diff --git a/tests/agent_test.py b/tests/agent_test.py index 9ec68fff0..558450f7b 100644 --- a/tests/agent_test.py +++ b/tests/agent_test.py @@ -46,7 +46,7 @@ def test_custom_llm(): assert agent.llm.model_name == "gpt-4" assert agent.llm.temperature == 0 -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_agent_without_memory(): no_memory_agent = Agent( role="test role", @@ -76,7 +76,7 @@ def test_agent_without_memory(): assert no_memory_agent.agent_executor.memory is None assert memory_agent.agent_executor.memory is not None -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_agent_execution(): agent = Agent( role="test role", @@ -88,7 +88,7 @@ def test_agent_execution(): output = agent.execute_task("How much is 1 + 1?") assert output == "2" -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_agent_execution_with_tools(): from langchain.tools import tool @@ -112,7 +112,7 @@ def test_agent_execution_with_tools(): output = agent.execute_task("What is 3 times 4") assert output == "12" -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_agent_execution_with_specific_tools(): from langchain.tools import tool diff --git a/tests/agent_tools/agent_tools_test.py b/tests/agent_tools/agent_tools_test.py index d17ee1ab4..3d5d7fe05 100644 --- a/tests/agent_tools/agent_tools_test.py +++ b/tests/agent_tools/agent_tools_test.py @@ -12,8 +12,7 @@ researcher = Agent( ) tools = AgentTools(agents=[researcher]) - -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_delegate_work(): result = tools.delegate_work( command="researcher|share your take on AI Agents|I heard you hate them" @@ -21,7 +20,7 @@ def test_delegate_work(): assert result == "I apologize if my previous statements have given you the impression that I hate AI agents. As a technology researcher, I don't hold personal sentiments towards AI or any other technology. Rather, I analyze them objectively based on their capabilities, applications, and implications. AI agents, in particular, are a fascinating domain of research. They hold tremendous potential in automating and optimizing various tasks across industries. However, like any other technology, they come with their own set of challenges, such as ethical considerations around privacy and decision-making. My objective is to understand these technologies in depth and provide a balanced view." -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_ask_question(): result = tools.ask_question( command="researcher|do you hate AI Agents?|I heard you LOVE them" @@ -29,12 +28,16 @@ def test_ask_question(): assert result == "As an AI, I don't possess feelings or emotions, so I don't love or hate anything. However, I can provide detailed analysis and research on AI agents. They are a fascinating field of study with the potential to revolutionize many industries, although they also present certain challenges and ethical considerations." +def test_can_not_self_delegate(): + # TODO: Add test for self delegation + pass + def test_delegate_work_with_wrong_input(): result = tools.ask_question( command="writer|share your take on AI Agents" ) - assert result == "Error executing tool. Missing exact 3 pipe (|) separated values." + assert result == "Error executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|information`." def test_delegate_work_to_wrong_agent(): result = tools.ask_question( diff --git a/tests/agent_tools/cassettes/test_ask_question.yaml b/tests/agent_tools/cassettes/test_ask_question.yaml new file mode 100644 index 000000000..1f2c8e9bb --- /dev/null +++ b/tests/agent_tools/cassettes/test_ask_question.yaml @@ -0,0 +1,251 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re + an expert researcher, specialized in technology\n\nYour personal goal is: make + the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou + have access to the following tools:\n\n\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI for its opinion + on AI agents, based on the impression that the AI dislikes them. The AI clarifies + that it doesn''t hold personal sentiments towards AI or any technology, but + instead analyzes them objectively. The AI finds AI agents a fascinating domain + of research with great potential for task automation and optimization across + industries, but acknowledges they present challenges such as ethical considerations + around privacy and decision-making.\nBegin! This is VERY important to you, your + job depends on it!\n\nCurrent Task: do you hate AI Agents?\n\nThis is the context + you are working with:\nI heard you LOVE them\n\n"}], "model": "gpt-4", "n": + 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1494' + content-type: + - application/json + cookie: + - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=; + _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8Xx2vMXN4WCrWeeO4DOAowhb3oeDJ\",\n \"object\": + \"chat.completion\",\n \"created\": 1703102489,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\nFinal + Answer: As an AI, I don't possess feelings or emotions, so I don't love or hate + anything. However, I can provide detailed analysis and research on AI agents. + They are a fascinating field of study with the potential to revolutionize many + industries, although they also present certain challenges and ethical considerations.\"\n + \ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n + \ ],\n \"usage\": {\n \"prompt_tokens\": 291,\n \"completion_tokens\": + 75,\n \"total_tokens\": 366\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a7a3efab6a4b0-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 20:01:35 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '6060' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299652' + x-ratelimit-remaining-tokens_usage_based: + - '299652' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 69ms + x-ratelimit-reset-tokens_usage_based: + - 69ms + x-request-id: + - 3ad0d047d5260434816f61ec105bdbb8 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI for its opinion on AI + agents, based on the impression that the AI dislikes them. The AI clarifies + that it doesn''t hold personal sentiments towards AI or any technology, but + instead analyzes them objectively. The AI finds AI agents a fascinating domain + of research with great potential for task automation and optimization across + industries, but acknowledges they present challenges such as ethical considerations + around privacy and decision-making.