intelligence. The AI thinks artificial intelligence is a force
for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
intelligence is a force for good?\nAI: Because artificial intelligence will
help humans reach their full potential.\n\nNew summary:\nThe human asks what
the AI thinks of artificial intelligence. The AI thinks artificial intelligence
is a force for good because it will help humans reach their full potential.\nEND
OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: share
your take on AI Agents\n\nThis is the context you are working with:\nI heard
you hate them\nAI: I apologize if my previous statements have given you the
impression that I hate AI agents. As a technology researcher, I don''t hold
personal sentiments towards AI or any other technology. Rather, I analyze them
objectively based on their capabilities, applications, and implications. AI
agents, in particular, are a fascinating domain of research. They hold tremendous
potential in automating and optimizing various tasks across industries. However,
like any other technology, they come with their own set of challenges, such
as ethical considerations around privacy and decision-making. My objective is
to understand these technologies in depth and provide a balanced view.\n\nNew
summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1622'
content-type:
- application/json
cookie:
- __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
_cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.6.0
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.6.0
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-8Xx2pqWD01uG0roGJ4daSfvaXLchg\",\n \"object\":
\"chat.completion\",\n \"created\": 1703102483,\n \"model\": \"gpt-4-0613\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"The human asks the AI for its opinion
on AI agents, based on the impression that the AI dislikes them. The AI clarifies
that it doesn't hold personal sentiments towards AI or any technology, but instead
analyzes them objectively. The AI finds AI agents a fascinating domain of research
with great potential for task automation and optimization across industries,
but acknowledges they present challenges such as ethical considerations around
privacy and decision-making.\"\n },\n \"logprobs\": null,\n \"finish_reason\":
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 279,\n \"completion_tokens\":
81,\n \"total_tokens\": 360\n },\n \"system_fingerprint\": null\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 838a7a17fbb9a4b0-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 20 Dec 2023 20:01:29 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- user-z7g4wmlazxqvc5wjyaaaocfz
openai-processing-ms:
- '5872'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-limit-tokens_usage_based:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299610'
x-ratelimit-remaining-tokens_usage_based:
- '299610'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 77ms
x-ratelimit-reset-tokens_usage_based:
- 77ms
x-request-id:
- bff02b569530c001aa9a2adba9adbeb9
http_version: HTTP/1.1
status_code: 200
version: 1