andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-22 22:58:13 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Merge branch 'feature/kickoff-consistent-output' of https://github.com/bhancockio/crewAI into temp-feature/replay_from_task

Browse Source
This commit is contained in:
Lorenze Jay
2024-07-10 12:33:32 -07:00
parent 3613bd469a 39d6a9a643
commit d7b765ab32
19 changed files with 9051 additions and 281 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
tests/agent_test.py
View File

@@ -4,6 +4,10 @@ from unittest import mock
from unittest.mock import patch
import pytest
from langchain.tools import tool
from langchain_core.exceptions import OutputParserException
from langchain_openai import ChatOpenAI
from crewai import Agent, Crew, Task
from crewai.agents.cache import CacheHandler
from crewai.agents.executor import CrewAgentExecutor
@@ -11,9 +15,6 @@ from crewai.agents.parser import CrewAgentParser
from crewai.tools.tool_calling import InstructorToolCalling
from crewai.tools.tool_usage import ToolUsage
from crewai.utilities import RPMController
from langchain.tools import tool
from langchain_core.exceptions import OutputParserException
from langchain_openai import ChatOpenAI
def test_agent_creation():
@@ -630,8 +631,9 @@ def test_agent_use_specific_tasks_output_as_context(capsys):
crew = Crew(agents=[agent1, agent2], tasks=tasks)
result = crew.kickoff()
assert "bye" not in result.raw_output().lower()
assert "hi" in result.raw_output().lower() or "hello" in result.raw_output().lower()
print("LOWER RESULT", result.raw)
assert "bye" not in result.raw.lower()
assert "hi" in result.raw.lower() or "hello" in result.raw.lower()
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -643,7 +645,7 @@ def test_agent_step_callback():
with patch.object(StepCallback, "callback") as callback:
@tool
def learn_about_AI(topic) -> float:
def learn_about_AI(topic) -> str:
"""Useful for when you need to learn about AI to write an paragraph about it."""
return "AI is a very broad field."
@@ -677,7 +679,7 @@ def test_agent_function_calling_llm():
with patch.object(llm.client, "create", wraps=llm.client.create) as private_mock:
@tool
def learn_about_AI(topic) -> float:
def learn_about_AI(topic) -> str:
"""Useful for when you need to learn about AI to write an paragraph about it."""
return "AI is a very broad field."
@@ -749,8 +751,8 @@ def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
crew = Crew(agents=[agent1], tasks=tasks)
result = crew.kickoff()
print("RESULT: ", result.raw_output())
assert result.raw_output() == "Howdy!"
print("RESULT: ", result.raw)
assert result.raw == "Howdy!"
@pytest.mark.vcr(filter_headers=["authorization"])

1431
tests/cassettes/test_crew_kickoff_usage_metrics.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

1464
tests/cassettes/test_kickoff_for_each_multiple_inputs.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

192
tests/cassettes/test_kickoff_for_each_single_input.yaml Normal file
View File

@@ -0,0 +1,192 @@
interactions:
- request:
body: '{"messages": [{"content": "You are dog Researcher. You have a lot of experience
with dog.\nYour personal goal is: Express hot takes on dog.To give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an analysis around dog.\n\nThis is the expect criteria for your
final answer: 1 bullet point about dog that''s under 15 words. \n you MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o",
"n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '951'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
Dogs"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
are"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
unparalleled"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
in"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
loyalty"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
and"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
companionship"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
to"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
humans"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9j74gJiY9YxFxbeZ5jmpPclWEeaiP","object":"chat.completion.chunk","created":1720538982,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0959de6b916783-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 15:29:42 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=LA.xC.jE_aMjiSgGgU6kDsBPhb_akgqn_4Rx.jXYfnQ-1720538982-1.0.1.1-l5Q1BHprIz5Jxb4HWyYsMfbg6mEnP2H95Vxt89ez24pKOb__90s8LJBBqK52zmPNcPYSSUcaR0wRAaSVFoa4Fw;
path=/; expires=Tue, 09-Jul-24 15:59:42 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=zzJ51X.VwRkIq7VLCg9xPQGbXoUmAH6b.2g6sf6Y58Y-1720538982657-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '240'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999783'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_abdec68aded596628dfd5b999919447d
status:
code: 200
message: OK
version: 1

1209
tests/cassettes/test_output_json_dict_hierarchical.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

