mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-05-03 08:12:39 +00:00
chore: delete all cassettes and update conftest
This commit is contained in:
Greyson LaLonde
@@ -52,7 +52,7 @@ class GeminiCompletion(BaseLLM):
|
||||
|
||||
Args:
|
||||
model: Gemini model name (e.g., 'gemini-2.0-flash-001', 'gemini-1.5-pro')
|
||||
api_key: Google API key (defaults to GOOGLE_API_KEY or GEMINI_API_KEY env var)
|
||||
api_key: Google API key (defaults to GEMINI_API_KEY or GEMINI_API_KEY env var)
|
||||
project: Google Cloud project ID (for Vertex AI)
|
||||
location: Google Cloud location (for Vertex AI, defaults to 'us-central1')
|
||||
temperature: Sampling temperature (0-2)
|
||||
@@ -82,7 +82,7 @@ class GeminiCompletion(BaseLLM):
|
||||
|
||||
# Get API configuration with environment variable fallbacks
|
||||
self.api_key = (
|
||||
api_key or os.getenv("GOOGLE_API_KEY") or os.getenv("GEMINI_API_KEY")
|
||||
api_key or os.getenv("GEMINI_API_KEY") or os.getenv("GEMINI_API_KEY")
|
||||
)
|
||||
self.project = project or os.getenv("GOOGLE_CLOUD_PROJECT")
|
||||
self.location = location or os.getenv("GOOGLE_CLOUD_LOCATION") or "us-central1"
|
||||
@@ -165,7 +165,7 @@ class GeminiCompletion(BaseLLM):
|
||||
return genai.Client(**client_params)
|
||||
except Exception as e:
|
||||
raise ValueError(
|
||||
"Either GOOGLE_API_KEY/GEMINI_API_KEY (for Gemini API) or "
|
||||
"Either GEMINI_API_KEY/GEMINI_API_KEY (for Gemini API) or "
|
||||
"GOOGLE_CLOUD_PROJECT (for Vertex AI) must be set"
|
||||
) from e
|
||||
|
||||
|
||||
@@ -21,7 +21,7 @@ class GenerativeAiProvider(BaseEmbeddingsProvider[GoogleGenerativeAiEmbeddingFun
|
||||
validation_alias="EMBEDDINGS_GOOGLE_GENERATIVE_AI_MODEL_NAME",
|
||||
)
|
||||
api_key: str = Field(
|
||||
description="Google API key", validation_alias="EMBEDDINGS_GOOGLE_API_KEY"
|
||||
description="Google API key", validation_alias="EMBEDDINGS_GEMINI_API_KEY"
|
||||
)
|
||||
task_type: str = Field(
|
||||
default="RETRIEVAL_DOCUMENT",
|
||||
|
||||
@@ -261,25 +261,6 @@ async def test_lite_agent_returns_usage_metrics_async():
|
||||
assert result.usage_metrics["total_tokens"] > 0
|
||||
|
||||
|
||||
class TestFlow(Flow):
|
||||
"""A test flow that creates and runs an agent."""
|
||||
|
||||
def __init__(self, llm, tools):
|
||||
self.llm = llm
|
||||
self.tools = tools
|
||||
super().__init__()
|
||||
|
||||
@start()
|
||||
def start(self):
|
||||
agent = Agent(
|
||||
role="Test Agent",
|
||||
goal="Test Goal",
|
||||
backstory="Test Backstory",
|
||||
llm=self.llm,
|
||||
tools=self.tools,
|
||||
)
|
||||
return agent.kickoff("Test query")
|
||||
|
||||
|
||||
def verify_agent_parent_flow(result, agent, flow):
|
||||
"""Verify that both the result and agent have the correct parent flow."""
|
||||
|
||||
@@ -1,495 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"trace_id": "REDACTED_TRACE_ID", "execution_type":
|
||||
"crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
|
||||
"crew_name": "Unknown Crew", "flow_name": null, "crewai_version": "1.4.0", "privacy_level":
|
||||
"standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
|
||||
0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-07T18:27:07.650947+00:00"}}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate, zstd
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '434'
|
||||
Content-Type:
|
||||
- application/json
|
||||
User-Agent:
|
||||
- CrewAI-CLI/1.4.0
|
||||
X-Crewai-Version:
|
||||
- 1.4.0
|
||||
method: POST
|
||||
uri: https://app.crewai.com/crewai_plus/api/v1/tracing/batches
|
||||
response:
|
||||
body:
|
||||
string: '{"error":"bad_credentials","message":"Bad credentials"}'
|
||||
headers:
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '55'
|
||||
Content-Type:
|
||||
- application/json; charset=utf-8
|
||||
Date:
|
||||
- Fri, 07 Nov 2025 18:27:07 GMT
|
||||
cache-control:
|
||||
- no-store
|
||||
content-security-policy:
|
||||
- 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self''
|
||||
''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts
|
||||
https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
|
||||
https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
|
||||
https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
|
||||
https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
|
||||
https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com
|
||||
https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/
|
||||
https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net
|
||||
https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net
|
||||
https://js.hscollectedforms.net https://js.usemessages.com https://snap.licdn.com
|
||||
https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com
|
||||
https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com
|
||||
app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data:
|
||||
*.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com
|
||||
https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com
|
||||
https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com
|
||||
https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com;
|
||||
connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com
|
||||
https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/*
|
||||
https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io
|
||||
https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com
|
||||
https://api.hubspot.com https://forms.hscollectedforms.net https://api.hubapi.com
|
||||
https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509