\n\nNew lines of conversation:\nHuman: do + you hate AI Agents?\n\nThis is the context you are working with:\nI heard you + LOVE them\nAI: As an AI, I don''t possess feelings or emotions, so I don''t + love or hate anything. However, I can provide detailed analysis and research + on AI agents. They are a fascinating field of study with the potential to revolutionize + many industries, although they also present certain challenges and ethical considerations.\n\nNew + summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1726' + content-type: + - application/json + cookie: + - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=; + _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8Xx32X5innWZd8vEETP1jZMLH3b1O\",\n \"object\": + \"chat.completion\",\n \"created\": 1703102496,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI for its opinion + on AI agents, based on the impression that the AI dislikes them. The AI clarifies + that it doesn't hold personal sentiments towards AI or any technology, but instead + analyzes them objectively. The AI finds AI agents a fascinating domain of research + with great potential for task automation and optimization across industries, + but acknowledges they present challenges such as ethical considerations around + privacy and decision-making. When asked again if it hates or loves AI agents, + the AI reiterates that it doesn't possess feelings or emotions, but can provide + detailed analysis and research on AI agents.\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 300,\n \"completion_tokens\": 117,\n \"total_tokens\": 417\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a7a67ecaca4b0-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 20:01:41 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '5610' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299585' + x-ratelimit-remaining-tokens_usage_based: + - '299585' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 83ms + x-ratelimit-reset-tokens_usage_based: + - 83ms + x-request-id: + - 5b0b96506faa544c5d35b52286a3389c + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/agent_tools/cassettes/test_delegate_work.yaml b/tests/agent_tools/cassettes/test_delegate_work.yaml new file mode 100644 index 000000000..d9cf8f23c --- /dev/null +++ b/tests/agent_tools/cassettes/test_delegate_work.yaml @@ -0,0 +1,250 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re + an expert researcher, specialized in technology\n\nYour personal goal is: make + the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou + have access to the following tools:\n\n\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n \nBegin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: share your take on AI Agents\n\nThis + is the context you are working with:\nI heard you hate them\n\n"}], "model": + "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1030' + content-type: + - application/json + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8Xx2cQWLZ8Nd34HGmbQluyZWlD58b\",\n \"object\": + \"chat.completion\",\n \"created\": 1703102470,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\nFinal + Answer: I apologize if my previous statements have given you the impression + that I hate AI agents. As a technology researcher, I don't hold personal sentiments + towards AI or any other technology. Rather, I analyze them objectively based + on their capabilities, applications, and implications. AI agents, in particular, + are a fascinating domain of research. They hold tremendous potential in automating + and optimizing various tasks across industries. However, like any other technology, + they come with their own set of challenges, such as ethical considerations around + privacy and decision-making. My objective is to understand these technologies + in depth and provide a balanced view.\"\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 211,\n \"completion_tokens\": 134,\n \"total_tokens\": 345\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a79c59ea7a4b0-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 20:01:23 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=; + path=/; expires=Wed, 20-Dec-23 20:31:23 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + - _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000; + path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '12923' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299769' + x-ratelimit-remaining-tokens_usage_based: + - '299769' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 46ms + x-ratelimit-reset-tokens_usage_based: + - 46ms + x-request-id: + - 6468cdd7ae76aea910c72a503a58b8da + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: share + your take on AI Agents\n\nThis is the context you are working with:\nI heard + you hate them\nAI: I apologize if my previous statements have given you the + impression that I hate AI agents. As a technology researcher, I don''t hold + personal sentiments towards AI or any other technology. Rather, I analyze them + objectively based on their capabilities, applications, and implications. AI + agents, in particular, are a fascinating domain of research. They hold tremendous + potential in automating and optimizing various tasks across industries. However, + like any other technology, they come with their own set of challenges, such + as ethical considerations around privacy and decision-making. My objective is + to understand these technologies in depth and provide a balanced view.\n\nNew + summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1622' + content-type: + - application/json + cookie: + - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=; + _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8Xx2pqWD01uG0roGJ4daSfvaXLchg\",\n \"object\": + \"chat.completion\",\n \"created\": 1703102483,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI for its opinion + on AI agents, based on the impression that the AI dislikes them. The AI clarifies + that it doesn't hold personal sentiments towards AI or any technology, but instead + analyzes them objectively. The AI finds AI agents a fascinating domain of research + with great potential for task automation and optimization across industries, + but acknowledges they present challenges such as ethical considerations around + privacy and decision-making.