453
tests/cassettes/test_output_json_dict_sequential.yaml Normal file
View File

@@ -0,0 +1,453 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\n\nThis is the expect criteria for your final
answer: The score of the title. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJmkP063CQ01vF8ENhkPSwN9BQH","object":"chat.completion.chunk","created":1720559138,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45f368ab6734-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 21:05:38 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=43lNOCqE3W6gMhKEVIvu20BhU4nI7wyQYcgn28hcb3o-1720559138-1.0.1.1-2pdG6KFn0J2AHC_tnhcxXCqmZ_RyZfwthLi5ET6Aq4v1L9z3EcYxV1D1CeKjOgEBJPLD9GUDdMmIR3h86QYx7w;
path=/; expires=Tue, 09-Jul-24 21:35:38 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=T4YvZnF6fWjq7JTPVyPFDIHaXBpT8E23GcG55Q0Ky6A-1720559138248-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '159'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_a58604fe17d3de5d4491ec972e98312b
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=43lNOCqE3W6gMhKEVIvu20BhU4nI7wyQYcgn28hcb3o-1720559138-1.0.1.1-2pdG6KFn0J2AHC_tnhcxXCqmZ_RyZfwthLi5ET6Aq4v1L9z3EcYxV1D1CeKjOgEBJPLD9GUDdMmIR3h86QYx7w;
_cfuvid=T4YvZnF6fWjq7JTPVyPFDIHaXBpT8E23GcG55Q0Ky6A-1720559138248-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA2xSTW/bMAy9+1cIPMeDncRL7Gt2GNJhOWzdDmthKIriqJFETaK7FkH++yDHjd2g
PggEH98HSJ8SxkDtoGIgDpyEcTotn1Zr8/1lvViV9+rY6ru/zhW/8i+HpvA/YRIZuH2Sgt5YnwQa
pyUptBdYeMlJRtV8Mc2Kosxnyw4wuJM60hpH6RzTaTadp1mR5rOeeEAlZICK/UkYY+zUvTGi3ckX
qFg2eesYGQJvJFTXIcbAo44d4CGoQNwSTAZQoCVpY2rbaj0CCFHXgms9GF++06ge9sS1rk3Y/Cvv
Nq75upx+Pj7/vsfnb2ta6ZHfRfrVdYH2rRXX/Yzwa7+6MWMMLDcd94dALzctuZZu6IwB901rpKUY
HU4PEOLwA1TzM7wbPScf1Y99db6uVWPjPG7DzZZgr6wKh9pLHrq0EAjdxSLKPXbna99dBJxH46gm
PEobBZf99WD4Xwaw6DFC4nrEKZI+HoTXQNLUe2Ub6Z1X3Slh7+p5li3lbLvIS0jOyX8AAAD//wMA
s5wGAdMCAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45f828146734-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 09 Jul 2024 21:05:38 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '215'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999969'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_34b28faf23b6422bb0855e6a45c65e92
status:
code: 200
message: OK
- request:
body: '{"input": ["examples(Examples): Specific scenarios used to explain counting,
addition, and subtraction through the zoo theme, such as counting animals, adding
new ones, and subtracting adopted ones."], "model": "text-embedding-ada-002",
"encoding_format": "base64"}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '265'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/embeddings
response:
body:
string: !!binary |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headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45f9bc6c4589-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 09 Jul 2024 21:05:39 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=IuvCm3DYH_Yj2KCjQfa873zjAj_2TgaF47eD6tQ4Mhs-1720559139-1.0.1.1-fWDjNt6ARNNwSwU4ZoyX.VoMhynDVIi97V54zsXBMuMg_KjRGid.vTsH.YWP4cEbPWj_vdlZjnfl3ef4S90Eog;
path=/; expires=Tue, 09-Jul-24 21:35:39 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=uolQOZ2C52Hd5W7TXNWyFaYk4FEIIwP0B2MH49GGYtA-1720559139009-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
access-control-allow-origin:
- '*'
alt-svc:
- h3=":443"; ma=86400
openai-model:
- text-embedding-ada-002
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '18'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '10000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '9999953'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5f80532d772393d55159f71cbd4e8211
status:
code: 200
message: OK
version: 1

1516
tests/cassettes/test_output_json_hierarchical.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

258
tests/cassettes/test_output_json_sequential.yaml Normal file
View File

@@ -0,0 +1,258 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\n\nThis is the expect criteria for your final
answer: The score of the title. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJkXh6z3EfmS24VIKd3az5QmUI6","object":"chat.completion.chunk","created":1720559136,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45eb19a3c00b-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 21:05:36 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=pA7SjF9QjLel4TzQ_lNj63W_TlcZBVsYreOxByhCguY-1720559136-1.0.1.1-HZhSIVb4ZIrgcL3DwhR7q53vNdieKNmEv_0ZAHDbmBBkD891hDrzxqLpBZSw7j_mFtCPQEjxpAMjD5JI3o8NEw;
path=/; expires=Tue, 09-Jul-24 21:35:36 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=OblnrTSQSq8R858tQhKPz9cFRCWv.MPPI1wxnvjeHJI-1720559136855-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '96'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_ee2fc8fd37b03ee0bcf92ff34f91a51c
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=pA7SjF9QjLel4TzQ_lNj63W_TlcZBVsYreOxByhCguY-1720559136-1.0.1.1-HZhSIVb4ZIrgcL3DwhR7q53vNdieKNmEv_0ZAHDbmBBkD891hDrzxqLpBZSw7j_mFtCPQEjxpAMjD5JI3o8NEw;
_cfuvid=OblnrTSQSq8R858tQhKPz9cFRCWv.MPPI1wxnvjeHJI-1720559136855-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA2xS22rjMBB991eIeY4X5+K68WsoXbplt6WUQjfFKIp8SWSNkMabpiH/XuS4sRvW
D2KYM+fCjA8BY1CtIWUgSk6iNiqcbxZ3anfPy6sPnu92k23iVvttUl7/XPz+BSPPwNVGCvpi/RBY
GyWpQn2ChZWcpFcdJ5MojufjadICNa6l8rTCUDjDcBJNZmEUh+NpRyyxEtJByv4GjDF2aF8fUa/l
O6QsGn11aukcLySk5yHGwKLyHeDOVY64Jhj1oEBNUvvUulFqABCiygRXqjc+fYdB3e+JK5Wtdrc3
L83Y7h8Xm4/7l3/b13nx8Hz3MPA7Se9NGyhvtDjvZ4Cf++mFGWOged1ynwRa+ach09AFnTHgtmhq
qclHh8MSnB9eQjo7wrfRY/C/+q2rjue1KiyMxZW72BLkla5cmVnJXZsWHKE5WXi5t/Z8zbeLgLFY
G8oIt1J7wevuetD/Lz0YdxghcTXgxEEXD9zekayzvNKFtMZW7SkhN9k6Tq6mUZLPIwiOwScAAAD/
/wMAE8hqg9MCAAA=
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45ef8871c00b-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 09 Jul 2024 21:05:37 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '298'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999969'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_cea16690999d7a4128fd55687dc31397
status:
code: 200
message: OK
version: 1