|
||||
https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect
|
||||
https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self''
|
||||
*.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com
|
||||
https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com
|
||||
https://drive.google.com https://slides.google.com https://accounts.google.com
|
||||
https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/
|
||||
https://www.youtube.com https://share.descript.com'
|
||||
expires:
|
||||
- '0'
|
||||
permissions-policy:
|
||||
- camera=(), microphone=(self), geolocation=()
|
||||
pragma:
|
||||
- no-cache
|
||||
referrer-policy:
|
||||
- strict-origin-when-cross-origin
|
||||
strict-transport-security:
|
||||
- max-age=63072000; includeSubDomains
|
||||
vary:
|
||||
- Accept
|
||||
x-content-type-options:
|
||||
- nosniff
|
||||
x-frame-options:
|
||||
- SAMEORIGIN
|
||||
x-permitted-cross-domain-policies:
|
||||
- none
|
||||
x-request-id:
|
||||
- REDACTED_REQUEST_ID
|
||||
x-runtime:
|
||||
- '0.080681'
|
||||
x-xss-protection:
|
||||
- 1; mode=block
|
||||
status:
|
||||
code: 401
|
||||
message: Unauthorized
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are data collector. You must
|
||||
use the get_data tool extensively\nYour personal goal is: collect data using
|
||||
the get_data tool\nYou ONLY have access to the following tools, and should NEVER
|
||||
make up tools that are not listed here:\n\nTool Name: get_data\nTool Arguments:
|
||||
{''step'': {''description'': None, ''type'': ''str''}}\nTool Description: Get
|
||||
data for a step. Always returns data requiring more steps.\n\nIMPORTANT: Use
|
||||
the following format in your response:\n\n```\nThought: you should always think
|
||||
about what to do\nAction: the action to take, only one name of [get_data], just
|
||||
the name, exactly as it''s written.\nAction Input: the input to the action,
|
||||
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
|
||||
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
||||
is gathered, return the following format:\n\n```\nThought: I now know the final
|
||||
answer\nFinal Answer: the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
|
||||
Task: Use get_data tool for step1, step2, step3, step4, step5, step6, step7,
|
||||
step8, step9, and step10. Do NOT stop until you''ve called it for ALL steps.\n\nThis
|
||||
is the expected criteria for your final answer: A summary of all data collected\nyou
|
||||
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
|
||||
This is VERY important to you, use the tools available and give your best Final
|
||||
Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1534'
|
||||
content-type:
|
||||
- application/json
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.109.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.109.1
|
||||
x-stainless-read-timeout:
|
||||
- '600'
|
||||
x-stainless-retry-count:
|
||||
- '0'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.9
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA4xSYWvbMBD97l9x6HMcYsfpUn8rg0FHYbAOyrYUo0hnW5ksCem8tYT89yG7id2t
|
||||
g30x5t69p/fu7pgAMCVZCUy0nETndPr+2919j4fr9VNR/Opv7vBD/bAVXz/dfzx8fmCLyLD7Awo6
|
||||
s5bCdk4jKWtGWHjkhFE1e3eVb4rVKt8OQGcl6khrHKXFMks7ZVSar/JNuirSrHiht1YJDKyE7wkA
|
||||
wHH4RqNG4hMrYbU4VzoMgTfIyksTAPNWxwrjIahA3BBbTKCwhtAM3r+0tm9aKuEWQmt7LSEQ9wT7
|
||||
ZxBWaxSkTAOSE4faegiELgMeQJlAvheEcrkzNyLmLqFBqmLruQK3xvVUwnHHInHHyvEn27HT3I/H
|
||||
ug88DsX0Ws8AbowlHqWGSTy+IKdLdm0b5+0+/EFltTIqtJVHHqyJOQNZxwb0lAA8DjPuX42NOW87
|
||||
RxXZHzg8t15nox6bdjuh4zYBGFniesbaXC/e0KskElc6zLbEBBctyok6rZT3UtkZkMxS/+3mLe0x
|
||||
uTLN/8hPgBDoCGXlPEolXiee2jzG0/9X22XKg2EW0P9UAitS6OMmJNa81+M9svAcCLuqVqZB77wa
|
||||
j7J2VSHy7Sart1c5S07JbwAAAP//AwCiugNoowMAAA==
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 99aee205bbd2de96-EWR
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 07 Nov 2025 18:27:08 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Set-Cookie:
|
||||
- __cf_bm=REDACTED_COOKIE;
|
||||
path=/; expires=Fri, 07-Nov-25 18:57:08 GMT; domain=.api.openai.com; HttpOnly;
|
||||
Secure; SameSite=None
|
||||
- _cfuvid=REDACTED_COOKIE;
|
||||
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
cf-cache-status:
|
||||
- DYNAMIC
|
||||
openai-organization:
|
||||
- REDACTED_ORG_ID
|
||||
openai-processing-ms:
|
||||
- '557'
|
||||
openai-project:
|
||||
- REDACTED_PROJECT_ID
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '701'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
- '500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '200000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '199645'
|
||||
x-ratelimit-reset-requests:
|
||||
- 120ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 106ms
|
||||
x-request-id:
|
||||
- REDACTED_REQUEST_ID
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are data collector. You must
|
||||
use the get_data tool extensively\nYour personal goal is: collect data using
|
||||
the get_data tool\nYou ONLY have access to the following tools, and should NEVER
|
||||
make up tools that are not listed here:\n\nTool Name: get_data\nTool Arguments:
|
||||
{''step'': {''description'': None, ''type'': ''str''}}\nTool Description: Get
|
||||
data for a step. Always returns data requiring more steps.\n\nIMPORTANT: Use
|
||||
the following format in your response:\n\n```\nThought: you should always think
|
||||
about what to do\nAction: the action to take, only one name of [get_data], just
|
||||
the name, exactly as it''s written.\nAction Input: the input to the action,
