andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-09 08:08:32 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Add support to delegate work

Browse Source
This commit is contained in:
Joao Moura
2023-11-10 18:15:45 -03:00
parent d6989b7959
commit 6ff18128a7
15 changed files with 1786 additions and 1636 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
tests/agent_test.py
View File

@@ -18,7 +18,7 @@ def test_agent_creation():
assert agent.backstory == "test backstory"
assert agent.tools == []
def test_agent_default_value():
def test_agent_default_values():
agent = Agent(
role="test role",
goal="test goal",
@@ -29,6 +29,7 @@ def test_agent_default_value():
assert agent.llm.model_name == "gpt-4"
assert agent.llm.temperature == 0.7
assert agent.llm.verbose == False
assert agent.allow_delegation == True
def test_custom_llm():
agent = Agent(
@@ -50,11 +51,12 @@ def test_agent_execution():
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory"
backstory="test backstory",
allow_delegation=False
)
output = agent.execute_task("How much is 1 + 1?")
assert output == "1 + 1 equals 2."
assert output == "1 + 1 = 2"
@pytest.mark.vcr()
def test_agent_execution_with_tools():
@@ -73,8 +75,35 @@ def test_agent_execution_with_tools():
role="test role",
goal="test goal",
backstory="test backstory",
tools=[multiplier]
tools=[multiplier],
allow_delegation=False
)
output = agent.execute_task("What is 3 times 4")
assert output == "3 times 4 is 12."
assert output == "3 times 4 is 12"
@pytest.mark.vcr()
def test_agent_execution_with_specific_tools():
from langchain.tools import tool
@tool
def multiplier(numbers) -> float:
"""Useful for when you need to multiply two numbers together.
The input to this tool should be a comma separated list of numbers of
length two, representing the two numbers you want to multiply together.
For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
a, b = numbers.split(',')
return int(a) * int(b)
agent = Agent(
role="test role",
goal="test goal",
backstory="test backstory",
allow_delegation=False
)
output = agent.execute_task(
task="What is 3 times 4",
tools=[multiplier]
)
assert output == "12"

0
tests/agent_tools/__init__.py Normal file
View File

46
tests/agent_tools/agent_tools_test.py Normal file
View File

@@ -0,0 +1,46 @@
"""Test Agent creation and execution basic functionality."""
import pytest
from ...crewai import Agent
from ...crewai.tools.agent_tools import AgentTools
researcher = Agent(
role="researcher",
goal="make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology",
allow_delegation=False
)
tools = AgentTools(agents=[researcher])
@pytest.mark.vcr()
def test_delegate_work():
result = tools.delegate_work(
command="researcher|share your take on AI Agents|I heard you hate them"
)
assert result == "As a technology researcher, it's important to maintain objectivity. AI agents have their own merits and demerits. On the positive side, they can automate routine tasks, improve efficiency, and enable new forms of communication and decision-making. However, there are potential downsides, like job displacement due to automation and concerns about privacy and security. It's not accurate to say that I hate them, but rather, I recognize the potential implications - both positive and negative - of their use."
@pytest.mark.vcr()
def test_ask_question():
result = tools.ask_question(
command="researcher|do you hate AI Agents?|I heard you LOVE them"
)
assert result == "As a researcher, my feelings towards AI Agents are neutral. I neither love nor hate them. I study and analyze them objectively to understand their potential, capabilities, and limitations. While I appreciate the technological advancement they represent, my job is to approach them from an analytical and scientific perspective."
def test_delegate_work_to_wrong_agent():
result = tools.ask_question(
command="writer|share your take on AI Agents|I heard you hate them"
)
assert result == "Error executing tool."
def test_ask_question_to_wrong_agent():
result = tools.ask_question(
command="writer|do you hate AI Agents?|I heard you LOVE them"
)
assert result == "Error executing tool."

207
tests/agent_tools/cassettes/test_ask_question.yaml Normal file
View File

@@ -0,0 +1,207 @@
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\nTOOLS:\n------\n\nYou
have access to the following tools:\n\n\n\nTo use a tool, please use the 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: do you hate AI Agents?\n\nThis
is the context you are working with:\nI heard you LOVE them\n\n"}], "model":
"gpt-4", "max_tokens": null, "stream": false, "n": 1, "temperature": 0.7, "stop":
["\nObservation"]}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1042'
Content-Type:
- application/json
Cookie:
- __cf_bm=tK5mxmIOd60ucoQKATtbR8SRQ_JqyXuQNF3_REtUp8Y-1699495558-0-AYxCQwfqvfsWejuO19whuBqtsq2nrXi+wWcAirvErhN24TrrInAJKVGS9DLI/ZeUJPnfoX8EyTWdV32kPHM68cM=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 823282bba87b1ceb-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 09 Nov 2023 02:08:59 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '3917'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '100'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '299770'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 45ms
x-request-id:
- 9ddc4f75922fceafc44487e8f65707eb
status:
code: 200
message: OK
- 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: do you
hate AI Agents?\n\nThis is the context you are working with:\nI heard you LOVE
them\nAI: As a researcher, my feelings towards AI Agents are neutral. I neither
love nor hate them. I study and analyze them objectively to understand their
potential, capabilities, and limitations. While I appreciate the technological
advancement they represent, my job is to approach them from an analytical and
scientific perspective.\n\nNew summary:"}], "model": "gpt-4", "max_tokens":
null, "stream": false, "n": 1, "temperature": 0.7}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1289'
Content-Type:
- application/json
Cookie:
- __cf_bm=tK5mxmIOd60ucoQKATtbR8SRQ_JqyXuQNF3_REtUp8Y-1699495558-0-AYxCQwfqvfsWejuO19whuBqtsq2nrXi+wWcAirvErhN24TrrInAJKVGS9DLI/ZeUJPnfoX8EyTWdV32kPHM68cM=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 823282d5cdcc1ceb-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 09 Nov 2023 02:09:03 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '3310'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '100'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '299699'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 60ms
x-request-id:
- 3f90abfc5a4c9e1c14f2502f88195bbd
status:
code: 200
message: OK
version: 1

215
tests/agent_tools/cassettes/test_delegate_work.yaml Normal file
View File

@@ -0,0 +1,215 @@
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\nTOOLS:\n------\n\nYou
have access to the following tools:\n\n\n\nTo use a tool, please use the 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", "max_tokens": null, "stream": false, "n": 1, "temperature": 0.7, "stop":
["\nObservation"]}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1048'
Content-Type:
- application/json
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 82328f5b5d5a013b-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 09 Nov 2023 02:17:38 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=Kok7joFOxdnT4Rx42sui.msFN7jEZTBCOWV7KIuNoRU-1699496258-0-AWKfmFHxH6JvrxGRge6CrVDGH8NMMnlPoiNxVrU67tDkND02pVJemu65mT6VtMZ2t9HbOQUO+GHsKxUfpQh3BXI=;
path=/; expires=Thu, 09-Nov-23 02:47:38 GMT; 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:
- clearbit-2
openai-processing-ms:
- '5497'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '100'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '299769'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 46ms
x-request-id:
- cb70f6cd3ef05277cf4d4b56d0bf5595
status:
code: 200
message: OK
- 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: As a technology researcher, it''s important to maintain objectivity.
AI agents have their own merits and demerits. On the positive side, they can
automate routine tasks, improve efficiency, and enable new forms of communication
and decision-making. However, there are potential downsides, like job displacement
due to automation and concerns about privacy and security. It''s not accurate
to say that I hate them, but rather, I recognize the potential implications
- both positive and negative - of their use.\n\nNew summary:"}], "model": "gpt-4",
"max_tokens": null, "stream": false, "n": 1, "temperature": 0.7}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1475'
Content-Type:
- application/json
Cookie:
- __cf_bm=Kok7joFOxdnT4Rx42sui.msFN7jEZTBCOWV7KIuNoRU-1699496258-0-AWKfmFHxH6JvrxGRge6CrVDGH8NMMnlPoiNxVrU67tDkND02pVJemu65mT6VtMZ2t9HbOQUO+GHsKxUfpQh3BXI=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 82328f7f6eae013b-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 09 Nov 2023 02:17:44 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '5386'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '100'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '299652'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 69ms
x-request-id:
- 1a9f4c2a0146fabe806e3bd5a30018d8
status:
code: 200
message: OK
version: 1

