andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-07 07:08:31 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
206ad7c954d00998ca6c4fc39290209c6c2b66d2
crewAI/tests/cassettes/test_task_tools_override_agent_tools.yaml
João Moura 82647358b2 Adding Multimodal Abilities to Crew (#1805) 
* initial fix on delegation tools

* fixing tests for delegations and coding

* Refactor prepare tool and adding initial add images logic

* supporting image tool

* fixing linter

* fix linter

* Making sure multimodal feature support i18n

* fix linter and types

* mixxing translations

* fix types and linter

* Revert "fixing linter"

This reverts commit 2eda5fdeed.

* fix linters

* test

* fix

* fix

* fix linter

* fix

* ignore

* type improvements
2024-12-27 17:03:35 -03:00

570 lines
34 KiB
YAML
Raw Blame History

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: Test Tool\nTool Arguments: {''query'': {''description'': ''Query to process'',
''type'': ''str''}}\nTool Description: A test tool that just returns the input\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Test Tool], just the name, exactly as
it''s written.\nAction Input: the input to the action, just a simple python
dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question"}, {"role": "user", "content": "\nCurrent Task: Write a test
task\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-mini", "stop":
["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '1536'
content-type:
- application/json
cookie:
- _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhQfznhDMtsr58XvTuRDZoB1kxwfK\",\n \"object\":
\"chat.completion\",\n \"created\": 1734914011,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I need to come up with a suitable test
task that meets the criteria provided. I will focus on outlining a clear and
effective test task related to AI and AI agents.\\n\\nAction: Test Tool\\nAction
Input: {\\\"query\\\": \\\"Create a test task that involves evaluating the performance
of an AI agent in a given scenario, including criteria for success, tools required,
and process for assessment.\\\"}\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
298,\n \"completion_tokens\": 78,\n \"total_tokens\": 376,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_d02d531b47\"\n}\n"
headers:
CF-RAY:
- 8f6442b868fda486-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Dec 2024 00:33:32 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=i6jvNjhsDne300GPAeEmyiJJKYqy7OPuamFG_kht3KE-1734914012-1.0.1.1-tCeVANAF521vkXpBdgYw.ov.fYUr6t5QC4LG_DugWyzu4C60Pi2CruTVniUgfCvkcu6rdHA5DwnaEZf2jFaRCQ;
path=/; expires=Mon, 23-Dec-24 01:03:32 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
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:
- crewai-iuxna1
openai-processing-ms:
- '1400'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999642'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_c3e50e9ca9dc22de5572692e1a9c0f16
http_version: HTTP/1.1
status_code: 200
- request:
body: !!binary |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headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '14771'
Content-Type:
- application/x-protobuf
User-Agent:
- OTel-OTLP-Exporter-Python/1.27.0
method: POST
uri: https://telemetry.crewai.com:4319/v1/traces
response:
body:
string: "\n\0"
headers:
Content-Length:
- '2'
Content-Type:
- application/x-protobuf
Date:
- Mon, 23 Dec 2024 00:33:37 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are Researcher. You''re
an expert researcher, specialized in technology, software engineering, AI and
startups. You work as a freelancer and is now working on doing research and
analysis for a new customer.\nYour personal goal is: Make the best research
and analysis on content about AI and AI agents\nYou ONLY have access to the
following tools, and should NEVER make up tools that are not listed here:\n\nTool
Name: Test Tool\nTool Arguments: {''query'': {''description'': ''Query to process'',
''type'': ''str''}}\nTool Description: A test tool that just returns the input\n\nUse
the following format:\n\nThought: you should always think about what to do\nAction:
the action to take, only one name of [Test Tool], just the name, exactly as
it''s written.\nAction Input: the input to the action, just a simple python
dictionary, enclosed in curly braces, using \" to wrap keys and values.\nObservation:
the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
I now know the final answer\nFinal Answer: the final answer to the original
input question"}, {"role": "user", "content": "\nCurrent Task: Write a test
task\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:"}, {"role": "assistant", "content":
"I need to come up with a suitable test task that meets the criteria provided.
I will focus on outlining a clear and effective test task related to AI and
AI agents.\n\nAction: Test Tool\nAction Input: {\"query\": \"Create a test task
that involves evaluating the performance of an AI agent in a given scenario,
including criteria for success, tools required, and process for assessment.\"}\nObservation:
Processed: Create a test task that involves evaluating the performance of an
AI agent in a given scenario, including criteria for success, tools required,
and process for assessment."}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '2160'
content-type:
- application/json
cookie:
- _cfuvid=2u_Xw.i716TDjD2vb2mvMyWxhA4q1MM1JvbrA8CNZpI-1734895557894-0.0.1.1-604800000;
__cf_bm=i6jvNjhsDne300GPAeEmyiJJKYqy7OPuamFG_kht3KE-1734914012-1.0.1.1-tCeVANAF521vkXpBdgYw.ov.fYUr6t5QC4LG_DugWyzu4C60Pi2CruTVniUgfCvkcu6rdHA5DwnaEZf2jFaRCQ
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.11.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AhQg0Cx1FED7gOwMpJUD5cQxVzQBK\",\n \"object\":
\"chat.completion\",\n \"created\": 1734914012,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I need to compile a complete
and detailed test task based on the processed input, ensuring it includes all
necessary components as per the expect criteria.\\n\\nFinal Answer: \\n### Test
Task: Evaluating the Performance of an AI Agent\\n\\n**Objective:** \\nTo evaluate
the performance of an AI agent in simulating conversation with users in a customer
service context.\\n\\n**Scenario:**\\nAn AI agent is tasked with handling customer
inquiries on an e-commerce platform. The agent must respond to questions about
product availability, order tracking, returns, and other common queries.\\n\\n**Criteria
for Success:**\\n1. **Accuracy:** The AI should provide correct information
in at least 90% of the interactions.\\n2. **Response Time:** The average response
time should be under 2 seconds.\\n3. **User Satisfaction:** Aim for a user satisfaction
score of 85% or higher based on follow-up surveys after interactions.\\n4. **Fallback
Rate:** The AI should not default to a human agent more than 10% of the time.\\n\\n**Tools
Required:**\\n- Chatbot development platform (e.g., Dialogflow, Rasa)\\n- Metrics
tracking software (to measure accuracy, response times, and user satisfaction)\\n-
Survey tool (e.g., Google Forms, SurveyMonkey) for feedback collection\\n\\n**Process
for Assessment:**\\n1. **Setup:** Deploy the AI agent on a testing environment
simulating real customer inquiries.\\n2. **Data Collection:** Run the test for
a predetermined period (e.g., one week) or until a set number of interactions
(e.g., 1000).\\n3. **Measurement:**\\n - Record the interactions and analyze
the accuracy of the AI's responses.\\n - Measure the average response time
for each interaction.\\n - Collect user satisfaction scores via surveys sent
after the interaction.\\n4. **Analysis:** Compile the data to see if the AI
met the success criteria. Identify strengths and weaknesses in the responses.\\n5.
**Review:** Share findings with the development team to strategize improvements.\\n\\nThis
detailed task will help assess the AI agent\u2019s capabilities and provide
insights for further enhancements.\",\n \"refusal\": null\n },\n
\ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n
\ \"usage\": {\n \"prompt_tokens\": 416,\n \"completion_tokens\": 422,\n
\ \"total_tokens\": 838,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_d02d531b47\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8f6442c2ba15a486-GRU
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Mon, 23 Dec 2024 00:33:39 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '6734'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999497'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7d8df8b840e279bd64280d161d854161
http_version: HTTP/1.1
status_code: 200
version: 1
Reference in New Issue View Git Blame Copy Permalink