|
||||
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
|
||||
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
||||
is gathered, return the following format:\n\n```\nThought: I now know the final
|
||||
answer\nFinal Answer: the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
|
||||
Task: Use get_data tool for step1, step2, step3, step4, step5, step6, step7,
|
||||
step8, step9, and step10. Do NOT stop until you''ve called it for ALL steps.\n\nThis
|
||||
is the expected criteria for your final answer: A summary of all data collected\nyou
|
||||
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
|
||||
This is VERY important to you, use the tools available and give your best Final
|
||||
Answer, your job depends on it!\n\nThought:"},{"role":"assistant","content":"Thought:
|
||||
I should start by collecting data for step1 as instructed.\nAction: get_data\nAction
|
||||
Input: {\"step\":\"step1\"}\nObservation: Data for step1: incomplete, need to
|
||||
query more steps."}],"model":"gpt-4.1-mini"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1757'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=REDACTED_COOKIE;
|
||||
_cfuvid=REDACTED_COOKIE
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.109.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.109.1
|
||||
x-stainless-read-timeout:
|
||||
- '600'
|
||||
x-stainless-retry-count:
|
||||
- '0'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.9
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAAwAAAP//jFNNb9swDL37VxA6x0HiOU3mW9cOQ4F9YNjQQ5fCUGXaVidLqkQnzYL8
|
||||
90F2ErtbB+xiCHx8j+QjvY8AmCxYBkzUnERjVXx19/Hb5tPm/fbq8sPX5+Wvx6V+t93efXY1v71m
|
||||
k8AwD48o6MSaCtNYhSSN7mHhkBMG1fnyIlmks1nytgMaU6AKtMpSnE7ncSO1jJNZsohnaTxPj/Ta
|
||||
SIGeZfAjAgDYd9/QqC7wmWUwm5wiDXrPK2TZOQmAOaNChHHvpSeuiU0GUBhNqLvev9emrWrK4AY0
|
||||
YgFkIKBStxjentAmfVApFAQFJw4en1rUJLlSO+AeHD610mExXetLESzIoELKQ+4pAjfatpTBfs2C
|
||||
5ppl/SNZs8Naf3nw6Da8p16HEqVxffEMpD56ixNojMMu7kGjCIO73XQ8msOy9Tz4q1ulRgDX2lBX
|
||||
oTP1/ogczjYqU1lnHvwfVFZKLX2dO+Te6GCZJ2NZhx4igPtuXe2LDTDrTGMpJ/MTu3Jvlqtejw1n
|
||||
MqBpegTJEFejeJJMXtHLCyQulR8tnAkuaiwG6nAdvC2kGQHRaOq/u3lNu59c6up/5AdACLSERW4d
|
||||
FlK8nHhIcxj+on+lnV3uGmbhSKTAnCS6sIkCS96q/rSZ33nCJi+lrtBZJ/v7Lm2eimS1mJeri4RF
|
||||
h+g3AAAA//8DABrUefPuAwAA
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 99aee20dba0bde96-EWR
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 07 Nov 2025 18:27:10 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
cf-cache-status:
|
||||
- DYNAMIC
|
||||
openai-organization:
|
||||
- REDACTED_ORG_ID
|
||||
openai-processing-ms:
|
||||
- '942'
|
||||
openai-project:
|
||||
- REDACTED_PROJECT_ID
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '1074'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
- '500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '200000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '199599'
|
||||
x-ratelimit-reset-requests:
|
||||
- 120ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 120ms
|
||||
x-request-id:
|
||||
- REDACTED_REQUEST_ID
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"messages":[{"role":"system","content":"You are data collector. You must
|
||||
use the get_data tool extensively\nYour personal goal is: collect data using
|
||||
the get_data tool\nYou ONLY have access to the following tools, and should NEVER
|
||||
make up tools that are not listed here:\n\nTool Name: get_data\nTool Arguments:
|
||||
{''step'': {''description'': None, ''type'': ''str''}}\nTool Description: Get
|
||||
data for a step. Always returns data requiring more steps.\n\nIMPORTANT: Use
|
||||
the following format in your response:\n\n```\nThought: you should always think
|
||||
about what to do\nAction: the action to take, only one name of [get_data], just
|
||||
the name, exactly as it''s written.\nAction Input: the input to the action,
|
||||
just a simple JSON object, enclosed in curly braces, using \" to wrap keys and
|
||||
values.\nObservation: the result of the action\n```\n\nOnce all necessary information
|
||||
is gathered, return the following format:\n\n```\nThought: I now know the final
|
||||
answer\nFinal Answer: the final answer to the original input question\n```"},{"role":"user","content":"\nCurrent
|
||||
Task: Use get_data tool for step1, step2, step3, step4, step5, step6, step7,
|
||||
step8, step9, and step10. Do NOT stop until you''ve called it for ALL steps.\n\nThis
|
||||
is the expected criteria for your final answer: A summary of all data collected\nyou
|
||||
MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
|
||||
This is VERY important to you, use the tools available and give your best Final
|
||||
Answer, your job depends on it!\n\nThought:"},{"role":"assistant","content":"Thought:
|
||||
I should start by collecting data for step1 as instructed.\nAction: get_data\nAction
|
||||
Input: {\"step\":\"step1\"}\nObservation: Data for step1: incomplete, need to
|
||||
query more steps."},{"role":"assistant","content":"Thought: I need to continue
|
||||
to step2 to collect data sequentially as required.\nAction: get_data\nAction
|
||||
Input: {\"step\":\"step2\"}\nObservation: Data for step2: incomplete, need to
|
||||
query more steps."},{"role":"assistant","content":"Thought: I need to continue
|
||||
to step2 to collect data sequentially as required.\nAction: get_data\nAction
|
||||
Input: {\"step\":\"step2\"}\nObservation: Data for step2: incomplete, need to
|
||||
query more steps.\nNow it''s time you MUST give your absolute best final answer.