179
tests/cassettes/test_agent_execution.yaml
View File

@@ -1,121 +1,16 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are an AI assistant reading
the transcript of a conversation between an AI and a human. Extract all of the
proper nouns from the last line of conversation. As a guideline, a proper noun
is generally capitalized. You should definitely extract all names and places.\n\nThe
conversation history is provided just in case of a coreference (e.g. \"What
do you know about him\" where \"him\" is defined in a previous line) -- ignore
items mentioned there that are not in the last line.\n\nReturn the output as
a single comma-separated list, or NONE if there is nothing of note to return
(e.g. the user is just issuing a greeting or having a simple conversation).\n\nEXAMPLE\nConversation
history:\nPerson #1: how''s it going today?\nAI: \"It''s going great! How about
you?\"\nPerson #1: good! busy working on Langchain. lots to do.\nAI: \"That
sounds like a lot of work! What kind of things are you doing to make Langchain
better?\"\nLast line:\nPerson #1: i''m trying to improve Langchain''s interfaces,
the UX, its integrations with various products the user might want ... a lot
of stuff.\nOutput: Langchain\nEND OF EXAMPLE\n\nEXAMPLE\nConversation history:\nPerson
#1: how''s it going today?\nAI: \"It''s going great! How about you?\"\nPerson
#1: good! busy working on Langchain. lots to do.\nAI: \"That sounds like a lot
of work! What kind of things are you doing to make Langchain better?\"\nLast
line:\nPerson #1: i''m trying to improve Langchain''s interfaces, the UX, its
integrations with various products the user might want ... a lot of stuff. I''m
working with Person #2.\nOutput: Langchain, Person #2\nEND OF EXAMPLE\n\nConversation
history (for reference only):\n\nLast line of conversation (for extraction):\nHuman:
How much is 1 + 1?\n\nOutput:"}], "model": "gpt-4", "max_tokens": null, "stream":
false, "n": 1, "temperature": 0.7}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1879'
Content-Type:
- application/json
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQT2uDQBDF736KYc5a1ASN3lootJcU+gdCSwmbdRo36q64k9IS/O5l1cT0Mof5
vffmMScPAFWBOaAsBcumrYPVAz0Wv693t1VJz2/lJtm9yPj4Hm8Wh+8KfecwuwNJPrtupGnamlgZ
PWLZkWByqVGSZXGURmk2gMYUVDvbvuVgGYRJtJgcpVGSLObw4QEAnIbpuumCfjCH0D9vGrJW7Anz
iwgAO1O7DQprlWWhGf0ZSqOZ9FB3/bS+x4n0l8gvpZUttx0Ja7STWTbtKOs9gM+h4vHfVWw707S8
ZVORdr2XYTrm4fyNmUYTY8OivjatPHej9/4AAAD//wMAIl8yO4kBAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8217f2097fed01af-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Sun, 05 Nov 2023 20:46:20 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '847'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '100'
x-ratelimit-limit-tokens:
- '150000'
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '149557'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 177ms
x-request-id:
- c0e542a54029d73256f7615e6edc08e7
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
main goal is: test goal\nTOOLS:\n------\n\nYou have access to the following
personal goal is: test goal\nTOOLS:\n------\n\nYou have access to the following
tools:\n\n\n\nTo use a tool, please use the 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 \n\n This
is your understanding of the current situation:\n {}\nBegin!\n\nCurrent
Task: How much is 1 + 1?\n\n"}], "model": "gpt-4", "max_tokens": null, "stream":
false, "n": 1, "temperature": 0.7, "stop": ["\nObservation"]}'
[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: How
much is 1 + 1?\n\n"}], "model": "gpt-4", "max_tokens": null, "stream": false,
"n": 1, "temperature": 0.7, "stop": ["\nObservation"]}'
headers:
Accept:
- '*/*'
@@ -126,7 +21,7 @@ interactions:
Connection:
- keep-alive
Content-Length:
- '886'
- '869'
Content-Type:
- application/json
User-Agent:
@@ -141,17 +36,17 @@ interactions:
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQQU/CQBCF7/0Vk70KpFsQaC+GhKhcPBiMJmrIuh3ble1O7U6jgfS/my0IetnD
++a9ebP7CECYXGQgdKlYV7Udzm9xhY87Xj3QzqbLuNzePNH6fny5MKjFIDjo7QM1/7pGmqraIhty
B6wbVIwhVU7TNJEzOY97UFGONtiKmoeTYTyV46OjJKPRiwyeIwCAff+Gbi7Hb5FB7++VCr1XBYrs
NAQgGrJBEcp741k5FoMz1OQYXV93XVJblJzBkmAFDjEHJmg9ggImsldwRy/u2jhlYeH8FzYZSLgA
CfjZKushGYljcHdq9G6c8eWmQeXJhS2eqT6MdRHAa39h+6+0qBuqat4wbdGFs+UsPeSJ82eeaTI5
QiZW9o8ej6OwpIt+AAAA//8DAHOHxGfJAQAA
H4sIAAAAAAAAA1RQwUrDQBC95yuGvZpK0pTSBEQkpZhLFSp4UCnrZky2bnZCdkrV0n+XTdNWL3N4
b96b92YfAAhdigyEqiWrpjWjWUHTTb7KV8+P8TJfRPPiXv58d6uK5rsHEXoFvW9Q8Ul1rahpDbIm
e6RVh5LRu8bTNJ2kyThKe6KhEo2XVS2PJqNoGieDoiat0IkMXgIAgH0/fTZb4pfIIApPSIPOyQpF
dl4CEB0ZjwjpnHYsLYvwQiqyjLaP+1TTtqo5gzlBARaxBCbYOgQJTGRuYUmvdqGtNHBn3Q67DGK4
ghhuYCwGy8M5y4e22tXrDqUj6/0dU3tcOwQAb3237b+4ou2oaXnN9InWF45nQzdxeeOFHScDycTS
/MGjJPBHDsEvAAAA//8DANNUqtjDAQAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8217f210daec01af-GRU
- 8232450e7c33016c-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
@@ -161,9 +56,13 @@ interactions:
Content-Type:
- application/json
Date:
- Sun, 05 Nov 2023 20:46:21 GMT
- Thu, 09 Nov 2023 01:26:50 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=gkc3fZTvDPQQcvL6AsOb5ZabV_BJygyXmsJKgi0mtCU-1699493210-0-AWKdSYb5U/QGRawJ4wWK6DvEWiy6+l7vXFmP3RnnSvAVR+kc3AFmDrcnMowxNcJdOH8DqFD/H8jQAb6ZfMNSE3E=;
path=/; expires=Thu, 09-Nov-23 01:56:50 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
@@ -175,7 +74,7 @@ interactions:
openai-organization:
- clearbit-2
openai-processing-ms:
- '1086'
- '911'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -183,17 +82,17 @@ interactions:
x-ratelimit-limit-requests:
- '100'
x-ratelimit-limit-tokens:
- '150000'
- '300000'
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '149810'
- '299813'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 76ms
- 37ms
x-request-id:
- ebeb778dd7c0273460cdb5e24fdbfe7c
- 57fa8c5d7c0ca15499c9624bb1a13c0f
status:
code: 200
message: OK
@@ -208,7 +107,7 @@ interactions:
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: How much
is 1 + 1?\nAI: 1 + 1 equals 2.\n\nNew summary:"}], "model": "gpt-4", "max_tokens":
is 1 + 1?\nAI: 1 + 1 = 2\n\nNew summary:"}], "model": "gpt-4", "max_tokens":
null, "stream": false, "n": 1, "temperature": 0.7}'
headers:
Accept:
@@ -220,9 +119,11 @@ interactions:
Connection:
- keep-alive
Content-Length:
- '905'
- '899'
Content-Type:
- application/json
Cookie:
- __cf_bm=gkc3fZTvDPQQcvL6AsOb5ZabV_BJygyXmsJKgi0mtCU-1699493210-0-AWKdSYb5U/QGRawJ4wWK6DvEWiy6+l7vXFmP3RnnSvAVR+kc3AFmDrcnMowxNcJdOH8DqFD/H8jQAb6ZfMNSE3E=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
@@ -235,17 +136,17 @@ interactions:
response:
body:
string: !!binary |
H4sIAAAAAAAAA1RQQW7CMBC85xUrXxsQpiWF3LhUpaIHJDhVFXKdBbvEdshuVBDi75VDgPayh52Z
nZk9JQDCFiIHoY1i7aqyN37F2WaxfDlmfGz2q6NbLQ6H5m1az+v3uUijInx9o+arqq+Dq0pkG/wF
1jUqxnhVZpPJUD7LsWwBFwoso2xbce+pN8jkY6cwwWokkcNHAgBwamfM5gs8iBwG6XXjkEhtUeQ3
EoCoQxk3QhFZYuVZpHdQB8/o27hLg2Aapzwo2hGwQZjOQAHZ2ACcYgP7Bil2SYED/BirzZVXI1XB
F1GnGCQ8gATcN6okGPZFZ3i+Jd1Yb8msa1QUfHQnDtWFdk4APtvmzb8yoqqDq3jNYYc+vkOOsss9
cX/yHR2OOpADq/KPaiyTaHJOfgEAAP//AwADfIQK4QEAAA==
H4sIAAAAAAAAA1SQT08CMRDF7/spJr0KhF2QuHvzpESjHsCLMaSUkdZtO2s7CEL47qbLP73MYd77
zbyZXQYgzEJUIJSWrFxjuzdjGtX2e/u8nk7u+vP66XVjXh7K6f2jLreikwiaf6LiE9VT5BqLbMgf
ZBVQMqap+agsh+WgyPut4GiBNmHLhrvDbn+UD46EJqMwigreMgCAXVtTNr/Ajaig5duOwxjlEkV1
NgGIQDZ1hIzRRJaeReciKvKMvo070Qh65aQHGesIrBFuxyAhmnQBOMkamkBzi64DTLDWRumTTVEI
qNj+gPRxjSHxkiGHK8gBv1bSRih64rh4f078YbyJehZQRvIpRWRqDrZ9BvDefmD17yjRBHINz5hq
9Okt+fXoME9cnn1Ri5PIxNL+oW6KLC3ZZ78AAAD//wMAQUWO/+kBAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8217f219bdf601af-GRU
- 823245165c88016c-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
@@ -255,7 +156,7 @@ interactions:
Content-Type:
- application/json
Date:
- Sun, 05 Nov 2023 20:46:23 GMT
- Thu, 09 Nov 2023 01:26:52 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -269,7 +170,7 @@ interactions:
openai-organization:
- clearbit-2
openai-processing-ms:
- '1196'
- '1229'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -277,17 +178,17 @@ interactions:
x-ratelimit-limit-requests:
- '100'
x-ratelimit-limit-tokens:
- '150000'
- '300000'
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '149793'
- '299795'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 82ms
- 40ms
x-request-id:
- 088729b81730273860e6434d8eb6ed57
- 5a5b201eb4124de1372291f96d0142df
status:
code: 200
message: OK