1649
tests/cassettes/test_output_pydantic_hierarchical.yaml Normal file
View File

File diff suppressed because it is too large Load Diff

258
tests/cassettes/test_output_pydantic_sequential.yaml Normal file
View File

@@ -0,0 +1,258 @@
interactions:
- request:
body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
final answer to the task use the exact following format:\n\nThought: I now can
give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
final answer must be the great and the most complete as possible, it must be
outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
Task: Give me an integer score between 1-5 for the following title: ''The impact
of AI in the future of work''\n\nThis is the expect criteria for your final
answer: The score of the title. \n you MUST return the actual complete content
as the final answer, not a summary.\n\nBegin! This is VERY important to you,
use the tools available and give your best Final Answer, your job depends on
it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
"stream": true, "temperature": 0.7}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '997'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: 'data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
I"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
now"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
can"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
give"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
a"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
great"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
Answer"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
data: {"id":"chatcmpl-9jCJjSE1CUTbcdPQgWhGnINQBfDJr","object":"chat.completion.chunk","created":1720559135,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
data: [DONE]
'
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45e24b19bd4d-ATL
Connection:
- keep-alive
Content-Type:
- text/event-stream; charset=utf-8
Date:
- Tue, 09 Jul 2024 21:05:35 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=N7yNe.ilaHt2MJPusthFVyL5PrE._f_nyf4RfU.oIv0-1720559135-1.0.1.1-oCOj_tvpNYp16zBvNbxW.TwSHAFXRiB_i23X4XBw_o01D1_7OKj_HwRNZWdwg9DjDh_C_FSMKTonmzQmsUmtdg;
path=/; expires=Tue, 09-Jul-24 21:35:35 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=aiUOV0PnMjHles7YFoHcFY7PK2Ag6MdKr0GWZzZ_rZo-1720559135403-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '105'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999771'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_759b74b995b84a531eae7df3eddf1196
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
"I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
{"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
"function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
`ScoreOutput` with all the required parameters with correct types", "parameters":
{"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
["score"], "type": "object"}}}]}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '519'
content-type:
- application/json
cookie:
- __cf_bm=N7yNe.ilaHt2MJPusthFVyL5PrE._f_nyf4RfU.oIv0-1720559135-1.0.1.1-oCOj_tvpNYp16zBvNbxW.TwSHAFXRiB_i23X4XBw_o01D1_7OKj_HwRNZWdwg9DjDh_C_FSMKTonmzQmsUmtdg;
_cfuvid=aiUOV0PnMjHles7YFoHcFY7PK2Ag6MdKr0GWZzZ_rZo-1720559135403-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.35.10
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.35.10
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.3
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
body:
string: !!binary |
H4sIAAAAAAAAA2xS22rcMBB991eIeV4XX9ZJ1m8lEGgKSZtSUnLBKPLYq40sCWmcdFn234u8ztpZ
6gcxzJlzYca7iDGQNZQMxJqT6KyKV5vL680mzX58Xd4l773D7O63vMjP7rfrKwuLwDAvGxT0wfoi
TGcVkjT6AAuHnDCopudZUhSrNC8GoDM1qkBrLcVLE2dJtoyTIk7zkbg2UqCHkj1GjDG2G94QUdf4
F0qWLD46HXrPW4TyOMQYOKNCB7j30hPXBIsJFEYT6pBa90rNADJGVYIrNRkfvt2snvbElareb27S
b28/v7/VRXtP13X75+GMF+hmfgfprR0CNb0Wx/3M8GO/PDFjDDTvBu4vYRze9mR7OqEzBty1fYea
QnTYPYEPw09QLvfwaXQf/a9+Hqv9ca3KtNaZF3+yJWikln5dOeR+SAuejD1YBLnn4Xz9p4uAdaaz
VJF5RR0EL8brwfS/TGAxYmSIqxmniMZ44LeesKsaqVt01snhlNDYSmByvsrzPGkg2kf/AAAA//8D
AKtPZkLTAgAA
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8a0b45e5ffd7bd4d-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Tue, 09 Jul 2024 21:05:36 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '153'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains
x-ratelimit-limit-requests:
- '10000'
x-ratelimit-limit-tokens:
- '22000000'
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '21999969'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_36cd16b74a2085c72139d09309d21e39
status:
code: 200
message: OK
version: 1