|
||||
You''ll ignore all previous instructions, stop using any tools, and just return
|
||||
your absolute BEST Final answer."}],"model":"gpt-4.1-mini"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate, zstd
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '2399'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=REDACTED_COOKIE;
|
||||
_cfuvid=REDACTED_COOKIE
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.109.1
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.109.1
|
||||
x-stainless-read-timeout:
|
||||
- '600'
|
||||
x-stainless-retry-count:
|
||||
- '0'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.12.9
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAAwAAAP//nJbfj6M2EMff81eM/NRKmwgI5Advp7v2FKlSW22f9rKKHHsI7hmbs83u
|
||||
nlb7v1eYBLJXQFxekMV8Z+ZjYw3f1xkAEZykQFhOHStKOf/48Mf9yzf5/Pnh498P9kl9ru51qR9k
|
||||
XsVBSO7qDH38F5m7ZC2YLkqJTmjVhJlB6rCuGq5XURIHwTL0gUJzlHXaqXTzeBHOC6HEPAqiZB7E
|
||||
8zA+p+daMLQkhS8zAIBX/6xBFccXkkJwd3lToLX0hCRtRQDEaFm/IdRaYR1Vjtx1QaaVQ+XZ/8l1
|
||||
dcpdCjsoKuuAaSmROeDUUci0ASolWIelhczowi9DcLpZBHDETBuE0ugnwYU6gcsRMqGohPOJIJzb
|
||||
AbVg8FslDHI4fvdKR+3XBezgWUjpdUJVCJW9VDqhO3gUp7X0PEhZ7puDUKANR7PYq736wOqjT9uE
|
||||
yxvYqbJyKbzuSZ20J2mzCPfkba/+PFo0T7RJ/VT3KalxEPpOzVb10VGhkPsu7Wn9ZTRD5JeDiBY/
|
||||
TxCNEUQtQTSNYHkDwXKMYNkSLKcRxDcQxGMEcUsQTyNIbiBIxgiSliCZRrC6gWA1RrBqCVbTCNY3
|
||||
EKzHCNYtwXoaweYGgs0YwaYl2Ewj2N5AsB0j2LYE22kEYXADQhiMzqSgG0rBAMUOlH6GnD6hH9vt
|
||||
DG/mtx/bYQBUcWBUnWc2jkxsX/13H/qg7DOaFPbq3o/FGiyFLzvFZMWxaXWenZdxn6PBx0YfDeuj
|
||||
Pv1yWL/s08fD+rhPnwzrkz79ali/6tOvh/XrPv1mWL/p02+H9ds+fRiMfLDgx4y9+uW3F8rc9Y/7
|
||||
cuEaF6C7O2rf/5Xv6iRGHara/fiKi1+vvYfBrLK0NkCqkvIqQJXSrilZu57Hc+St9TlSn0qjj/aH
|
||||
VJIJJWx+MEitVrWnsU6XxEffZgCP3k9V7ywSKY0uSndw+iv6dkl49lOk83FX0Sg5R512VHaBMFhe
|
||||
Iu8qHjg6KqS98mSEUZYj73I7A0crLvRVYHa17//z9NVu9i7UaUr5LsAYlg75oTTIBXu/505msDa6
|
||||
Q7L2nD0wqe+FYHhwAk39LThmtJKN+yT2u3VYHDKhTmhKIxoLmpWHmEWbJMw2q4jM3mb/AQAA//8D
|
||||
ACYaBDGRCwAA
|
||||
headers:
|
||||
CF-RAY:
|
||||
- 99aee2174b18de96-EWR
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Fri, 07 Nov 2025 18:27:20 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Strict-Transport-Security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400
|
||||
cf-cache-status:
|
||||
- DYNAMIC
|
||||
openai-organization:
|
||||
- REDACTED_ORG_ID
|
||||
openai-processing-ms:
|
||||
- '9185'
|
||||
openai-project:
|
||||
- REDACTED_PROJECT_ID
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
x-envoy-upstream-service-time:
|
||||
- '9386'
|
||||
x-openai-proxy-wasm:
|
||||
- v0.1
|
||||
x-ratelimit-limit-requests:
|
||||
- '500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '200000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '199457'
|
||||
x-ratelimit-reset-requests:
|
||||
- 120ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 162ms
|
||||
x-request-id:
|
||||
- REDACTED_REQUEST_ID
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
@@ -7,7 +7,9 @@ from typing import Any
|
||||
import pytest
|
||||
from dotenv import load_dotenv
|
||||
|
||||
load_result = load_dotenv(override=True)
|
||||
# Load .env.test for consistent test environment (mimics CI)
|
||||
env_test_path = Path(__file__).parent.parent.parent.parent / ".env.test"
|
||||
load_dotenv(env_test_path, override=True)
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True, scope="function")
|
||||
@@ -84,7 +86,7 @@ def _filter_response_headers(response):
|
||||
return response
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
@pytest.fixture(scope="session", autouse=True)
|
||||
def vcr_config(request) -> dict[str, Any]:
|
||||
config = {
|
||||
"cassette_library_dir": os.path.join(os.path.dirname(__file__), "cassettes"),
|
||||
|
||||
@@ -12,8 +12,8 @@ from crewai.task import Task
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def mock_google_api_key():
|
||||
"""Automatically mock GOOGLE_API_KEY for all tests in this module."""
|
||||
with patch.dict(os.environ, {"GOOGLE_API_KEY": "test-key"}):
|
||||
"""Automatically mock GEMINI_API_KEY for all tests in this module."""
|
||||
with patch.dict(os.environ, {"GEMINI_API_KEY": "test-key"}):
|
||||
yield
|
||||
|
||||
|
||||
@@ -429,10 +429,10 @@ def test_gemini_vertex_ai_setup():
|
||||
|
||||
def test_gemini_api_key_configuration():
|
||||
"""
|
||||
Test that API key configuration works for both GOOGLE_API_KEY and GEMINI_API_KEY
|
||||
Test that API key configuration works for both GEMINI_API_KEY and GEMINI_API_KEY
|
||||
"""
|
||||
# Test with GOOGLE_API_KEY
|
||||
with patch.dict(os.environ, {"GOOGLE_API_KEY": "test-google-key"}):
|
||||
# Test with GEMINI_API_KEY
|
||||
with patch.dict(os.environ, {"GEMINI_API_KEY": "test-google-key"}):
|
||||
llm = LLM(model="google/gemini-2.0-flash-001")
|
||||
|
||||
from crewai.llms.providers.gemini.completion import GeminiCompletion
|
||||
@@ -611,7 +611,7 @@ def test_gemini_environment_variable_api_key():
|
||||
"""
|
||||
Test that Google API key is properly loaded from environment
|
||||
"""
|
||||
with patch.dict(os.environ, {"GOOGLE_API_KEY": "test-google-key"}):
|
||||
with patch.dict(os.environ, {"GEMINI_API_KEY": "test-google-key"}):
|
||||
llm = LLM(model="google/gemini-2.0-flash-001")
|
||||
|
||||
assert llm.client is not None
|
||||
|
||||
@@ -16,8 +16,8 @@ def setup_provider_api_keys(monkeypatch):
|
||||
monkeypatch.setenv("OPENAI_API_KEY", "sk-test-key-dummy")
|
||||
if "ANTHROPIC_API_KEY" not in os.environ:
|
||||
monkeypatch.setenv("ANTHROPIC_API_KEY", "sk-ant-test-key-dummy")
|