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 279,\n \"completion_tokens\": + 81,\n \"total_tokens\": 360\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a7a17fbb9a4b0-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 20:01:29 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '5872' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299610' + x-ratelimit-remaining-tokens_usage_based: + - '299610' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 77ms + x-ratelimit-reset-tokens_usage_based: + - 77ms + x-request-id: + - bff02b569530c001aa9a2adba9adbeb9 + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/cassettes/test_agent_execution.yaml b/tests/cassettes/test_agent_execution.yaml new file mode 100644 index 000000000..6ac79b7a7 --- /dev/null +++ b/tests/cassettes/test_agent_execution.yaml @@ -0,0 +1,224 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\n\n\nTo use a tool, please use the exact following format:\n\n```\nThought: + Do I need to use a tool? Yes\nAction: the action to take, should be one of []\nAction + Input: the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```\n\t\tThis is the summary of your work so far:\n \nBegin! + This is VERY important to you, your job depends on it!\n\nCurrent Task: How + much is 1 + 1?\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], + "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '851' + content-type: + - application/json + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuDsBh2o1JE49eouNIBWCE2vn9pB\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091636,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\nFinal + Answer: 2\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 181,\n \"completion_tokens\": + 17,\n \"total_tokens\": 198\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 83897143cca7a477-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:00:38 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=H9RUg933Wznv5vpw9KzjZyJZSXUer6tLsBPnCGaO5sY-1703091638-1-AQMrr8fshVzTPZkSf5UmVC0gg4mnCVMhRfsAVDwFMAcb9eo7Gj6h8TFKL6YGvGlR5eid/JQIY/YbP3d9k7VV+RA=; + path=/; expires=Wed, 20-Dec-23 17:30:38 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + - _cfuvid=G34V4_SI2mUudYSgDXesqo_OnsZMUghvvyGp95eog58-1703091638133-0-604800000; + path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '1879' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299812' + x-ratelimit-remaining-tokens_usage_based: + - '299812' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 37ms + x-ratelimit-reset-tokens_usage_based: + - 37ms + x-request-id: + - 199af19ff2674901b03dbe9d166d7ffb + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: How much + is 1 + 1?\nAI: 2\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, + "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '871' + content-type: + - application/json + cookie: + - __cf_bm=H9RUg933Wznv5vpw9KzjZyJZSXUer6tLsBPnCGaO5sY-1703091638-1-AQMrr8fshVzTPZkSf5UmVC0gg4mnCVMhRfsAVDwFMAcb9eo7Gj6h8TFKL6YGvGlR5eid/JQIY/YbP3d9k7VV+RA=; + _cfuvid=G34V4_SI2mUudYSgDXesqo_OnsZMUghvvyGp95eog58-1703091638133-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuDuhhGTeJIvAaVjt8lxngLaR7GV\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091638,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI to add 1 + 1, to + which the AI responds with 2.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 150,\n \"completion_tokens\": + 22,\n \"total_tokens\": 172\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 83897152ad2ba477-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:00:41 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2860' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299798' + x-ratelimit-remaining-tokens_usage_based: + - '299798' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 40ms + x-ratelimit-reset-tokens_usage_based: + - 40ms + x-request-id: + - 6acd80ebd8c2463aa09cbb1550d14de3 + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/cassettes/test_agent_execution_with_specific_tools.yaml b/tests/cassettes/test_agent_execution_with_specific_tools.yaml new file mode 100644 index 000000000..51bce8237 --- /dev/null +++ b/tests/cassettes/test_agent_execution_with_specific_tools.yaml @@ -0,0 +1,345 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together. \n\t\t\tThe input to this tool should be a + comma separated list of numbers of \n\t\t\tlength two, representing the two + numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the + input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of [multiplier]\nAction Input: the input to the + action\nObservation: the result of the action\n```\n\nWhen you have a response + for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n \nBegin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model": + "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1199' + content-type: + - application/json + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuE6OrjKKco53f0TIqPQEE3nWeNj\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091650,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: + multiplier\\nAction Input: 3,4\\n\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 260,\n \"completion_tokens\": + 24,\n \"total_tokens\": 284\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8389719d5cba0110-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:00:52 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=; + path=/; expires=Wed, 20-Dec-23 17:30:52 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + - _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000; + path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2423' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299729' + x-ratelimit-remaining-tokens_usage_based: + - '299729' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 54ms + x-ratelimit-reset-tokens_usage_based: + - 54ms + x-request-id: + - 8f99f43731fa878eaf0fcbf0719d1b3f + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together. \n\t\t\tThe input to this tool should be a + comma separated list of numbers of \n\t\t\tlength two, representing the two + numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the + input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of [multiplier]\nAction Input: the input to the + action\nObservation: the result of the action\n```\n\nWhen you have a response + for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n \nBegin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do + I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\n\nObservation: + 12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": + false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1305' + content-type: + - application/json + cookie: + - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=; + _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuE86Ud94rsOP7VA4Bgxo6RM5XE6\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091652,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + 3 times 4 is 12.