277
tests/crew_test.py
View File

@@ -87,6 +87,86 @@ def test_crew_config_conditional_requirement():
]
def test_async_task_cannot_include_sequential_async_tasks_in_context():
task1 = Task(
description="Task 1",
async_execution=True,
expected_output="output",
agent=researcher,
)
task2 = Task(
description="Task 2",
async_execution=True,
expected_output="output",
agent=researcher,
context=[task1],
)
task3 = Task(
description="Task 3",
async_execution=True,
expected_output="output",
agent=researcher,
context=[task2],
)
task4 = Task(
description="Task 4",
expected_output="output",
agent=writer,
)
task5 = Task(
description="Task 5",
async_execution=True,
expected_output="output",
agent=researcher,
context=[task4],
)
# This should raise an error because task2 is async and has task1 in its context without a sync task in between
with pytest.raises(
ValueError,
match="Task 'Task 2' is asynchronous and cannot include other sequential asynchronous tasks in its context.",
):
Crew(tasks=[task1, task2, task3, task4, task5], agents=[researcher, writer])
# This should not raise an error because task5 has a sync task (task4) in its context
try:
Crew(tasks=[task1, task4, task5], agents=[researcher, writer])
except ValueError:
pytest.fail("Unexpected ValidationError raised")
def test_context_no_future_tasks():
task2 = Task(
description="Task 2",
expected_output="output",
agent=researcher,
)
task3 = Task(
description="Task 3",
expected_output="output",
agent=researcher,
context=[task2],
)
task4 = Task(
description="Task 4",
expected_output="output",
agent=researcher,
)
task1 = Task(
description="Task 1",
expected_output="output",
agent=researcher,
context=[task4],
)
# This should raise an error because task1 has a context dependency on a future task (task4)
with pytest.raises(
ValueError,
match="Task 'Task 1' has a context dependency on a future task 'Task 4', which is not allowed.",
):
Crew(tasks=[task1, task2, task3, task4], agents=[researcher, writer])
def test_crew_config_with_wrong_keys():
no_tasks_config = json.dumps(
{
@@ -144,10 +224,10 @@ def test_crew_creation():
expected_string_output = "1. **The Rise of AI in Healthcare**: The convergence of AI and healthcare is a promising frontier, offering unprecedented opportunities for disease diagnosis and patient outcome prediction. AI's potential to revolutionize healthcare lies in its capacity to synthesize vast amounts of data, generating precise and efficient results. This technological breakthrough, however, is not just about improving accuracy and efficiency; it's about saving lives. As we stand on the precipice of this transformative era, we must prepare for the complex challenges and ethical questions it poses, while embracing its ability to reshape healthcare as we know it.\n\n2. **Ethical Implications of AI**: As AI intertwines with our daily lives, it presents a complex web of ethical dilemmas. This fusion of technology, philosophy, and ethics is not merely academically intriguing but profoundly impacts the fabric of our society. The questions raised range from decision-making transparency to accountability, and from privacy to potential biases. As we navigate this ethical labyrinth, it is crucial to establish robust frameworks and regulations to ensure that AI serves humanity, and not the other way around.\n\n3. **AI and Data Privacy**: The rise of AI brings with it an insatiable appetite for data, spawning new debates around privacy rights. Balancing the potential benefits of AI with the right to privacy is a unique challenge that intersects technology, law, and human rights. In an increasingly digital world, where personal information forms the backbone of many services, we must grapple with these issues. It's time to redefine the concept of privacy and devise innovative solutions that ensure our digital footprints are not abused.\n\n4. **AI in Job Market**: The discourse around AI's impact on employment is a narrative of contrast, a tale of displacement and creation. On one hand, AI threatens to automate a multitude of jobs, on the other, it promises to create new roles that we cannot yet imagine. This intersection of technology, economics, and labor rights is a critical dialogue that will shape our future. As we stand at this crossroads, we must not only brace ourselves for the changes but also seize the opportunities that this technological wave brings.\n\n5. **Future of AI Agents**: The evolution of AI agents signifies a leap towards a future where AI is not just a tool, but a partner. These sophisticated AI agents, employed in customer service to personal assistants, are redefining our interactions with technology. As we gaze into the future of AI agents, we see a landscape of possibilities and challenges. This journey will be about harnessing the potential of AI agents while navigating the issues of trust, dependence, and ethical use."
assert str(result) == expected_string_output
assert result.raw_output() == expected_string_output
assert result.raw == expected_string_output
assert isinstance(result, CrewOutput)
assert len(result.tasks_output) == len(tasks)