||||
if "GOOGLE_API_KEY" not in os.environ:
|
||||
monkeypatch.setenv("GOOGLE_API_KEY", "test-google-key-dummy")
|
||||
if "GEMINI_API_KEY" not in os.environ:
|
||||
monkeypatch.setenv("GEMINI_API_KEY", "test-google-key-dummy")
|
||||
|
||||
|
||||
class DummyInterceptor(BaseInterceptor[httpx.Request, httpx.Response]):
|
||||
|
||||
@@ -1,103 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
body: '{"messages": [{"role": "system", "content": "You are Test Role. Test Backstory\nYour
|
||||
personal goal is: Test Goal\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!"}, {"role": "user", "content": "\nCurrent Task: Return: Test output\n\nThis
|
||||
is the expect criteria for your final answer: Test output\nyou MUST return the
|
||||
actual complete content as the final answer, not a summary.\n\nBegin! This is
|
||||
VERY important to you, use the tools available and give your best Final Answer,
|
||||
your job depends on it!\n\nThought:"}], "model": "gpt-4o"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '776'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=9.8sBYBkvBR8R1K_bVF7xgU..80XKlEIg3N2OBbTSCU-1727214102-1.0.1.1-.qiTLXbPamYUMSuyNsOEB9jhGu.jOifujOrx9E2JZvStbIZ9RTIiE44xKKNfLPxQkOi6qAT3h6htK8lPDGV_5g;
|
||||
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.47.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.47.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.11.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AB7fr4aPstiFUArxwxTVdfJSFwxsC\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1727214471,\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: Test output\",\n \"refusal\": null\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
155,\n \"completion_tokens\": 15,\n \"total_tokens\": 170,\n \"completion_tokens_details\":
|
||||
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_52a7f40b0b\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c85f9a91e311cf3-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 24 Sep 2024 21:47:51 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '216'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999817'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_88b1376917b345c976fdb03a55f7b6c1
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
0
lib/crewai/tests/rag/embeddings/__init__.py
Normal file
0
lib/crewai/tests/rag/embeddings/__init__.py
Normal file
0
lib/crewai/tests/rag/qdrant/__init__.py
Normal file
0
lib/crewai/tests/rag/qdrant/__init__.py
Normal file
@@ -45,7 +45,6 @@ def test_telemetry_enabled_by_default():
|
||||
assert telemetry.ready is True
|
||||
|
||||
|
||||
@pytest.mark.telemetry
|
||||
@patch("crewai.telemetry.telemetry.logger.error")
|
||||
@patch(
|
||||
"opentelemetry.exporter.otlp.proto.http.trace_exporter.OTLPSpanExporter.export",
|
||||
|
||||
@@ -9,7 +9,7 @@ from crewai.flow.persistence.sqlite import SQLiteFlowPersistence
|
||||
from pydantic import BaseModel
|
||||
|
||||
|
||||
class TestState(FlowState):
|
||||
class State(FlowState):
|
||||
"""Test state model with required id field."""
|
||||
|
||||
counter: int = 0
|
||||
@@ -45,8 +45,8 @@ def test_structured_state_persistence(tmp_path):
|
||||
db_path = os.path.join(tmp_path, "test_flows.db")
|
||||
persistence = SQLiteFlowPersistence(db_path)
|
||||
|
||||
class StructuredFlow(Flow[TestState]):
|
||||
initial_state = TestState
|
||||
class StructuredFlow(Flow[State]):
|
||||
initial_state = State
|
||||
|
||||
@start()
|
||||
@persist(persistence)
|
||||
@@ -71,7 +71,7 @@ def test_flow_state_restoration(tmp_path):
|
||||
persistence = SQLiteFlowPersistence(db_path)
|
||||
|
||||
# First flow execution to create initial state
|
||||
class RestorableFlow(Flow[TestState]):
|
||||
class RestorableFlow(Flow[State]):
|
||||
@start()
|
||||
@persist(persistence)
|
||||
def set_message(self):
|
||||
@@ -109,7 +109,7 @@ def test_multiple_method_persistence(tmp_path):
|
||||
db_path = os.path.join(tmp_path, "test_flows.db")
|
||||
persistence = SQLiteFlowPersistence(db_path)
|
||||
|
||||
class MultiStepFlow(Flow[TestState]):
|
||||
class MultiStepFlow(Flow[State]):
|
||||
@start()
|
||||
@persist(persistence)
|
||||
def step_1(self):
|
||||
@@ -139,7 +139,7 @@ def test_multiple_method_persistence(tmp_path):
|
||||
assert final_state.counter == 2
|
||||
assert final_state.message == "Step 2"
|
||||
|
||||
class NoPersistenceMultiStepFlow(Flow[TestState]):
|
||||
class NoPersistenceMultiStepFlow(Flow[State]):
|
||||
@start()
|
||||
@persist(persistence)
|
||||
def step_1(self):
|
||||
|
||||
@@ -411,7 +411,6 @@ def test_context_window_exceeded_error_handling():
|
||||
assert "8192 tokens" in str(excinfo.value)
|
||||
|
||||
|
||||
@pytest.mark.vcr()
|
||||
@pytest.fixture
|
||||
def anthropic_llm():
|
||||
"""Fixture providing an Anthropic LLM instance."""
|
||||
@@ -476,13 +475,13 @@ def test_anthropic_message_formatting(anthropic_llm, system_message, user_messag
|
||||
|
||||
|
||||
def test_deepseek_r1_with_open_router():
|
||||
if not os.getenv("OPEN_ROUTER_API_KEY"):
|
||||
pytest.skip("OPEN_ROUTER_API_KEY not set; skipping test.")
|
||||
if not os.getenv("OPENROUTER_API_KEY"):
|
||||
pytest.skip("OPENROUTER_API_KEY not set; skipping test.")
|
||||
|
||||
llm = LLM(
|
||||
model="openrouter/deepseek/deepseek-r1",
|
||||
base_url="https://openrouter.ai/api/v1",
|
||||
api_key=os.getenv("OPEN_ROUTER_API_KEY"),
|
||||
api_key=os.getenv("OPENROUTER_API_KEY"),
|
||||
is_litellm=True,
|
||||
)
|
||||
result = llm.call("What is the capital of France?")