303
tests/cassettes/test_agent_execution_with_specific_tools.yaml Normal file
View File

@@ -0,0 +1,303 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goal\nTOOLS:\n------\n\nYou have access to the following
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
to multiply two numbers together. \n\t\t\tThe input to this tool should be a
comma separated list of numbers of \n\t\t\tlength two, representing the two
numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the following
format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to
take, should be one of [multiplier]\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: What is 3 times 4\n\n"}], "model":
"gpt-4", "max_tokens": null, "stream": false, "n": 1, "temperature": 0.7, "stop":
["\nObservation"]}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1217'
Content-Type:
- application/json
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1RQy2rDMBC8+ysWnZ1SN66JfSmBQHEOSaFpIW1KUORtrFbWCmsNgZB/L3Kevexh
ZmdnZvcRgNCVKECoWrJqnBmMpq9Juix3i810+TEr1aae5W8vz+P5/H3SijgoaPODis+qO0WNM8ia
7JFWLUrGcDXJ8jxLsywZ9URDFZog2zoepIP7LBmeFDVphV4U8BkBAOz7GbLZCneigPv4jDTovdyi
KC5LAKIlExAhvdeepWURX0lFltH2cRc1dduaC5gQlGARK2CCziNIYCLzBEv0KztWoUwBTWdYO6Ox
PWNQWtdxAcM4XVlx8jhcwn1rq329blF6ssHQM7nj2iEC+OrLdv/yC9dS43jN9Is2fODhMT/eE9e/
3rDpiWRiaW7w0TAKJofoDwAA//8DAHj9RNPUAQAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8240e667dda81d40-GIG
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 10 Nov 2023 20:03:40 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=qYjHtObHmnuj7bUr95x9cwbTcVmcUYOIypCLBKdVYs4-1699646620-0-AQeu11iFH6nTGNmgj6ZfcaJImCKZh6t5u20SP71vsQESEAE6zlxJ6ZkKJQmIkv3sR37LF/PKPhzLydE3f+srokY=;
path=/; expires=Fri, 10-Nov-23 20:33:40 GMT; 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:
- clearbit-2
openai-processing-ms:
- '1274'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299729'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 54ms
x-request-id:
- dc4e4c53dc93ab456ba5f5f66282131f
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goal\nTOOLS:\n------\n\nYou have access to the following
tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
to multiply two numbers together. \n\t\t\tThe input to this tool should be a
comma separated list of numbers of \n\t\t\tlength two, representing the two
numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the following
format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to
take, should be one of [multiplier]\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: What is 3 times 4\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\n\nObservation:
multiplier is not a valid tool, try one of [].\nThought: \n"}], "model": "gpt-4",
"max_tokens": null, "stream": false, "n": 1, "temperature": 0.7, "stop": ["\nObservation"]}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1367'
Content-Type:
- application/json
Cookie:
- __cf_bm=qYjHtObHmnuj7bUr95x9cwbTcVmcUYOIypCLBKdVYs4-1699646620-0-AQeu11iFH6nTGNmgj6ZfcaJImCKZh6t5u20SP71vsQESEAE6zlxJ6ZkKJQmIkv3sR37LF/PKPhzLydE3f+srokY=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SRS2/bMBCE7/oVA15ysQ3LsoVGlyJAUMQ9pK8UPTRBQElbizEfKncVpw383wvK
TtxcCHBnvuVw9zkDlGlVBdV0WhrX2+m7j9/y8lNx+bD6emWK1bWtzffVzfbvj4vPX+ZqkohQP1Aj
L9SsCa63JCb4g9xE0kKpa16en5fLslzMR8GFlmzCNr1Ml9N5mRdHogumIVYVfmYA8DyeKZtv6UlV
GPmx4ohZb0hVryZAxWBTRWlmw6K9qMlJbIIX8mPcm44igYkcQwJqgoZLxJZmWGOnGfTUUyPGb5Jh
4OSQEGy6ucGK6e0fSEfwg6sp8gT1IDAC3fekIyct0hlDe1CMIUL7dgTGLob9mUA/amN1bWmGq7Cj
R4oTrLH1YQfptKCAGEeMJej3oC0jX8xu/WXAGp6ofZvsPa7Drf9gvLa48LyjWCFfqOP/96+D+2W8
4e4+kubg0zBYQn+w7TPgblzE8Ga2qo/B9XIvYUs+baeY54d+6rTzk1oujqIE0fY/qiyy9Mg++wcA
AP//AwAOHyo+cAIAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8240e671495c1d40-GIG
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 10 Nov 2023 20:03:44 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '3513'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299693'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 61ms
x-request-id:
- 4a2658b98a181b090c362f6ce027ab4b
status:
code: 200
message: OK
- 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: What
is 3 times 4\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "max_tokens": null,
"stream": false, "n": 1, "temperature": 0.7}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '891'
Content-Type:
- application/json
Cookie:
- __cf_bm=qYjHtObHmnuj7bUr95x9cwbTcVmcUYOIypCLBKdVYs4-1699646620-0-AQeu11iFH6nTGNmgj6ZfcaJImCKZh6t5u20SP71vsQESEAE6zlxJ6ZkKJQmIkv3sR37LF/PKPhzLydE3f+srokY=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQT0/DMAzF7/0UVs7dtG6lsN4GCI0dJiQQEkJoylKzhjZxlHgaY9p3R+n+wcWH
9/Ozn71LAISuRAlC1ZKVcW3vZvacTWY/d3PVIMm3e5y+TR/o9nXerPhJpNFByy9UfHL1FRnXImuy
B6w8SsY4NSvG4yIvimHeAUMVttG2ctzLe4MiGx0dNWmFQZTwngAA7Loas9kKv0UJg/SkGAxBrlCU
5yYA4amNipAh6MDSskgvUJFltF3clxqhXhtpQYYmANcIk0dgArNuWbt2CyNYbiFPQdrqhD0GR7YK
sNFcd6Ii71ExSBs26FPIhn1x3Lc/B/3UVod64VEGsnF5YHKHtn0C8NEdvv53i3CejOMFU4M2fiPL
x4d54vLjCx1eHSETy/aP6zpP4pJ98gsAAP//AwA0pTz34AEAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8240e688ca6e1d40-GIG
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 10 Nov 2023 20:03:45 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '1515'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299797'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 40ms
x-request-id:
- 76574b94ab5a1c54d1ac4d372a830eb9
status:
code: 200
message: OK
version: 1