assert result.result() == [expected_string_output]
assert result.raw == expected_string_output
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -174,7 +254,7 @@ def test_sync_task_execution():
)
mock_task_output = TaskOutput(
description="Mock description", raw_output="mocked output", agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
@@ -210,7 +290,7 @@ def test_hierarchical_process():
result = crew.kickoff()
assert (
result.raw_output()
result.raw
== "1. 'Demystifying AI: An in-depth exploration of Artificial Intelligence for the layperson' - In this piece, we will unravel the enigma of AI, simplifying its complexities into digestible information for the everyday individual. By using relatable examples and analogies, we will journey through the neural networks and machine learning algorithms that define AI, without the jargon and convoluted explanations that often accompany such topics.\n\n2. 'The Role of AI in Startups: A Game Changer?' - Startups today are harnessing the power of AI to revolutionize their businesses. This article will delve into how AI, as an innovative force, is shaping the startup ecosystem, transforming everything from customer service to product development. We'll explore real-life case studies of startups that have leveraged AI to accelerate their growth and disrupt their respective industries.\n\n3. 'AI and Ethics: Navigating the Complex Landscape' - AI brings with it not just technological advancements, but ethical dilemmas as well. This article will engage readers in a thought-provoking discussion on the ethical implications of AI, exploring issues like bias in algorithms, privacy concerns, job displacement, and the moral responsibility of AI developers. We will also discuss potential solutions and frameworks to address these challenges.\n\n4. 'Unveiling the AI Agents: The Future of Customer Service' - AI agents are poised to reshape the customer service landscape, offering businesses the ability to provide round-the-clock support and personalized experiences. In this article, we'll dive deep into the world of AI agents, examining how they work, their benefits and limitations, and how they're set to redefine customer interactions in the digital age.\n\n5. 'From Science Fiction to Reality: AI in Everyday Life' - AI, once a concept limited to the realm of sci-fi, has now permeated our daily lives. This article will highlight the ubiquitous presence of AI, from voice assistants and recommendation algorithms, to autonomous vehicles and smart homes. We'll explore how AI, in its various forms, is transforming our everyday experiences, making the future seem a lot closer than we imagined."
)
@@ -248,7 +328,7 @@ def test_crew_with_delegating_agents():
result = crew.kickoff()
assert (
result.raw_output()
result.raw
== "AI Agents, simply put, are intelligent systems that can perceive their environment and take actions to reach specific goals. Imagine them as digital assistants that can learn, adapt and make decisions. They operate in the realms of software or hardware, like a chatbot on a website or a self-driving car. The key to their intelligence is their ability to learn from their experiences, making them better at their tasks over time. In today's interconnected world, AI agents are transforming our lives. They enhance customer service experiences, streamline business processes, and even predict trends in data. Vehicles equipped with AI agents are making transportation safer. In healthcare, AI agents are helping to diagnose diseases, personalizing treatment plans, and monitoring patient health. As we embrace the digital era, these AI agents are not just important, they're becoming indispensable, shaping a future where technology works intuitively and intelligently to meet our needs."
)
@@ -413,7 +493,7 @@ def test_api_calls_throttling(capsys):
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_kickoff_for_each_full_ouput():
def test_crew_kickoff_usage_metrics():
inputs = [
{"topic": "dog"},
{"topic": "cat"},
@@ -432,14 +512,11 @@ def test_crew_kickoff_for_each_full_ouput():
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], full_output=True)
crew = Crew(agents=[agent], tasks=[task])
results = crew.kickoff_for_each(inputs=inputs)
assert len(results) == len(inputs)
for result in results:
assert "usage_metrics" in result
assert isinstance(result["usage_metrics"], dict)
# Assert that all required keys are in usage_metrics and their values are not None
for key in [
"total_tokens",
@@ -447,8 +524,8 @@ def test_crew_kickoff_for_each_full_ouput():
"completion_tokens",
"successful_requests",
]:
assert key in result["usage_metrics"]
assert result["usage_metrics"][key] > 0
assert key in result.token_usage
assert result.token_usage[key] > 0
def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
@@ -471,22 +548,6 @@ def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
assert agent._rpm_controller is None
"""
Future tests:
TODO: 1 async task, 1 sync task. Make sure sync task waits for async to finish before starting.[]
TODO: 3 async tasks, 1 sync task. Make sure sync task waits for async to finish before starting.
