fixing parser, tools and executor

This commit is contained in:
João Moura
2024-09-15 18:41:59 -03:00
parent c2795307f6
commit f216b0a78c
98 changed files with 21270 additions and 26437 deletions

View File

@@ -1,4 +1,40 @@
interactions:
- request:
body: !!binary |
CtACCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSpwIKEgoQY3Jld2FpLnRl
bGVtZXRyeRKQAgoQJBta1m+F+Iayh6b6Px/2+hIIh6bzKHFuQlgqDlRhc2sgRXhlY3V0aW9uMAE5
iKEYquxV9RdBIJbWqe1V9RdKLgoIY3Jld19rZXkSIgogYzMwNzYwMDkzMjY3NjE0NDRkNTdjNzFk
MWRhM2YyN2NKMQoHY3Jld19pZBImCiQzZjBhMmUzNy1mN2RhLTRlM2UtOTE4Ni0xNTk5Nzk1MTEz
NGFKLgoIdGFza19rZXkSIgogODBkN2JjZDQ5MDk5MjkwMDgzODMyZjBlOTgzMzgwZGZKMQoHdGFz
a19pZBImCiQ2M2ZjODA3OS05ZmEzLTRkN2ItOGVjYy1lODk5NzMxZTY3MzR6AhgBhQEAAQAA
headers:
Accept:
- '*/*'
Accept-Encoding:
- gzip, deflate
Connection:
- keep-alive
Content-Length:
- '339'
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:
- Sun, 15 Sep 2024 06:08:37 GMT
status:
code: 200
message: OK
- request:
body: '{"messages": [{"role": "system", "content": "You are researcher. You''re
an expert researcher, specialized in technology\nYour personal goal is: make
@@ -13,7 +49,7 @@ interactions:
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",
"stop": ["\nObservation"]}'
"stop": ["\nResult"]}'
headers:
accept:
- application/json
@@ -22,12 +58,12 @@ interactions:
connection:
- keep-alive
content-length:
- '1054'
- '1049'
content-type:
- application/json
cookie:
- __cf_bm=r6BNUnXat.26mviZiJYUf7Qj4ea5gbt_oPxyClKcVOE-1726214380-1.0.1.1-2S3G10sPdiG2syQSO8wKWXE7Nmdgt88imgakr81w9DemMH8mVDg0q6r9ANx6tM4_CPvgGQlMVstDhDRkIDwhzg;
_cfuvid=dp2yoCmGHVlURh_U78_UoIfnhcO5UhufnL5whkUSMTQ-1726214380689-0.0.1.1-604800000
- __cf_bm=J1VIPhfusyyXtwM.1L9zbe3jdnU7NVyHC3AWiKXO280-1726379702-1.0.1.1-LDa9RyXFli18t4ZEuVAENTChdNAkRtdWXRkRLbBHbCXdobugQ3T.arhMpSKwtnBRXKPcC4b66UA7BsSy1VXDHQ;
_cfuvid=Bz2zevKuFYZqnEFwqmqVHcRo5pT0fm0fTtc_6_VQs4g-1726379702153-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
@@ -51,43 +87,61 @@ interactions:
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-A6venRwoEA9IZPRKdsZuzO6034lVF\",\n \"object\":
\"chat.completion\",\n \"created\": 1726214965,\n \"model\": \"gpt-4o-2024-05-13\",\n
content: "{\n \"id\": \"chatcmpl-A7ciw2zOvP4hz1Yuurr1MIlPDrg8f\",\n \"object\":
\"chat.completion\",\n \"created\": 1726380514,\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 have been a transformative force in various industries, but
it's important to note that personal opinions about them can be nuanced. While
I wouldn\u2019t use the term \\\"hate,\\\" there are both positive aspects and
significant concerns that need to be considered. \\n\\nOn the positive side,
AI agents excel in performing repetitive tasks with high efficiency and accuracy,
enabling businesses to optimize their operations and reduce costs. They play
a vital role in areas such as customer service, where they can handle inquiries
around the clock without fatigue, and in data analysis, where they can process
vast amounts of information far quicker than a human could. Additionally, AI
agents can be trained to adapt and learn from new data, making them increasingly
valuable over time.\\n\\nHowever, there are also valid concerns. Privacy and
security are major issues; AI agents often require access to large datasets
that can include sensitive personal information, and breaches can have serious
repercussions. There's also the ethical dimension, as the deployment of AI agents
can lead to job displacement for roles that were traditionally performed by
humans. This raises important questions about the future of work and the socio-economic
impact of automation. Furthermore, the decision-making of AI agents can sometimes
be opaque, making it challenging to understand how they arrive at specific conclusions
or actions, which is particularly concerning in high-stakes areas like medical
diagnoses or judicial decisions.\\n\\nSo, it's not a matter of \\\"hating\\\"
AI agents, but rather a case of needing to balance their incredible potential
with careful consideration of the associated risks and ethical implications.
Thoughtful regulation and ongoing public discourse will be crucial in ensuring
that AI agents are developed and deployed in ways that are beneficial to society
as a whole.\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
200,\n \"completion_tokens\": 345,\n \"total_tokens\": 545,\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0\n }\n },\n \"system_fingerprint\": \"fp_a2ff031fb5\"\n}\n"