207
tests/cassettes/test_agent_execution_with_tools.yaml
View File

@@ -1,113 +1,4 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are an AI assistant reading
the transcript of a conversation between an AI and a human. Extract all of the
proper nouns from the last line of conversation. As a guideline, a proper noun
is generally capitalized. You should definitely extract all names and places.\n\nThe
conversation history is provided just in case of a coreference (e.g. \"What
do you know about him\" where \"him\" is defined in a previous line) -- ignore
items mentioned there that are not in the last line.\n\nReturn the output as
a single comma-separated list, or NONE if there is nothing of note to return
(e.g. the user is just issuing a greeting or having a simple conversation).\n\nEXAMPLE\nConversation
history:\nPerson #1: how''s it going today?\nAI: \"It''s going great! How about
you?\"\nPerson #1: good! busy working on Langchain. lots to do.\nAI: \"That
sounds like a lot of work! What kind of things are you doing to make Langchain
better?\"\nLast line:\nPerson #1: i''m trying to improve Langchain''s interfaces,
the UX, its integrations with various products the user might want ... a lot
of stuff.\nOutput: Langchain\nEND OF EXAMPLE\n\nEXAMPLE\nConversation history:\nPerson
#1: how''s it going today?\nAI: \"It''s going great! How about you?\"\nPerson
#1: good! busy working on Langchain. lots to do.\nAI: \"That sounds like a lot
of work! What kind of things are you doing to make Langchain better?\"\nLast
line:\nPerson #1: i''m trying to improve Langchain''s interfaces, the UX, its
integrations with various products the user might want ... a lot of stuff. I''m
working with Person #2.\nOutput: Langchain, Person #2\nEND OF EXAMPLE\n\nConversation
history (for reference only):\n\nLast line of conversation (for extraction):\nHuman:
What is 3 times 4\n\nOutput:"}], "model": "gpt-4", "max_tokens": null, "stream":
false, "n": 1, "temperature": 0.7}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1878'
Content-Type:
- application/json
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQMW+DMBCFd37F6WaoIKEksLVShi5k6VZVkWuc4NT4LHxJq0b898qQhHa54b73
3j3dJQJA3WAFKFvBsnMmWb9Yf8rq8379s3pyZ7Mpno3Q29e6Lb5SjIODPo5K8s31IKlzRrEmO2HZ
K8EqpGZFWeblYvm4GEFHjTLBdnCc5ElaZMuroyUtlccK3iIAgMs4QzfbqG+sII1vm055Lw4Kq7sI
AHsyYYPCe+1ZWMZ4hpIsKzvWrbf1Bq9kuEfutdW+3fVKeLJB5pncJBsigPex4unfVXQ9dY53TJ/K
ht55Wkx5OH9jptmVMbEwf02rKNwYol8AAAD//wMAtfp4RYkBAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 82323023acba0182-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Thu, 09 Nov 2023 01:12:33 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=pggttVzpKyQR4nT.B1yq6_bhIXPGndjWgQ1FDQWrqmI-1699492353-0-AdtCtI4A9MJL7HNTV51tlyV/nXd/jR6ewJjLEbxTXtzvv5pNZJ/AcBybsdljMBmcKJ+MAD1bX9NwEjuW0k7E6F8=;
path=/; expires=Thu, 09-Nov-23 01:42:33 GMT; 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:
- clearbit-2
openai-processing-ms:
- '433'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '100'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '299557'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 88ms
x-request-id:
- 222744a81f853802353e390dd40173ea
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
personal goal is: test goal\nTOOLS:\n------\n\nYou have access to the following
@@ -121,9 +12,8 @@ interactions:
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 \n\n This is your understanding
of the current situation:\n {}\nBegin! This is VERY important to you,
your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model":
is the summary of your work so far:\n \nBegin! This is VERY important
to you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model":
"gpt-4", "max_tokens": null, "stream": false, "n": 1, "temperature": 0.7, "stop":
["\nObservation"]}'
headers:
@@ -136,11 +26,11 @@ interactions:
Connection:
- keep-alive
Content-Length:
- '1293'
- '1217'
Content-Type:
- application/json
Cookie:
- __cf_bm=pggttVzpKyQR4nT.B1yq6_bhIXPGndjWgQ1FDQWrqmI-1699492353-0-AdtCtI4A9MJL7HNTV51tlyV/nXd/jR6ewJjLEbxTXtzvv5pNZJ/AcBybsdljMBmcKJ+MAD1bX9NwEjuW0k7E6F8=
- __cf_bm=gkc3fZTvDPQQcvL6AsOb5ZabV_BJygyXmsJKgi0mtCU-1699493210-0-AWKdSYb5U/QGRawJ4wWK6DvEWiy6+l7vXFmP3RnnSvAVR+kc3AFmDrcnMowxNcJdOH8DqFD/H8jQAb6ZfMNSE3E=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
@@ -153,17 +43,17 @@ interactions:
response:
body:
string: !!binary |
H4sIAAAAAAAAA1RQy2rDMBC8+ysWnZ1ix3ZS61IKbSFQeuoltCWo8jZWK2uFtQ6BkH8vct6XPczs
7MzsLgEQphEShG4V687byf3ChY3bvGX1tsr0srLP8xdVZZxXr5yLNCro+xc1n1R3mjpvkQ25A617
VIzxaj6r67KeFlUxEh01aKNs7XlSTrJZXhwVLRmNQUj4SAAAduOM2VyDWyEhS09IhyGoNQp5XgIQ
PdmICBWCCawci/RCanKMboz73tKwblnCE8ECHGIDTDAEBAVMZB9gieHTPepYRkI3WDbeGuxPGCyc
H1hCkZbi6LA/R/sxzoR21aMK5KJdYPKHtX0C8DVWHW7SC99T53nF9Icu9p/O88M9cfnqFVscSSZW
9gqvyySa7JN/AAAA//8DAGryDPHSAQAA
H4sIAAAAAAAAA1RQTUvDQBC951cMe06lTWJo9iKlglQEL2IRLWW7GZvVzc6SnYBS+t9l008vc3hv
3rz3ZpcACFMLCUI3inXr7Wi6oLJ9yuduWWavv3OznD0/Fo3ql25TP4g0KmjzhZpPqhtNrbfIhtyB
1h0qxnh1UlZVUeXZJBuIlmq0Ubb1PCpG43KSHxUNGY1BSHhPAAB2w4zZXI0/QsI4PSEthqC2KOR5
CUB0ZCMiVAgmsHIs0gupyTG6Ie5LQ/22YQn3BAtwiDUwQR8QFDCRvYM3DB9upmMZCW1v2XhrsDth
sHC+Zwl5Woijw/4c7dM4E5p1hyqQi3aByR/W9gnAaqja/0svfEet5zXTN7rYP7utDvfE5atXbH4k
mVjZK3yaJdFkn/wBAAD//wMAU+pOotIBAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 823230284a450182-GRU
- 823245216f2f520b-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
@@ -173,7 +63,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 09 Nov 2023 01:12:34 GMT
- Thu, 09 Nov 2023 01:26:53 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -187,7 +77,7 @@ interactions:
openai-organization:
- clearbit-2
openai-processing-ms:
- '1120'
- '1105'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -199,13 +89,13 @@ interactions:
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '299710'
- '299729'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 57ms
- 54ms
x-request-id:
- 00d0dced84c81ed56d116437daa60a72
- 951ac7b6b78d0178415f15e6576c49e6
status:
code: 200
message: OK
@@ -222,12 +112,11 @@ interactions:
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 \n\n This is your understanding
of the current situation:\n {}\nBegin! This is VERY important to you,
your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do I need
to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\nObservation: 12\nThought:
\n"}], "model": "gpt-4", "max_tokens": null, "stream": false, "n": 1, "temperature":
0.7, "stop": ["\nObservation"]}'
is the summary of your work so far:\n \nBegin! This is VERY important
to you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought:
Do I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\nObservation:
12\nThought: \n"}], "model": "gpt-4", "max_tokens": null, "stream": false, "n":
1, "temperature": 0.7, "stop": ["\nObservation"]}'
headers:
Accept:
- '*/*'
@@ -238,11 +127,11 @@ interactions:
Connection:
- keep-alive
Content-Length:
- '1397'
- '1321'
Content-Type:
- application/json
Cookie:
- __cf_bm=pggttVzpKyQR4nT.B1yq6_bhIXPGndjWgQ1FDQWrqmI-1699492353-0-AdtCtI4A9MJL7HNTV51tlyV/nXd/jR6ewJjLEbxTXtzvv5pNZJ/AcBybsdljMBmcKJ+MAD1bX9NwEjuW0k7E6F8=
- __cf_bm=gkc3fZTvDPQQcvL6AsOb5ZabV_BJygyXmsJKgi0mtCU-1699493210-0-AWKdSYb5U/QGRawJ4wWK6DvEWiy6+l7vXFmP3RnnSvAVR+kc3AFmDrcnMowxNcJdOH8DqFD/H8jQAb6ZfMNSE3E=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
@@ -255,17 +144,17 @@ interactions:
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQW08CQQyF3/dXNPMMBHZXhH0x3ghoNCSoMVFDxtkKg7PTzbYEE7L/3cxy05c+
9Os5Pe02AlA2Vxkos9RiitK1BxPPm5fRbDy4Wr0OzqfT2/vn8dPD7Hoc31nVCgr6XKGRg6pjqCgd
iiW/w6ZCLRhce/3hMB3GyVnagIJydEG2KKWdtrv9XrJXLMkaZJXBWwQAsG1qyOZz/FEZdFuHToHM
eoEqOw4BqIpc6CjNbFm0F9U6QUNe0Ddxbwgm4BFzEII1I2gQIncBj/TuR9ZrB5eeN1hlkIDYAhlS
sAy9uKP2hvUxyZf1lpfzCjWTD+4sVO7G6gjgo7ls/S+sKisqSpkLfaMP5ybddOenTk880TjeQyHR
7o8q7kdhSR39AgAA//8DAGQ+69zBAQAA
H4sIAAAAAAAAA1SQS0/DQAyE7/kV1p5b1DwUSC6oqKpUIXHgCqhaNibdNrFD7NJKVf872vQFlz3M
55kd+xABGF+ZEoxbWXVt14wfFpyT/DzNdt9I06zevM6f11b32/t57c0oOPhzjU4vrjvHbdegeqYT
dj1axZAa50WRFWkSpwNoucIm2OpOx9l4ksfp2bFi71BMCW8RAMBheEM3qnBvSpiMLkqLIrZGU16H
AEzPTVCMFfGiltSMbtAxKdJQd8awAEKsQBm2gmBBmZtHeOF3mnuyDUxJdtiXkIL6FgUy8AJxYs55
x2uRL09eVsserTCFcFHuTmPHCOBjWGz7r6vpem47XSpvkMK2SZGc8szthn9ofIbKapubnsZpFD45
Rr8AAAD//wMAIwC1ssABAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 82323030ddb90182-GRU
- 8232452a2e6e520b-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
@@ -275,7 +164,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 09 Nov 2023 01:12:36 GMT
- Thu, 09 Nov 2023 01:26:55 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -289,7 +178,7 @@ interactions:
openai-organization:
- clearbit-2
openai-processing-ms:
- '1128'
- '1095'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -301,13 +190,13 @@ interactions:
x-ratelimit-remaining-requests:
- '99'
x-ratelimit-remaining-tokens:
- '299685'
- '299704'
x-ratelimit-reset-requests:
- 600ms
x-ratelimit-reset-tokens:
- 62ms
- 59ms
x-request-id:
- 2edfda088d7c07b018426c91a4506903
- aa5df5b29842f6d68339b5c4887eeecc
status:
code: 200
message: OK
@@ -322,7 +211,7 @@ interactions:
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: What
is 3 times 4\nAI: 3 times 4 is 12.\n\nNew summary:"}], "model": "gpt-4", "max_tokens":
is 3 times 4\nAI: 3 times 4 is 12\n\nNew summary:"}], "model": "gpt-4", "max_tokens":
null, "stream": false, "n": 1, "temperature": 0.7}'
headers:
Accept:
@@ -334,11 +223,11 @@ interactions:
Connection:
- keep-alive
Content-Length:
- '905'
- '904'
Content-Type:
- application/json
Cookie:
- __cf_bm=pggttVzpKyQR4nT.B1yq6_bhIXPGndjWgQ1FDQWrqmI-1699492353-0-AdtCtI4A9MJL7HNTV51tlyV/nXd/jR6ewJjLEbxTXtzvv5pNZJ/AcBybsdljMBmcKJ+MAD1bX9NwEjuW0k7E6F8=
- __cf_bm=gkc3fZTvDPQQcvL6AsOb5ZabV_BJygyXmsJKgi0mtCU-1699493210-0-AWKdSYb5U/QGRawJ4wWK6DvEWiy6+l7vXFmP3RnnSvAVR+kc3AFmDrcnMowxNcJdOH8DqFD/H8jQAb6ZfMNSE3E=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
@@ -351,17 +240,17 @@ interactions:
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SQMW/CQAyF9/wK62ZAJEAE2TpUAqlSFzrQqkLXi0sO7s5R7EhFiP9eXQKkXTz4
e89+9iUBULZUBShTaTG+duPlJvDZro+Hrffr12x3fntpps/y3hrOd2oUHfR1RCN318SQrx2KpdBj
06AWjFPTfLWar7LZIu+ApxJdtB1qGc/H0zyd3RwVWYOsCvhIAAAuXY3ZQok/qoDp6N7xyKwPqIqH
CEA15GJHaWbLooOo0QANBcHQxd1WCFXrdQDNJwapEJ42IARGO9M6LQgzEOuRYT6BbY8b5JpCGeVa
Bg6WIc0m6rbo+kj4bYPlat+gZgpxKwvVveyaAHx2F7f/jlB1Q76WvdAJQ3xDulj089Tw3IFm+Q0K
iXZ/XMs0iUuuyS8AAAD//wMAmwGlztkBAAA=
H4sIAAAAAAAAA1SQu27DMAxFd38FodkJYuftrR1aZAzarSgCRWZsNbIomHQfCPLvhZyH24UD7z3k
JU8JgLKlKkCZWotpghutNrQIj9q9PG+PT9uKpeoO9udrv/zMNlalkaD9Bxq5UWNDTXAolvxFNi1q
wTg1W6zXs/U0z+a90FCJLmJVkNFsNFlk0ytRkzXIqoC3BADg1NeYzZf4rQqYpLdOg8y6QlXcTQCq
JRc7SjNbFu1FpYNoyAv6Pu5rjVB3jfag+cggNcLDBoTAaGc6pwVhCmIbZJiloH15s7TIgXwZES2D
ByxDlo/Vddn5nvJgveV616Jm8nEzC4WL7ZwAvPdXd/8OUaGlJshO6Ig+viKbzy/z1PDgQc2XV1FI
tPtDrfIkLjknvwAAAP//AwC2/4B/3QEAAA==
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8232303a294a0182-GRU
- 823245332d7b520b-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
@@ -371,7 +260,7 @@ interactions:
Content-Type:
- application/json
Date:
- Thu, 09 Nov 2023 01:12:37 GMT
- Thu, 09 Nov 2023 01:26:56 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -385,7 +274,7 @@ interactions:
openai-organization:
- clearbit-2
openai-processing-ms:
- '1025'
- '1275'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -403,7 +292,7 @@ interactions:
x-ratelimit-reset-tokens:
- 41ms
x-request-id:
- 8f752eda873d901ecec28888cdeb318d
- ac804646da74e95835f869ebd5313225
status:
code: 200
message: OK