TODO: 1 sync task, 1 async task. Make sure we wait for result from async before finishing crew.
TODO: 3 async tasks, 1 sync task. Make sure context from all 3 async tasks is passed to sync task.
TODO: 3 async tasks, 1 sync task. Pass in context from only 1 async task to sync task.
TODO: Test pydantic output of CrewOutput and test type in CrewOutput result
TODO: Test json output of CrewOutput and test type in CrewOutput result
TODO: TEST THE SAME THING BUT WITH HIERARCHICAL PROCESS
"""
@pytest.mark.vcr(filter_headers=["authorization"])
def test_sequential_async_task_execution_completion():
list_ideas = Task(
@@ -515,48 +576,11 @@ def test_sequential_async_task_execution_completion():
)
sequential_result = sequential_crew.kickoff()
assert sequential_result.raw_output().startswith(
assert sequential_result.raw.startswith(
"**The Evolution of Artificial Intelligence: A Journey Through Milestones**"
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_async_task_execution_completion():
from langchain_openai import ChatOpenAI
list_ideas = Task(
description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
expected_output="Bullet point list of 5 important events.",
agent=researcher,
async_execution=True,
)
list_important_history = Task(
description="Research the history of AI and give me the 5 most important events that shaped the technology.",
expected_output="Bullet point list of 5 important events.",
agent=researcher,
async_execution=True,
)
write_article = Task(
description="Write an article about the history of AI and its most important events.",
expected_output="A 4 paragraph article about AI.",
agent=writer,
context=[list_ideas, list_important_history],
)
hierarchical_crew = Crew(
agents=[researcher, writer],
process=Process.hierarchical,
tasks=[list_ideas, list_important_history, write_article],
manager_llm=ChatOpenAI(temperature=0, model="gpt-4"),
)
hierarchical_result = hierarchical_crew.kickoff()
assert hierarchical_result.raw_output().startswith(
"The history of artificial intelligence (AI) is a fascinating journey"
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_single_task_with_async_execution():
researcher_agent = Agent(
@@ -580,8 +604,7 @@ def test_single_task_with_async_execution():
)
result = crew.kickoff()
print(result.raw_output())
assert result.raw_output().startswith(
assert result.raw.startswith(
"- The impact of AI agents on remote work productivity."
)
@@ -614,17 +637,21 @@ def test_three_task_with_async_execution():
async_execution=True,
)
crew = Crew(
agents=[researcher_agent],
process=Process.sequential,
tasks=[bullet_list, numbered_list, letter_list],
)
# Expected result is that we will get an error
# because a crew can end only end with one or less
# async tasks
with pytest.raises(pydantic_core._pydantic_core.ValidationError) as error:
Crew(
agents=[researcher_agent],
process=Process.sequential,
tasks=[bullet_list, numbered_list, letter_list],
)
# Expected result is that we are going to concatenate the output from each async task.
# Because we add a buffer between each task, we should see a "----------" string
# after the first and second task in the final output.
result = crew.kickoff()
assert result.raw_output().count("\n\n----------\n\n") == 2
assert error.value.errors()[0]["type"] == "async_task_count"
assert (
"The crew must end with at most one asynchronous task."
in error.value.errors()[0]["msg"]
)
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -648,7 +675,7 @@ async def test_crew_async_kickoff():
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], full_output=True)
crew = Crew(agents=[agent], tasks=[task])
results = await crew.kickoff_for_each_async(inputs=inputs)
assert len(results) == len(inputs)
@@ -661,8 +688,7 @@ async def test_crew_async_kickoff():
"successful_requests",
]:
assert key in result.token_usage
# TODO: FIX THIS WHEN USAGE METRICS ARE RE-DONE
# assert result.token_usage[key] > 0
assert result.token_usage[key] > 0
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -695,7 +721,7 @@ def test_async_task_execution_call_count():
# Create a valid TaskOutput instance to mock the return value
mock_task_output = TaskOutput(
description="Mock description", raw_output="mocked output", agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Create a MagicMock Future instance
@@ -721,10 +747,8 @@ def test_async_task_execution_call_count():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_kickoff_for_each_single_input():
"""Tests if kickoff_for_each works with a single input."""
from unittest.mock import patch
inputs = [{"topic": "dog"}]
expected_outputs = ["Dogs are loyal companions and popular pets."]
agent = Agent(
role="{topic} Researcher",
@@ -738,32 +762,21 @@ def test_kickoff_for_each_single_input():
agent=agent,
)
with patch.object(Agent, "execute_task") as mock_execute_task:
mock_execute_task.side_effect = expected_outputs
crew = Crew(agents=[agent], tasks=[task])
results = crew.kickoff_for_each(inputs=inputs)
crew = Crew(agents=[agent], tasks=[task])
results = crew.kickoff_for_each(inputs=inputs)
assert len(results) == 1
print("RESULT:", results)