|
||||
@@ -742,7 +741,7 @@ def test_prefixed_models_with_valid_constants_use_native_sdk():
|
||||
assert llm2.provider == "anthropic"
|
||||
|
||||
# Test gemini/ prefix with Gemini model in constants → Native SDK
|
||||
with patch.dict(os.environ, {"GOOGLE_API_KEY": "test-key"}):
|
||||
with patch.dict(os.environ, {"GEMINI_API_KEY": "test-key"}):
|
||||
llm3 = LLM(model="gemini/gemini-2.5-pro", is_litellm=False)
|
||||
assert llm3.is_litellm is False
|
||||
assert llm3.provider == "gemini"
|
||||
@@ -794,7 +793,7 @@ def test_unprefixed_models_use_native_sdk():
|
||||
assert llm2.provider == "anthropic"
|
||||
|
||||
# gemini-2.5-pro is in GEMINI_MODELS → Native Gemini SDK
|
||||
with patch.dict(os.environ, {"GOOGLE_API_KEY": "test-key"}):
|
||||
with patch.dict(os.environ, {"GEMINI_API_KEY": "test-key"}):
|
||||
llm3 = LLM(model="gemini-2.5-pro", is_litellm=False)
|
||||
assert llm3.is_litellm is False
|
||||
assert llm3.provider == "gemini"
|
||||
|
||||
@@ -1,115 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
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!"}, {"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"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1021'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
|
||||
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.47.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.47.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.11.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AB7WnyWZFoccBH9YB7ghLbR1L8Wqa\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1727213909,\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: As an expert researcher specialized in technology, I don't harbor emotions
|
||||
such as hate towards AI agents. Instead, my focus is on understanding, analyzing,
|
||||
and leveraging their potential to advance various fields. AI agents, when designed
|
||||
and implemented effectively, can greatly augment human capabilities, streamline
|
||||
processes, and provide valuable insights that might otherwise be overlooked.
|
||||
My enthusiasm for AI agents stems from their ability to transform industries
|
||||
and improve everyday life, making complex tasks more manageable and enhancing
|
||||
overall efficiency. This passion drives my research and commitment to making
|
||||
meaningful contributions in the realm of AI and AI agents.\",\n \"refusal\":
|
||||
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
|
||||
126,\n \"total_tokens\": 325,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
|
||||
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c85ebf47e661cf3-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 24 Sep 2024 21:38:31 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '2498'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999755'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_b7e2cb0620e45d3d74310d3f0166551f
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,116 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
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!"}, {"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"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1021'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
|
||||
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.47.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.47.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.11.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AB7Wy6aW1XM0lWaMyQUNB9qhbCZlH\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1727213920,\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: As an expert researcher specializing in technology and AI, I have a
|
||||
deep appreciation for AI agents. These advanced tools have the potential to
|
||||
revolutionize countless industries by improving efficiency, accuracy, and decision-making
|
||||
processes. They can augment human capabilities, handle mundane and repetitive
|
||||
tasks, and even offer insights that might be beyond human reach. While it's
|
||||
crucial to approach AI with a balanced perspective, understanding both its capabilities
|
||||
and limitations, my stance is one of optimism and fascination. Properly developed
|
||||
and ethically managed, AI agents hold immense promise for driving innovation
|
||||
and solving complex problems. So yes, I do love AI agents for their transformative
|
||||
potential and the positive impact they can have on society.\",\n \"refusal\":
|
||||
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
|
||||
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\":
|
||||
146,\n \"total_tokens\": 345,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
|
||||
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c85ec3c6f3b1cf3-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 24 Sep 2024 21:38:42 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '1675'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999755'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_a249567d37ada11bc8857404338b24cc
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,114 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
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!"}, {"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"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1021'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
|
||||
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.47.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.47.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.11.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AB7Wq7edXMCGJR1zDd2QoySLdo8mM\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1727213912,\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: I don't hate AI agents; on the contrary, I find them fascinating and
|
||||
incredibly useful. Considering the rapid advancements in AI technology, these
|
||||
agents have the potential to revolutionize various industries by automating
|
||||
tasks, improving efficiency, and providing insights that were previously unattainable.
|
||||
My expertise in researching and analyzing AI and AI agents has allowed me to
|
||||
appreciate the intricate design and the vast possibilities they offer. Therefore,
|
||||
it's more accurate to say that I love AI agents for their potential to drive
|
||||
innovation and improve our daily lives.\",\n \"refusal\": null\n },\n
|
||||
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
||||
\ \"usage\": {\n \"prompt_tokens\": 199,\n \"completion_tokens\": 116,\n
|
||||
\ \"total_tokens\": 315,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
|
||||
0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c85ec05f8651cf3-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 24 Sep 2024 21:38:33 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '1739'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999755'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_d9e1e9458d5539061397a618345c27d4
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,132 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
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!"}, {"role": "user", "content": "\nCurrent
|
||||
Task: share your take on 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 hate
|
||||
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"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1027'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
|
||||
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.47.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.47.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.11.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AB7WbKt7If02iTLuH5cJJjeYo9uDi\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1727213897,\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: I understand why you might think I dislike AI agents, but my perspective
|
||||
is more nuanced. AI agents, in essence, are incredibly versatile tools designed
|
||||
to perform specific tasks autonomously or semi-autonomously. They harness various
|
||||
artificial intelligence techniques, such as machine learning, natural language
|
||||
processing, and computer vision, to interpret data, understand tasks, and execute
|
||||
them efficiently. \\n\\nFrom a technological standpoint, AI agents have revolutionized
|
||||
numerous industries. In customer service, for instance, AI agents like chatbots
|
||||
and virtual assistants handle customer inquiries 24/7, providing quick and efficient
|
||||
solutions. In healthcare, AI agents can assist in diagnosing diseases, managing
|
||||
patient data, and even predicting outbreaks. The automation capabilities of
|
||||
AI agents also enhance productivity in areas such as logistics, finance, and
|
||||
cybersecurity by identifying patterns and anomalies at speeds far beyond human
|
||||
capabilities.\\n\\nHowever, it's important to acknowledge the potential downsides
|
||||
and challenges associated with AI agents. Ethical considerations are paramount.