1467
tests/cassettes/test_crew_creation.yaml
View File

File diff suppressed because it is too large Load Diff

579
tests/cassettes/test_crew_with_delegating_agents.yaml Normal file
View File

@@ -0,0 +1,579 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\n\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nTOOLS:\n------\n\nYou
have access to the following tools:\n\nDelegate Work to Co-Worker: Useful to
delegate a specific task to one of the \n\t\t\t\tfollowing co-workers: [CEO,
Senior Writer].\n\t\t\t\tThe input to this tool should be a pipe (|) separated
text of length\n\t\t\t\tthree, representing the role you want to delegate it
to, the task and \n\t\t\t\tinformation necessary. For example, `coworker|task|information`.\n\nAsk
Question to Co-Worker: Useful to ask a question, opinion or take from on\n\t\t\t\tof
the following co-workers: [CEO, Senior Writer]. \n\t\t\t\tThe input to this
tool should be a pipe (|) separated text of length \n\t\t\t\tthree, representing
the role you want to ask it to, the question and \n\t\t\t\tinformation necessary.
For example, `coworker|question|information`.\n\n\nTo use a tool, please use
the following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
the action to take, should be one of [Delegate Work to Co-Worker, Ask Question
to Co-Worker]\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: Produce and amazing 1 paragraph draft of an
article about AI Agents.\n\n"}], "model": "gpt-4", "max_tokens": null, "stream":
false, "n": 1, "temperature": 0.7, "stop": ["\nObservation"]}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1925'
Content-Type:
- application/json
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 824143ad1aac0108-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 10 Nov 2023 21:07:23 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=BJCIwITJ38jRui6K.7wMbft5s6X08Igv1apUn36eQig-1699650443-0-AedvzmUPJryFUloxAEAX1O07DWDpjuQCqrS9A+Do71R+4EmtK2da6BZ9gQ+2H2Ktiu+zu4K9Svwd0VLOLW+vUCk=;
path=/; expires=Fri, 10-Nov-23 21:37:23 GMT; 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:
- clearbit-2
openai-processing-ms:
- '3672'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299560'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 88ms
x-request-id:
- baabf544ff76af09054a90d10db8b702
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are Senior Writer.\nYou''re
a senior writr, specialized in technology, software engineering, AI and startups.
You work as a freelancer and are now working on writing content for a new customer.\n\nYour
personal goal is: Write the best content about AI and AI agents.\nTOOLS:\n------\n\nYou
have access to the following tools:\n\n\n\nTo use a tool, please use the 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: Produce a 1 paragraph draft
of an article about AI Agents\n\nThis is the context you are working with:\nThis
paragraph should be engaging, informative and provide the reader with a brief
overview of what AI Agents are and why they are important. \n\n\n"}], "model":
"gpt-4", "max_tokens": null, "stream": false, "n": 1, "temperature": 0.7, "stop":
["\nObservation"]}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1298'
Content-Type:
- application/json
Cookie:
- __cf_bm=BJCIwITJ38jRui6K.7wMbft5s6X08Igv1apUn36eQig-1699650443-0-AedvzmUPJryFUloxAEAX1O07DWDpjuQCqrS9A+Do71R+4EmtK2da6BZ9gQ+2H2Ktiu+zu4K9Svwd0VLOLW+vUCk=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 824143c72aed0108-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 10 Nov 2023 21:07:33 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '9641'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299706'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 58ms
x-request-id:
- 442f5966ae613d11ca8f84b7bc0515fb
status:
code: 200
message: OK
- 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: Produce
a 1 paragraph draft of an article about AI Agents\n\nThis is the context you
are working with:\nThis paragraph should be engaging, informative and provide
the reader with a brief overview of what AI Agents are and why they are important.
\n\nAI: Artificial Intelligence (AI) agents, the cutting-edge technology that
is reshaping the digital landscape, are software entities that autonomously
perform tasks to achieve specific goals. These agents, programmed to make decisions
based on their environment, are the driving force behind a multitude of innovations,
from self-driving cars to personalized recommendations in e-commerce. They are
pushing boundaries in various sectors, mitigating human error, increasing efficiency,
and revolutionizing customer experience. The importance of AI agents is underscored
by their ability to adapt and learn, ushering in a new era of technology where
machines can mimic, and often surpass, human intelligence. Understanding AI
agents is akin to peering into the future, a future where technology is seamless,
intuitive, and astoundingly smart.\n\nNew summary:"}], "model": "gpt-4", "max_tokens":
null, "stream": false, "n": 1, "temperature": 0.7}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1955'
Content-Type:
- application/json
Cookie:
- __cf_bm=BJCIwITJ38jRui6K.7wMbft5s6X08Igv1apUn36eQig-1699650443-0-AedvzmUPJryFUloxAEAX1O07DWDpjuQCqrS9A+Do71R+4EmtK2da6BZ9gQ+2H2Ktiu+zu4K9Svwd0VLOLW+vUCk=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 824144053bcd0108-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 10 Nov 2023 21:07:39 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '5612'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299533'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 93ms
x-request-id:
- 07db6976c904d2b23e9d0702ba3bb933
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long
time CEO of a content creation agency with a Senior Writer on the team. You''re
now working on a new project and want to make sure the content produced is amazing.\n\nYour
personal goal is: Make sure the writers in your company produce amazing content.\nTOOLS:\n------\n\nYou
have access to the following tools:\n\nDelegate Work to Co-Worker: Useful to
delegate a specific task to one of the \n\t\t\t\tfollowing co-workers: [CEO,
Senior Writer].\n\t\t\t\tThe input to this tool should be a pipe (|) separated
text of length\n\t\t\t\tthree, representing the role you want to delegate it