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 293,\n \"completion_tokens\": + 22,\n \"total_tokens\": 315\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838971ae0f120110-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:00:55 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2334' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299703' + x-ratelimit-remaining-tokens_usage_based: + - '299703' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 59ms + x-ratelimit-reset-tokens_usage_based: + - 59ms + x-request-id: + - 44304b182424a8acad8a3121817bea58 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What + is 3 times 4\nAI: 3 times 4 is 12.\n\nNew summary:"}], "model": "gpt-4", "n": + 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '885' + content-type: + - application/json + cookie: + - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=; + _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuEBWLslSBUMDHZRViwpoXcclYOk\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091655,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI what is 3 times + 4, and the AI responds that 3 times 4 is 12.\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 155,\n \"completion_tokens\": 27,\n \"total_tokens\": 182\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838971be49500110-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:00:58 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2942' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299794' + x-ratelimit-remaining-tokens_usage_based: + - '299794' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 41ms + x-ratelimit-reset-tokens_usage_based: + - 41ms + x-request-id: + - 546e9b3713f3ff2d7f9868133efaa3a7 + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/cassettes/test_agent_execution_with_tools.yaml b/tests/cassettes/test_agent_execution_with_tools.yaml new file mode 100644 index 000000000..a1fb31b02 --- /dev/null +++ b/tests/cassettes/test_agent_execution_with_tools.yaml @@ -0,0 +1,344 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together. \n\t\t\tThe input to this tool should be a + comma separated list of numbers of \n\t\t\tlength two, representing the two + numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the + input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of [multiplier]\nAction Input: the input to the + action\nObservation: the result of the action\n```\n\nWhen you have a response + for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n \nBegin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model": + "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1199' + content-type: + - application/json + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuDxosP85Kqo6mU6biIggZ5c828i\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091641,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: + multiplier\\nAction Input: 3,4\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 260,\n \"completion_tokens\": + 23,\n \"total_tokens\": 283\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 83897166eba7a5fd-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:00:44 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=; + path=/; expires=Wed, 20-Dec-23 17:30:44 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + - _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000; + path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2718' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299729' + x-ratelimit-remaining-tokens_usage_based: + - '299729' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 54ms + x-ratelimit-reset-tokens_usage_based: + - 54ms + x-request-id: + - 1714a9f5a2141d30f72506facf616944 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need + to multiply two numbers together. \n\t\t\tThe input to this tool should be a + comma separated list of numbers of \n\t\t\tlength two, representing the two + numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the + input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of [multiplier]\nAction Input: the input to the + action\nObservation: the result of the action\n```\n\nWhen you have a response + for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n \nBegin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do + I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\nObservation: + 12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": + false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1303' + content-type: + - application/json + cookie: + - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=; + _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuE0tWsbI9QDkRau6rzSUZfuqhFN\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091644,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + 12\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 293,\n \"completion_tokens\": + 15,\n \"total_tokens\": 308\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838971796af6a5fd-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:00:46 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2355' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299704' + x-ratelimit-remaining-tokens_usage_based: + - '299704' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 59ms + x-ratelimit-reset-tokens_usage_based: + - 59ms + x-request-id: + - a3de9d34f17496d9bdd2ae9360f6054a + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: What + is 3 times 4\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": + false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '871' + content-type: + - application/json + cookie: + - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=; + _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuE3Di6FRdNAetXNfWs6OWyRAfkf\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091647,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI what is 3 times + 4 and the AI responds with 12.