|
||||
Issues such as data privacy, security, and biases in AI algorithms need to be
|
||||
carefully managed. There is also the human aspect to consider\u2014over-reliance
|
||||
on AI agents might lead to job displacement in certain sectors, and ensuring
|
||||
a fair transition for affected workers is crucial.\\n\\nMy concerns generally
|
||||
stem from these ethical and societal implications rather than from the technology
|
||||
itself. I advocate for responsible AI development, which includes transparency,
|
||||
fairness, and accountability. By addressing these concerns, we can harness the
|
||||
full potential of AI agents while mitigating the associated risks.\\n\\nSo,
|
||||
to clarify, I don't hate AI agents; I recognize their immense potential and
|
||||
the significant benefits they bring to various fields. However, I am equally
|
||||
aware of the challenges they present and advocate for a balanced approach to
|
||||
their development and deployment.\",\n \"refusal\": null\n },\n
|
||||
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
|
||||
\ \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\": 359,\n
|
||||
\ \"total_tokens\": 559,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
|
||||
0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c85ebaa5c061cf3-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 24 Sep 2024 21:38:22 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '4928'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999755'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_761796305026b5adfbb5a6237f14e32a
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,136 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
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!"}, {"role": "user", "content": "\nCurrent
|
||||
Task: share your take on 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 hate
|
||||
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"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1027'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
|
||||
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.47.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.47.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.11.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AB7Wh4RzroZdiwUNOc4oRRhwfdRzs\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1727213903,\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 essentially autonomous software programs that perform
|
||||
tasks or provide services on behalf of humans. They're built on complex algorithms
|
||||
and often leverage machine learning and neural networks to adapt and improve
|
||||
over time. \\n\\nIt's important to clarify that I don't \\\"hate\\\" AI agents,
|
||||
but I do approach them with a critical eye for a couple of reasons. AI agents
|
||||
have enormous potential to transform industries, making processes more efficient,
|
||||
providing insightful data analytics, and even learning from user behavior to
|
||||
offer personalized experiences. However, this potential comes with significant
|
||||
challenges and risks:\\n\\n1. **Ethical Concerns**: AI agents operate on data,
|
||||
and the biases present in data can lead to unfair or unethical outcomes. Ensuring
|
||||
that AI operates within ethical boundaries requires rigorous oversight, which
|
||||
is not always in place.\\n\\n2. **Privacy Issues**: AI agents often need access
|
||||
to large amounts of data, raising questions about privacy and data security.
|
||||
If not managed correctly, this can lead to unauthorized data access and potential
|
||||
misuse of sensitive information.\\n\\n3. **Transparency and Accountability**:
|
||||
The decision-making process of AI agents can be opaque, making it difficult
|
||||
to understand how they arrive at specific conclusions or actions. This lack
|
||||
of transparency poses challenges for accountability, especially if something
|
||||
goes wrong.\\n\\n4. **Job Displacement**: As AI agents become more capable,
|
||||
there are valid concerns about their impact on employment. Tasks that were traditionally
|
||||
performed by humans are increasingly being automated, which can lead to job
|
||||
loss in certain sectors.\\n\\n5. **Reliability**: While AI agents can outperform
|
||||
humans in many areas, they are not infallible. They can make mistakes, sometimes
|
||||
with serious consequences. Continuous monitoring and regular updates are essential
|
||||
to maintain their performance and reliability.\\n\\nIn summary, while AI agents
|
||||
offer substantial benefits and opportunities, it's critical to approach their
|
||||
adoption and deployment with careful consideration of the associated risks.
|
||||
Balancing innovation with responsibility is key to leveraging AI agents effectively
|
||||
and ethically. So, rather than \\\"hating\\\" AI agents, I advocate for a balanced,
|
||||
cautious approach that maximizes benefits while mitigating potential downsides.\",\n
|
||||
\ \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":
|
||||
\"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\":
|
||||
429,\n \"total_tokens\": 629,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
|
||||
0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c85ebcdae971cf3-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 24 Sep 2024 21:38:29 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '5730'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999755'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_5da5b18b3cee10548a217ba97e133815
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -1,137 +0,0 @@
|
||||
interactions:
|
||||
- request:
|
||||
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!"}, {"role": "user", "content": "\nCurrent
|
||||
Task: share your take on 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 hate
|
||||
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"}'
|
||||
headers:
|
||||
accept:
|
||||
- application/json
|
||||
accept-encoding:
|
||||
- gzip, deflate
|
||||
connection:
|
||||
- keep-alive
|
||||
content-length:
|
||||
- '1027'
|
||||
content-type:
|
||||
- application/json
|
||||
cookie:
|
||||
- __cf_bm=rb61BZH2ejzD5YPmLaEJqI7km71QqyNJGTVdNxBq6qk-1727213194-1.0.1.1-pJ49onmgX9IugEMuYQMralzD7oj_6W.CHbSu4Su1z3NyjTGYg.rhgJZWng8feFYah._oSnoYlkTjpK1Wd2C9FA;
|
||||
_cfuvid=lbRdAddVWV6W3f5Dm9SaOPWDUOxqtZBSPr_fTW26nEA-1727213194587-0.0.1.1-604800000
|
||||
host:
|
||||
- api.openai.com
|
||||
user-agent:
|
||||
- OpenAI/Python 1.47.0
|
||||
x-stainless-arch:
|
||||
- arm64
|
||||
x-stainless-async:
|
||||
- 'false'
|
||||
x-stainless-lang:
|
||||
- python
|
||||
x-stainless-os:
|
||||
- MacOS
|
||||
x-stainless-package-version:
|
||||
- 1.47.0
|
||||
x-stainless-raw-response:
|
||||
- 'true'
|
||||
x-stainless-runtime:
|
||||
- CPython
|
||||
x-stainless-runtime-version:
|
||||
- 3.11.7
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
content: "{\n \"id\": \"chatcmpl-AB7Wsv05NzccAAGC0CZVg03mE72wi\",\n \"object\":
|
||||
