andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-01 15:22:37 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Making all tests good

Browse Source
This commit is contained in:
João Moura
2024-09-13 04:30:11 -05:00
parent 7120a9860b
commit 91ddab207f
88 changed files with 28070 additions and 26873 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
tests/agent_tools/cassettes/test_ask_question.yaml
View File

@@ -1,18 +1,18 @@
interactions:
- request:
body: '{"messages": [{"role": "user", "content": "You are researcher. You''re
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
the best research and analysis on content about AI and AI agents\nTo 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: Your 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: do you hate AI Agents?\n\nThis
is the expect criteria for your final answer: Your best answer to your coworker
asking you this, accounting for the context shared. \n you MUST return the actual
complete content as the final answer, not a summary.\n\nThis is the context
you''re working with:\nI heard you LOVE them\n\nBegin! This is VERY important
to you, use the tools available and give your best Final Answer, your job depends
on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
these formats, my job depends on it!"}, {"role": "user", "content": "\nCurrent
Task: do you hate AI Agents?\n\nThis is the expect criteria for your final answer:
Your best answer to your coworker asking you this, accounting for the context
shared.\nyou MUST return the actual complete content as the final answer, not
a summary.\n\nThis is the context you''re working with:\nI heard you LOVE them\n\nBegin!
This is VERY important to you, use the tools available and give your best Final
Answer, your job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation"]}'
headers:
accept:
- application/json
@@ -21,16 +21,16 @@ interactions:
connection:
- keep-alive
content-length:
- '1015'
- '1048'
content-type:
- application/json
cookie:
- _cfuvid=_Qurzg7MGysLGzSugSD3ZV84qR5Lfxrt9mF2_tfTJqw-1725940709772-0.0.1.1-604800000;
__cf_bm=_VKcRD0U2g9VfrlK3xy3AVQfynnKXZY2jX0QBkR8us8-1725940709-1.0.1.1-F0MIxvXffEPTFVqJ6cgovOMZ9E88rvBTRMj7aIlAQz.bEZJA5fip0HhCYxawoz1MDdwfQ2X_c9FjtN27PR.RHw
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.44.0
- OpenAI/Python 1.45.0
x-stainless-arch:
- arm64
x-stainless-async:
@@ -40,7 +40,7 @@ interactions:
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.44.0
- 1.45.0
x-stainless-raw-response:
- 'true'
x-stainless-runtime:
@@ -50,37 +50,26 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A5mJQNSDLNf8gAtqujHs3AMhA6rjD\",\n \"object\":
\"chat.completion\",\n \"created\": 1725940716,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A6vf21WmSSHP1NWd6mOZbyMFwaPeT\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214980,\n \"model\": \"gpt-4o-2024-05-13\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: AI agents are a fascinating and powerful tool in the realm of technology.
As a researcher specialized in AI, I find that they can offer transformative
benefits across a variety of fields, from healthcare to finance, and even education.
While it's true that I have a deep appreciation for the capabilities and potential
of AI agents, it's important to consider them critically.\\n\\nAI agents can
streamline processes, make data-driven decisions more efficiently, and handle
complex algorithms that would be time-consuming for humans. They can analyze
vast amounts of data in real-time, offering insights that would otherwise be
unattainable. This potent combination of speed and accuracy can lead to significant
advancements and innovations.\\n\\nHowever, with any powerful technology, there
are inherent risks and challenges. Ethical considerations such as bias in AI
algorithms, privacy concerns, and the potential for job displacement must be
addressed as part of responsible AI development and deployment. Transparent
practices, rigorous testing, and strict regulatory measures are crucial to mitigating
these risks.\\n\\nIn conclusion, while I do have a passion for AI agents due
to their immense potential to drive progress and solve complex problems, I also
advocate for a balanced approach that carefully weighs their benefits against
the possible ethical implications. It's this nuanced perspective that fuels
my ongoing research and analysis in the field.\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 195,\n \"completion_tokens\":
262,\n \"total_tokens\": 457\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
Answer: As a researcher specialized in technology, I neither love nor hate AI
agents. My role is to objectively analyze their capabilities, impacts, and potential.
AI agents have many beneficial applications, such as improving healthcare, optimizing
logistics, and enhancing user experiences. However, there are also concerns
regarding privacy, ethical implications, and job displacement. My professional
stance is to critically evaluate both the advantages and the challenges, ensuring
that the development and deployment of AI agents are conducted responsibly and
ethically.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
199,\n \"completion_tokens\": 107,\n \"total_tokens\": 306,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c0c8027f8af2ae0-LAX
- 8c26a80a3a2f2ab9-LAX
Connection:
- keep-alive
Content-Encoding:
@@ -88,7 +77,7 @@ interactions:
Content-Type:
- application/json
Date:
- Tue, 10 Sep 2024 03:58:39 GMT
- Fri, 13 Sep 2024 08:09:41 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -102,7 +91,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '2347'
- '1227'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -114,13 +103,13 @@ interactions:
x-ratelimit-remaining-requests:
- '9999'
x-ratelimit-remaining-tokens:
- '29999756'
- '29999755'
x-ratelimit-reset-requests:
- 6ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_d98a2146a451f220968790785caf0586
- req_aa98d851407f05a0803bfebce008bc88
http_version: HTTP/1.1
status_code: 200
version: 1