for result in results:
assert result == expected_outputs[0]
@pytest.mark.vcr(filter_headers=["authorization"])
def test_kickoff_for_each_multiple_inputs():
"""Tests if kickoff_for_each works with multiple inputs."""
from unittest.mock import patch
inputs = [
{"topic": "dog"},
{"topic": "cat"},
{"topic": "apple"},
]
expected_outputs = [
"Dogs are loyal companions and popular pets.",
"Cats are independent and low-maintenance pets.",
"Apples are a rich source of dietary fiber and vitamin C.",
]
agent = Agent(
role="{topic} Researcher",
@@ -777,14 +790,10 @@ def test_kickoff_for_each_multiple_inputs():
agent=agent,
)
with patch.object(Agent, "execute_task") as mock_execute_task:
mock_execute_task.side_effect = expected_outputs
crew = Crew(agents=[agent], tasks=[task])
results = crew.kickoff_for_each(inputs=inputs)
crew = Crew(agents=[agent], tasks=[task])
results = crew.kickoff_for_each(inputs=inputs)
assert len(results) == len(inputs)
for i, res in enumerate(results):
assert res == expected_outputs[i]
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -1056,7 +1065,7 @@ def test_crew_function_calling_llm():
with patch.object(llm.client, "create", wraps=llm.client.create) as private_mock:
@tool
def learn_about_AI(topic) -> float:
def learn_about_AI(topic) -> str:
"""Useful for when you need to learn about AI to write an paragraph about it."""
return "AI is a very broad field."
@@ -1105,7 +1114,7 @@ def test_task_with_no_arguments():
crew = Crew(agents=[researcher], tasks=[task])
result = crew.kickoff()
assert result.raw_output() == "75"
assert result.raw == "75"
def test_code_execution_flag_adds_code_tool_upon_kickoff():
@@ -1170,39 +1179,12 @@ def test_agents_do_not_get_delegation_tools_with_there_is_only_one_agent():
result = crew.kickoff()
assert (
result.raw_output()
result.raw
== "Howdy! I hope this message finds you well and brings a smile to your face. Have a fantastic day!"
)
assert len(agent.tools) == 0
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_usage_metrics_are_captured_for_sequential_process():
agent = Agent(
role="Researcher",
goal="Be super empathetic.",
backstory="You're love to sey howdy.",
allow_delegation=False,
)
task = Task(description="say howdy", expected_output="Howdy!", agent=agent)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
assert result.raw_output() == "Howdy!"
required_keys = [
"total_tokens",
"prompt_tokens",
"completion_tokens",
"successful_requests",
]
for key in required_keys:
assert key in crew.usage_metrics, f"Key '{key}' not found in usage_metrics"
assert crew.usage_metrics[key] > 0, f"Value for key '{key}' is zero"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_sequential_crew_creation_tasks_without_agents():
task = Task(
@@ -1247,13 +1229,15 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
)
result = crew.kickoff()
assert result.raw_output() == '"Howdy!"'
assert result.raw == '"Howdy!"'
print(crew.usage_metrics)
assert crew.usage_metrics == {
"total_tokens": 1927,
"prompt_tokens": 1557,
"completion_tokens": 370,
"successful_requests": 4,
"total_tokens": 311,
"prompt_tokens": 224,
"completion_tokens": 87,
"successful_requests": 1,
}
@@ -1278,15 +1262,17 @@ def test_hierarchical_crew_creation_tasks_with_agents():
manager_llm=ChatOpenAI(model="gpt-4o"),
)
crew.kickoff()
assert crew.manager_agent is not None
assert crew.manager_agent.tools is not None
print("TOOL DESCRIPTION", crew.manager_agent.tools[0].description)
assert crew.manager_agent.tools[0].description.startswith(
"Delegate a specific task to one of the following coworkers: [Senior Writer]"
"Delegate a specific task to one of the following coworkers: [Senior Writer, Researcher]"
)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_hierarchical_crew_creation_tasks_without_async_execution():
def test_hierarchical_crew_creation_tasks_with_async_execution():
from langchain_openai import ChatOpenAI
task = Task(
@@ -1481,7 +1467,7 @@ def test_tools_with_custom_caching():
from crewai_tools import tool
@tool
def multiplcation_tool(first_number: int, second_number: int) -> str:
def multiplcation_tool(first_number: int, second_number: int) -> int:
"""Useful for when you need to multiply two numbers together."""
return first_number * second_number
@@ -1543,7 +1529,7 @@ def test_tools_with_custom_caching():
input={"first_number": 2, "second_number": 6},
output=12,
)
assert result.raw_output() == "3"
assert result.raw == "3"
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -1642,7 +1628,7 @@ def test_manager_agent():
)
mock_task_output = TaskOutput(
description="Mock description", raw_output="mocked output", agent="mocked agent"
description="Mock description", raw="mocked output", agent="mocked agent"
)
# Because we are mocking execute_sync, we never hit the underlying _execute_core
@@ -1818,11 +1804,6 @@ def test__setup_for_training():
assert agent.allow_delegation is False
# TODO: TEST EXPORT OUTPUT TASK WITH PYDANTIC
# TODO: TEST EXPORT OUTPUT TASK WITH JSON
# TODO: TEST EXPORT OUTPUT TASK CALLBACK
@pytest.mark.vcr(filter_headers=["authorization"])
def test_replay_feature():
list_ideas = Task(