to, the task and \n\t\t\t\tinformation necessary. For example, `coworker|task|information`.\n\nAsk
Question to Co-Worker: Useful to ask a question, opinion or take from on\n\t\t\t\tof
the following co-workers: [CEO, Senior Writer]. \n\t\t\t\tThe input to this
tool should be a pipe (|) separated text of length \n\t\t\t\tthree, representing
the role you want to ask it to, the question and \n\t\t\t\tinformation necessary.
For example, `coworker|question|information`.\n\n\nTo use a tool, please use
the following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
the action to take, should be one of [Delegate Work to Co-Worker, Ask Question
to Co-Worker]\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: Produce and amazing 1 paragraph draft of an
article about AI Agents.\nThought: Do I need to use a tool? Yes\nAction: Delegate
Work to Co-Worker\nAction Input: Senior Writer|Produce a 1 paragraph draft of
an article about AI Agents|This paragraph should be engaging, informative and
provide the reader with a brief overview of what AI Agents are and why they
are important. \n\nObservation: Artificial Intelligence (AI) agents, the cutting-edge
technology that is reshaping the digital landscape, are software entities that
autonomously perform tasks to achieve specific goals. These agents, programmed
to make decisions based on their environment, are the driving force behind a
multitude of innovations, from self-driving cars to personalized recommendations
in e-commerce. They are pushing boundaries in various sectors, mitigating human
error, increasing efficiency, and revolutionizing customer experience. The importance
of AI agents is underscored by their ability to adapt and learn, ushering in
a new era of technology where machines can mimic, and often surpass, human intelligence.
Understanding AI agents is akin to peering into the future, a future where technology
is seamless, intuitive, and astoundingly smart.\nThought: \n"}], "model": "gpt-4",
"max_tokens": null, "stream": false, "n": 1, "temperature": 0.7, "stop": ["\nObservation"]}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '3091'
Content-Type:
- application/json
Cookie:
- __cf_bm=BJCIwITJ38jRui6K.7wMbft5s6X08Igv1apUn36eQig-1699650443-0-AedvzmUPJryFUloxAEAX1O07DWDpjuQCqrS9A+Do71R+4EmtK2da6BZ9gQ+2H2Ktiu+zu4K9Svwd0VLOLW+vUCk=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA1SUTW/cRgyG7/4VhE4poDW8iL1Z76VwUBTYHlIUSdtDXQTcESWxniEFDmedTeD/
Xoy0jp2LMBh+PcOX4rcLgIa7ZgdNGNFDmuJq+9un9Xq/vQ3H8D4N7z5s9x83f9xc/371F+N109YI
PfxHwZ+jLoOmKZKzymIORuhUs643t7ebm6vrm9vZkLSjWMOGyVfXq6vN+u05YlQOlJsd/HMBAPBt
/lY26ehLs4Or9vkmUc44ULP77gTQmMZ602DOnB3Fm/bFGFScZMb9RWEPQtSBK5RMgOCq8Wf4oPfy
KwtGuJP8SLaDTyPBRxJWg7+NnQwm064E6gAFMOFXlgEmNBwMpxHwoMXhbg93A4nnHdw3d+bcc2CM
sBenGHkgCQRv7vY/Ac5uLfhIEIo7y7CibiBwCqNo1OEEPqIDZzDKI061XvXueGDHCBGlywEnagGN
IGvvj/VA4uxMeQnH4iqatOR4gomsV0vgmB9y7QGGkelIkCcKlRUGxZgv6+trd86Mk+lgmNLSt4QP
BB0FzqyS4YCZOlCpbGxAcmRTSSS+cM3IxseK36sFggONLB0gpBKdvXQE2gOL6BHrFOUWetMEmWK/
eg4NaDPxRJZVMPJX6sAoaEok3RIHLECr+coCza84zQxTyWNNctAiHVptDgsc0VhLhkzB1XILiZ0H
rFLAWBIKkJlaCyx1pHO9p74qShJOLaBUgqPGUqvzPBChZNdEBvRlIquOCwdwmtQcq/7a1zlZmlvl
LdKR5aBGHRxO5z7igSP7aRapw8nnapHQpIWSR7JajQUQhB6BDGvaV7PzOJIRpCqwUIaAAokThwVb
eyeBXGzCnNvza/nVkF7CnzOVo3S10g/A+MCyaPGM4Trr3BcvVufxfDpTvMLi2m5MkWpZFi/sfKQF
CrNXfViGeIKc0PzyvmnOP/LT9w3Qs3AeP1dFVOpfnV2nxe3pAuDfeaOUH5ZEM5mmyT+7PpDUNbN5
u13yNS/L68W6frc5W10d44thu76+qFWeLv4HAAD//wMA4FF0ljoFAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 82414429ed5c0108-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 10 Nov 2023 21:07:47 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '7913'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299270'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 146ms
x-request-id:
- 7f268488395030d8e4ecac89842bb40b
status:
code: 200
message: OK
- 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: Produce
and amazing 1 paragraph draft of an article about AI Agents.\nAI: The Senior
Writer produced an amazing paragraph about AI Agents: \"Artificial Intelligence
(AI) agents, the cutting-edge technology that is reshaping the digital landscape,
are software entities that autonomously perform tasks to achieve specific goals.
These agents, programmed to make decisions based on their environment, are the
driving force behind a multitude of innovations, from self-driving cars to personalized
recommendations in e-commerce. They are pushing boundaries in various sectors,
mitigating human error, increasing efficiency, and revolutionizing customer
experience. The importance of AI agents is underscored by their ability to adapt
and learn, ushering in a new era of technology where machines can mimic, and
often surpass, human intelligence. Understanding AI agents is akin to peering
into the future, a future where technology is seamless, intuitive, and astoundingly
smart.\"\n\nNew summary:"}], "model": "gpt-4", "max_tokens": null, "stream":
false, "n": 1, "temperature": 0.7}'
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Authorization:
- Bearer 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
Connection:
- keep-alive
Content-Length:
- '1844'
Content-Type:
- application/json
Cookie:
- __cf_bm=BJCIwITJ38jRui6K.7wMbft5s6X08Igv1apUn36eQig-1699650443-0-AedvzmUPJryFUloxAEAX1O07DWDpjuQCqrS9A+Do71R+4EmtK2da6BZ9gQ+2H2Ktiu+zu4K9Svwd0VLOLW+vUCk=
User-Agent:
- OpenAI/v1 PythonBindings/0.28.1
X-OpenAI-Client-User-Agent:
- '{"bindings_version": "0.28.1", "httplib": "requests", "lang": "python", "lang_version":
"3.9.7", "platform": "macOS-10.16-x86_64-i386-64bit", "publisher": "openai",
"uname": "Darwin 22.4.0 Darwin Kernel Version 22.4.0: Mon Mar 6 21:00:17
PST 2023; root:xnu-8796.101.5~3/RELEASE_X86_64 x86_64"}'
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8241445d6f060108-GRU
Cache-Control:
- no-cache, must-revalidate
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Fri, 10 Nov 2023 21:07:52 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- gpt-4-0613
openai-organization:
- clearbit-2
openai-processing-ms:
- '4637'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=15724800; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '300000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '299560'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 88ms
x-request-id:
- 4e3e1ec5267366325f3110cbeff4febc
status:
code: 200
message: OK
version: 1