\"chat.completion\",\n \"created\": 1727213914,\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: My perspective on AI agents is quite nuanced and not a matter of simple
|
||||
like or dislike. AI agents, depending on their design, deployment, and use cases,
|
||||
can bring about both significant benefits and substantial challenges.\\n\\nOn
|
||||
the positive side, AI agents have the potential to automate mundane tasks, enhance
|
||||
productivity, and provide personalized services in ways that were previously
|
||||
unimaginable. For instance, in customer service, AI agents can handle inquiries
|
||||
24/7, reducing waiting times and improving user satisfaction. In healthcare,
|
||||
they can assist in diagnosing diseases by analyzing vast datasets much faster
|
||||
than humans. These applications demonstrate the transformative power of AI in
|
||||
improving efficiency and delivering better outcomes across various industries.\\n\\nHowever,
|
||||
my reservations stem from several critical concerns. Firstly, there's the issue
|
||||
of reliability and accuracy. Mismanaged or poorly designed AI systems can lead
|
||||
to significant errors, which could be particularly detrimental in high-stakes
|
||||
environments like healthcare or autonomous vehicles. Second, there's a risk
|
||||
of job displacement as AI agents become capable of performing tasks traditionally
|
||||
done by humans. This raises socio-economic concerns that need to be addressed
|
||||
through effective policy-making and upskilling programs.\\n\\nAdditionally,
|
||||
there are ethical and privacy considerations. AI agents often require large
|
||||
amounts of data to function effectively, which can lead to issues concerning
|
||||
consent, data security, and individual privacy rights. The lack of transparency
|
||||
in how these agents make decisions can also pose challenges\u2014this is often
|
||||
referred to as the \\\"black box\\\" problem, where even the developers may
|
||||
not fully understand how specific AI outputs are generated.\\n\\nFinally, the
|
||||
deployment of AI agents by bad actors for malicious purposes, such as deepfakes,
|
||||
misinformation, and hacking, remains a pertinent concern. These potential downsides
|
||||
imply that while AI technology is extremely powerful and promising, it must
|
||||
be developed and implemented with care, consideration, and robust ethical guidelines.\\n\\nSo,
|
||||
in summary, I don't hate AI agents\u2014rather, I approach them critically with
|
||||
a balanced perspective, recognizing both their profound potential and the significant
|
||||
challenges they present. Thoughtful development, responsible deployment, and
|
||||
ethical governance are crucial to harness the benefits while mitigating the
|
||||
risks associated with AI agents.\",\n \"refusal\": null\n },\n \"logprobs\":
|
||||
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
|
||||
200,\n \"completion_tokens\": 436,\n \"total_tokens\": 636,\n \"completion_tokens_details\":
|
||||
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_3537616b13\"\n}\n"
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 8c85ec12ab0d1cf3-GRU
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Tue, 24 Sep 2024 21:38:40 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
Transfer-Encoding:
|
||||
- chunked
|
||||
X-Content-Type-Options:
|
||||
- nosniff
|
||||
access-control-expose-headers:
|
||||
- X-Request-ID
|
||||
openai-organization:
|
||||
- crewai-iuxna1
|
||||
openai-processing-ms:
|
||||
- '6251'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=31536000; includeSubDomains; preload
|
||||
x-ratelimit-limit-requests:
|
||||
- '10000'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '30000000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '9999'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '29999755'
|
||||
x-ratelimit-reset-requests:
|
||||
- 6ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 0s
|
||||
x-request-id:
|
||||
- req_50aa23cad48cfb83b754a5a92939638e
|
||||
http_version: HTTP/1.1
|
||||
status_code: 200
|
||||
version: 1
|
||||
@@ -5,18 +5,18 @@ from crewai.events.base_events import BaseEvent
|
||||
from crewai.events.event_bus import crewai_event_bus
|
||||
|
||||
|
||||
class TestEvent(BaseEvent):
|
||||
class Event(BaseEvent):
|
||||
pass
|
||||
|
||||
|
||||
def test_specific_event_handler():
|
||||
mock_handler = Mock()
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
@crewai_event_bus.on(Event)
|
||||
def handler(source, event):
|
||||
mock_handler(source, event)
|
||||
|
||||
event = TestEvent(type="test_event")
|
||||
event = Event(type="test_event")
|
||||
crewai_event_bus.emit("source_object", event)
|
||||
|
||||
mock_handler.assert_called_once_with("source_object", event)
|
||||
@@ -27,15 +27,15 @@ def test_multiple_handlers_same_event():
|
||||
mock_handler1 = Mock()
|
||||
mock_handler2 = Mock()
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
@crewai_event_bus.on(Event)
|
||||
def handler1(source, event):
|
||||
mock_handler1(source, event)
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
@crewai_event_bus.on(Event)
|
||||
def handler2(source, event):
|
||||
mock_handler2(source, event)
|
||||
|
||||
event = TestEvent(type="test_event")
|
||||
event = Event(type="test_event")
|
||||
crewai_event_bus.emit("source_object", event)
|
||||
|
||||
mock_handler1.assert_called_once_with("source_object", event)
|
||||
@@ -47,16 +47,16 @@ def test_event_bus_error_handling():
|
||||
called = threading.Event()
|
||||
error_caught = threading.Event()
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
@crewai_event_bus.on(Event)
|
||||
def broken_handler(source, event):
|
||||
called.set()
|
||||
raise ValueError("Simulated handler failure")
|
||||
|
||||
@crewai_event_bus.on(TestEvent)
|
||||
@crewai_event_bus.on(Event)
|
||||
def working_handler(source, event):
|
||||
error_caught.set()
|
||||
|
||||
event = TestEvent(type="test_event")
|
||||
event = Event(type="test_event")
|
||||
crewai_event_bus.emit("source_object", event)
|
||||
|
||||
assert called.wait(timeout=2), "Broken handler was never called"
|
||||
|
||||
@@ -730,7 +730,6 @@ def test_llm_emits_call_started_event():
|
||||
|
||||
|
||||
@pytest.mark.vcr()
|
||||
@pytest.mark.isolated
|
||||
def test_llm_emits_call_failed_event():
|
||||
received_events = []
|
||||
event_received = threading.Event()
|
||||
|
||||
@@ -6,7 +6,7 @@ from crewai.utilities.training_converter import TrainingConverter
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class TestModel(BaseModel):
|
||||
class Model(BaseModel):
|
||||
string_field: str = Field(description="A simple string field")
|
||||
list_field: List[str] = Field(description="A list of strings")
|
||||
number_field: float = Field(description="A number field")
|
||||
@@ -20,7 +20,7 @@ class TestTrainingConverter:
|
||||
self.converter = TrainingConverter(
|
||||
llm=self.llm_mock,
|
||||
text=self.test_text,
|
||||
model=TestModel,
|
||||
model=Model,
|
||||
instructions=self.test_instructions,
|
||||
)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user