\"assistant\",\n \"content\": \"Thought: I now can give a great answer\\nFinal
Answer: \\n\\nAI agents are autonomous programs that perform tasks or services
on behalf of users with a considerable degree of autonomy, often based on intelligence
derived from data and analytics. They can operate within specific domains or
across multiple areas, executing tasks ranging from mundane repetitive actions
to complex decision-making processes. Given their applications, it's essential
to examine both the benefits and criticisms to provide a balanced perspective.\\n\\n##
The Positive Aspects of AI Agents\\n\\n1. **Efficiency and Productivity:**\\n
\ AI agents can handle tedious and repetitive tasks efficiently, freeing up
human workers to focus on more complex and creative endeavors. This results
in significant time and cost savings for businesses.\\n\\n2. **24/7 Availability:**\\n
\ AI agents can work continuously without breaks, providing round-the-clock
service. This is especially beneficial for customer support, where they can
resolve issues and answer queries at any time.\\n\\n3. **Consistency and Accuracy:**\\n
\ Unlike humans, AI agents do not suffer from fatigue and can perform tasks
without error, ensuring a high level of consistency in operations.\\n\\n4. **Data
Handling and Analysis:**\\n AI agents can process and analyze vast amounts
of data quickly, identifying patterns and generating insights that would be
otherwise difficult to discern manually.\\n\\n## Criticisms and Concerns\\n\\n1.
**Job Displacement:**\\n One of the primary concerns is that AI agents could
replace human jobs, leading to unemployment. While they create new opportunities
in AI development and maintenance, the transition can be disruptive.\\n\\n2.
**Ethical Considerations:**\\n With increasing autonomy, ensuring that AI
agents act ethically and within the bounds of societal norms is a challenge.
Misuse of AI for malicious activities or biased decision-making are valid concerns
that need rigorous oversight.\\n\\n3. **Lack of Emotional Intelligence:**\\n
\ AI agents, no matter how advanced, lack the ability to empathize and understand
human emotions fully. This can be a drawback in areas that require delicate
human interaction, such as mental health support.\\n\\n4. **Dependence and Reliability:**\\n
\ Over-reliance on AI agents might lead to significant issues if they malfunction
or are compromised. Ensuring reliability and establishing fail-safes is critical.\\n\\n5.
**Security and Privacy:**\\n AI agents typically require access to large data
sets, often containing sensitive information. Ensuring robust data security
and user privacy is paramount to prevent misuse or data breaches.\\n\\n## Conclusion\\n\\nWhile
AI agents offer remarkable benefits in terms of efficiency, accuracy, and data
handling, their integration into society must be managed carefully to address
ethical concerns and potential negative impacts on employment and human interaction.
The onus is on developers, policymakers, and society at large to ensure that
AI agents are designed and deployed responsibly, balancing innovation with the
broader implications for humanity. \\n\\nDespite the apprehensions, dismissing
AI agents entirely overlooks their transformative potential. Instead, the focus
should be on harnessing these tools' capabilities while mitigating their risks,
ensuring they serve to enhance rather than hinder human progress.\",\n \"refusal\":
null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n
\ }\n ],\n \"usage\": {\n \"prompt_tokens\": 200,\n \"completion_tokens\":
609,\n \"total_tokens\": 809,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":
0\n }\n },\n \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8c26a7a95cff2ab9-LAX
- 8c3671654854745a-MIA
Connection:
- keep-alive
Content-Encoding:
@@ -95,7 +149,7 @@ interactions:
Content-Type:
- application/json
Date:
- Fri, 13 Sep 2024 08:09:29 GMT
- Sun, 15 Sep 2024 06:08:39 GMT
Server:
- cloudflare
Transfer-Encoding:
@@ -109,7 +163,7 @@ interactions:
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '4224'
- '5095'
openai-version:
- '2020-10-01'
strict-transport-security:
@@ -127,7 +181,7 @@ interactions:
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_7f1fc6147762baea44bbc8b27e73f29f
- req_5c935010b5cc7d844cef065245a1df13
http_version: HTTP/1.1
status_code: 200
version: 1