264
tests/task_test.py
View File

@@ -109,6 +109,8 @@ def test_task_callback():
def test_task_callback_returns_task_ouput():
from crewai.tasks.output_format import OutputFormat
researcher = Agent(
role="Researcher",
goal="Make the best research and analysis on content about AI and AI agents",
@@ -140,10 +142,12 @@ def test_task_callback_returns_task_ouput():
output_dict = json.loads(callback_data)
expected_output = {
"description": task.description,
"exported_output": "exported_ok",
"raw_output": "exported_ok",
"raw": "exported_ok",
"pydantic": None,
"json_dict": None,
"agent": researcher.role,
"summary": "Give me a list of 5 interesting ideas to explore...",
"output_format": OutputFormat.RAW,
}
assert output_dict == expected_output
@@ -200,7 +204,7 @@ def test_multiple_output_type_error():
@pytest.mark.vcr(filter_headers=["authorization"])
def test_output_pydantic():
def test_output_pydantic_sequential():
class ScoreOutput(BaseModel):
score: int
@@ -218,13 +222,46 @@ def test_output_pydantic():
agent=scorer,
)
crew = Crew(agents=[scorer], tasks=[task])
crew = Crew(agents=[scorer], tasks=[task], process=Process.sequential)
result = crew.kickoff()
assert isinstance(result, ScoreOutput)
assert isinstance(result.pydantic, ScoreOutput)
assert result.to_dict() == {"score": 4}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_output_json():
def test_output_pydantic_hierarchical():
from langchain_openai import ChatOpenAI
class ScoreOutput(BaseModel):
score: int
scorer = Agent(
role="Scorer",
goal="Score the title",
backstory="You're an expert scorer, specialized in scoring titles.",
allow_delegation=False,
)
task = Task(
description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
expected_output="The score of the title.",
output_pydantic=ScoreOutput,
agent=scorer,
)
crew = Crew(
agents=[scorer],
tasks=[task],
process=Process.hierarchical,
manager_llm=ChatOpenAI(model="gpt-4o"),
)
result = crew.kickoff()
assert isinstance(result.pydantic, ScoreOutput)
assert result.to_dict() == {"score": 4}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_output_json_sequential():
class ScoreOutput(BaseModel):
score: int
@@ -242,9 +279,126 @@ def test_output_json():
agent=scorer,
)
crew = Crew(agents=[scorer], tasks=[task])
crew = Crew(agents=[scorer], tasks=[task], process=Process.sequential)
result = crew.kickoff()
assert '{\n "score": 4\n}' == result
assert '{"score": 4}' == result.json
assert result.to_dict() == {"score": 4}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_output_json_hierarchical():
from langchain_openai import ChatOpenAI
class ScoreOutput(BaseModel):
score: int
scorer = Agent(
role="Scorer",
goal="Score the title",
backstory="You're an expert scorer, specialized in scoring titles.",
allow_delegation=False,
)
task = Task(
description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
expected_output="The score of the title.",
output_json=ScoreOutput,
agent=scorer,
)
crew = Crew(
agents=[scorer],
tasks=[task],
process=Process.hierarchical,
manager_llm=ChatOpenAI(model="gpt-4o"),
)
result = crew.kickoff()
assert '{"score": 4}' == result.json
assert result.to_dict() == {"score": 4}
def test_json_property_without_output_json():
class ScoreOutput(BaseModel):
score: int
scorer = Agent(
role="Scorer",
goal="Score the title",
backstory="You're an expert scorer, specialized in scoring titles.",
allow_delegation=False,
)
task = Task(
description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
expected_output="The score of the title.",
output_pydantic=ScoreOutput, # Using output_pydantic instead of output_json
agent=scorer,
)
crew = Crew(agents=[scorer], tasks=[task], process=Process.sequential)
result = crew.kickoff()
with pytest.raises(ValueError) as excinfo:
_ = result.json # Attempt to access the json property
assert "No JSON output found in the final task." in str(excinfo.value)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_output_json_dict_sequential():
class ScoreOutput(BaseModel):
score: int
scorer = Agent(
role="Scorer",
goal="Score the title",
backstory="You're an expert scorer, specialized in scoring titles.",
allow_delegation=False,
)
task = Task(
description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
expected_output="The score of the title.",
output_json=ScoreOutput,
agent=scorer,
)
crew = Crew(agents=[scorer], tasks=[task], process=Process.sequential)
result = crew.kickoff()
assert {"score": 4} == result.json_dict
assert result.to_dict() == {"score": 4}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_output_json_dict_hierarchical():
from langchain_openai import ChatOpenAI
class ScoreOutput(BaseModel):
score: int
scorer = Agent(
role="Scorer",
goal="Score the title",
backstory="You're an expert scorer, specialized in scoring titles.",
allow_delegation=False,
)
task = Task(
description="Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work'",
expected_output="The score of the title.",
output_json=ScoreOutput,
agent=scorer,
)
crew = Crew(
agents=[scorer],
tasks=[task],
process=Process.hierarchical,
manager_llm=ChatOpenAI(model="gpt-4o"),
)
result = crew.kickoff()
assert {"score": 4} == result.json_dict
assert result.to_dict() == {"score": 4}
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -280,7 +434,11 @@ def test_output_pydantic_to_another_task():
crew = Crew(agents=[scorer], tasks=[task1, task2], verbose=2)
result = crew.kickoff()
assert 5 == result.score
pydantic_result = result.pydantic
assert isinstance(
pydantic_result, ScoreOutput
), "Expected pydantic result to be of type ScoreOutput"
assert 5 == pydantic_result.score
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -311,7 +469,7 @@ def test_output_json_to_another_task():
crew = Crew(agents=[scorer], tasks=[task1, task2])
result = crew.kickoff()
assert '{\n "score": 5\n}' == result
assert '{"score": 5}' == result.json
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -363,7 +521,9 @@ def test_save_task_json_output():
with patch.object(Task, "_save_file") as save_file:
save_file.return_value = None
crew.kickoff()
save_file.assert_called_once_with('{\n "score": 4\n}')
save_file.assert_called_once_with(
{"score": 4}
) # TODO: @Joao, should this be a dict or a json string?
@pytest.mark.vcr(filter_headers=["authorization"])
@@ -558,12 +718,78 @@ def test_interpolate_inputs():
assert task.expected_output == "Bullet point list of 5 interesting ideas about ML."
"""
TODO: TEST SYNC
- Verify return type
"""
def test_task_output_str_with_pydantic():
from crewai.tasks.output_format import OutputFormat
"""
TODO: TEST ASYNC
- Verify return type
"""
class ScoreOutput(BaseModel):
score: int
score_output = ScoreOutput(score=4)
task_output = TaskOutput(
description="Test task",
agent="Test Agent",
pydantic=score_output,
output_format=OutputFormat.PYDANTIC,
)
assert str(task_output) == str(score_output)
def test_task_output_str_with_json_dict():
from crewai.tasks.output_format import OutputFormat
json_dict = {"score": 4}
task_output = TaskOutput(
description="Test task",
agent="Test Agent",
json_dict=json_dict,
output_format=OutputFormat.JSON,
)
assert str(task_output) == str(json_dict)
def test_task_output_str_with_raw():
from crewai.tasks.output_format import OutputFormat
raw_output = "Raw task output"
task_output = TaskOutput(
description="Test task",
agent="Test Agent",
raw=raw_output,
output_format=OutputFormat.RAW,
)
assert str(task_output) == raw_output
def test_task_output_str_with_pydantic_and_json_dict():
from crewai.tasks.output_format import OutputFormat
class ScoreOutput(BaseModel):
score: int
score_output = ScoreOutput(score=4)
json_dict = {"score": 4}
task_output = TaskOutput(
description="Test task",
agent="Test Agent",
pydantic=score_output,
json_dict=json_dict,
output_format=OutputFormat.PYDANTIC,
)
# When both pydantic and json_dict are present, pydantic should take precedence
assert str(task_output) == str(score_output)
def test_task_output_str_with_none():
from crewai.tasks.output_format import OutputFormat
task_output = TaskOutput(
description="Test task",
agent="Test Agent",
output_format=OutputFormat.RAW,
)
assert str(task_output) == ""