49
tests/crew_test.py
View File

@@ -8,13 +8,15 @@ def test_crew_creation():
researcher = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer."
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
allow_delegation=False
)
writer = Agent(
role="Senior Content Officer",
role="Senior Writer",
goal="Write the best content about AI and AI agents.",
backstory="You're a senior content officer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer."
backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
allow_delegation=False
)
tasks = [
@@ -34,12 +36,43 @@ def test_crew_creation():
tasks=tasks,
)
assert crew.kickoff() == """1. AI in Healthcare: Dive into an exploratory journey where silicon meets stethoscope, unraveling how Artificial Intelligence is revolutionizing the healthcare industry. From early diagnosis of life-threatening diseases to personalized treatment plans, AI is not just an assistant; it's becoming a lifesaver. Imagine a world where technology doesn't just assist doctors but empowers patients, offering them more control over their health and well-being.
assert crew.kickoff() == """1. AI and Ethics: In a world that is increasingly being dominated by Artificial Intelligence, the question of ethics is ever more important. This article will delve into the complex intersection of AI and ethics, exploring how the decisions made by AI can impact society. From privacy concerns to the accountability of AI decisions, this piece will provide readers with a comprehensive understanding of the ethical dilemmas posed by AI.
2. Ethical Implications of AI: Unearth the moral minefield that AI has become in this thought-provoking piece. As AI's capabilities grow, so do the ethical dilemmas. Should machines make life or death decisions? Can an algorithm be biased? Who bears responsibility for AI-induced outcomes? Join us as we navigate these murky waters, balancing the scales of technological advancement and ethical responsibility.
2. The Role of AI in Climate Change: Climate change is the defining issue of our time. This article will examine how AI is playing a pivotal role in combating this global challenge. From predicting climate patterns to optimizing renewable energy use, the piece will highlight how AI is not just a part of the problem, but also a crucial part of the solution.
3. AI in Climate Change: Witness how AI is becoming an indispensable ally in the fight against climate change. From forecasting weather patterns and predicting natural disasters to optimizing energy use and promoting sustainable practices, AI is proving to be a game-changer. Explore how this nascent technology can help us steer towards a more sustainable future.
3. AI in Healthcare: The fusion of AI and healthcare holds a transformative potential. This article will explore how AI is revolutionizing healthcare, from improving diagnosis and treatment to enhancing patient care and hospital management. It will show how AI is not just improving healthcare outcomes but also driving a more efficient and patient-centered healthcare system.
4. AI and Art: Embark on a fascinating exploration of where creativity meets code. Can a machine create a masterpiece? How does AI challenge our traditional notions of art? Delve into the world of AI-generated art, where algorithms are the artists and pixels are the palette, pushing the boundaries of what we consider "art".
4. The Future of AI and Work: The rise of AI has sparked a lively debate on its impact on jobs and the future of work. This article will explore this topic in-depth, examining both the potential job losses and the new opportunities created by AI. It will provide a balanced and insightful analysis of how AI is reshaping the world of work.
5. The Future of AI Agents: Step into the realm of speculation and prediction, where we explore the potential future of AI agents. How will they shape industries, influence our daily lives, and even redefine our understanding of "intelligence"? Engage in a lively discourse around the possibilities and perils that the future of AI agents might hold."""
5. AI in Space Exploration: The final frontier is not beyond the reach of AI. This article will spotlight the role of AI in space exploration, from analyzing vast amounts of astronomical data to autonomous spacecraft navigating the vast expanse of space. The piece will highlight how AI is not just aiding but also accelerating our quest to explore the universe."""
@pytest.mark.vcr()
def test_crew_with_delegating_agents():
ceo = Agent(
role="CEO",
goal="Make sure the writers in your company produce amazing content.",
backstory="You're an long time CEO of a content creation agency with a Senior Writer on the team. You're now working on a new project and want to make sure the content produced is amazing.",
allow_delegation=True
)
writer = Agent(
role="Senior Writer",
goal="Write the best content about AI and AI agents.",
backstory="You're a senior writr, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
allow_delegation=False
)
tasks = [
Task(
description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
agent=ceo
)
]
crew = Crew(
agents=[ceo, writer],
process=Process.sequential,
tasks=tasks,
)
assert crew.kickoff() == 'The Senior Writer produced an amazing paragraph about AI Agents: "Artificial Intelligence (AI) agents, the cutting-edge technology that is reshaping the digital landscape, are software entities that autonomously perform tasks to achieve specific goals. These agents, programmed to make decisions based on their environment, are the driving force behind a multitude of innovations, from self-driving cars to personalized recommendations in e-commerce. They are pushing boundaries in various sectors, mitigating human error, increasing efficiency, and revolutionizing customer experience. The importance of AI agents is underscored by their ability to adapt and learn, ushering in a new era of technology where machines can mimic, and often surpass, human intelligence. Understanding AI agents is akin to peering into the future, a future where technology is seamless, intuitive, and astoundingly smart."'

57
tests/task_test.py Normal file
View File

@@ -0,0 +1,57 @@
"""Test Agent creation and execution basic functionality."""
import pytest
from ..crewai import Agent, Task
def test_task_tool_reflect_agent_tools():
from langchain.tools import tool
@tool
def fake_tool() -> None:
"Fake tool"
pass
researcher = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
tools=[fake_tool],
allow_delegation=False
)
task = Task(
description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
agent=researcher
)
assert task.tools == [fake_tool]
def test_task_tool_takes_precedence_ove_agent_tools():
from langchain.tools import tool
@tool
def fake_tool() -> None:
"Fake tool"
pass
@tool
def fake_task_tool() -> None:
"Fake tool"
pass
researcher = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
tools=[fake_tool],
allow_delegation=False
)
task = Task(
description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
agent=researcher,
tools=[fake_task_tool],
allow_delegation=False
)
assert task.tools == [fake_task_tool]