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 149,\n \"completion_tokens\": + 20,\n \"total_tokens\": 169\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838971899954a5fd-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:00:49 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2698' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299798' + x-ratelimit-remaining-tokens_usage_based: + - '299798' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 40ms + x-ratelimit-reset-tokens_usage_based: + - 40ms + x-request-id: + - ddbd97cea4ec099c21c00ca922157ae1 + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/cassettes/test_agent_without_memory.yaml b/tests/cassettes/test_agent_without_memory.yaml new file mode 100644 index 000000000..b2e3ecf79 --- /dev/null +++ b/tests/cassettes/test_agent_without_memory.yaml @@ -0,0 +1,113 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour + personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following + tools:\n\n\n\nTo use a tool, please use the exact following format:\n\n```\nThought: + Do I need to use a tool? Yes\nAction: the action to take, should be one of []\nAction + Input: the input to the action\nObservation: the result of the action\n```\n\nWhen + you have a response for your task, or if you do not need to use a tool, you + MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: + [your response here]\n```\nBegin! This is VERY important to you, your job depends + on it!\n\nCurrent Task: How much is 1 + 1?\n\n"}], "model": "gpt-4", "n": 1, + "stop": ["\nObservation"], "stream": false, "temperature": 0.0}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '799' + content-type: + - application/json + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwKQzRwByjmOhHcKQk32biG9bslO\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099730,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\nFinal + Answer: 1 + 1 equals 2.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 169,\n \"completion_tokens\": + 24,\n \"total_tokens\": 193\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a36e258f71a90-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:15:33 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=MXonvOWhzu2xzqqQW6loCrPxpu3htpmRm9QULnV6Uic-1703099733-1-AXiceGXQ09SeMmJaW7hk60DzeZec+Bojjr+ptfpQQRQa0K6o+0oZS2Nhjv6TgYOas6QVkjTabKLwlzoS7qAeJoM=; + path=/; expires=Wed, 20-Dec-23 19:45:33 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + - _cfuvid=0hRVC1wV9ReH4cnY21jU6QE6m7DIZOjDOkZSBykI7yI-1703099733905-0-604800000; + path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '3423' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299825' + x-ratelimit-remaining-tokens_usage_based: + - '299825' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 35ms + x-ratelimit-reset-tokens_usage_based: + - 35ms + x-request-id: + - b8aea1a1a2f28a89da6e56213d29152c + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/cassettes/test_crew_creation.yaml b/tests/cassettes/test_crew_creation.yaml new file mode 100644 index 000000000..56c8b040a --- /dev/null +++ b/tests/cassettes/test_crew_creation.yaml @@ -0,0 +1,610 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access + to the following tools:\n\n\n\nTo use a tool, please use the exact following + format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to + take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n \nBegin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: Give me a list of 5 interesting + ideas to explore for na article, what makes them unique and interesting.\n\n"}], + "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1173' + content-type: + - application/json + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuEFy7ANTsR0yPJ75zQoqJ6ihEkP\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091659,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\n\\nFinal + Answer: \\n\\n1. **The Evolution of AI: From Old Concepts to New Frontiers** + - This topic would explore the history of AI from its earliest concepts in philosophy + and mathematics to the cutting-edge technologies of today. This would be interesting + as it gives the readers an understanding of how far we have come and where we + might go next.\\n\\n2. **AI Agents in Healthcare: The Future of Medicine** - + This topic addresses the unique ways AI is being used in healthcare, from diagnosing + diseases to predicting patient outcomes. It's interesting because it highlights + how AI technology can make significant impacts on our health and well-being.\\n\\n3. + **AI and Ethics: Navigating the Moral Landscape of Artificial Intelligence** + - This could be an engaging piece that delves into the ethical implications + of AI, such as privacy concerns, job displacement, and decision-making biases. + This is a unique topic because it invites readers to consider the societal implications + of AI.\\n\\n4. **Demystifying AI Algorithms: A Deep Dive into Machine Learning** + - This would be a technical article explaining how popular machine learning + algorithms work, including neural networks and reinforcement learning. This + topic is interesting as it provides insights into the 'black box' of AI for + a non-technical audience.\\n\\n5. **AI Startups: The Game Changers of the Tech + Industry** - This article would profile promising AI startups and their innovative + products or services. What makes this topic unique is that it gives a glimpse + into the entrepreneurial side of AI, showcasing how startups are driving the + AI revolution.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 238,\n \"completion_tokens\": + 320,\n \"total_tokens\": 558\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838971d4593501aa-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:01:38 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=lhXyDHHBBKgFgSeDJK7E90moYsVyXxwqYmoAjsR8zds-1703091698-1-AYOGE4WrbSFLThbY9Taz64kS7u1A9etNqu5IlAbOO60eV5UT/UaDydp38qZtI5dS17GuIFB6ZLTm9Ap/IHZJjJw=; + path=/; expires=Wed, 20-Dec-23 17:31:38 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000; + path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '38911' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299731' + x-ratelimit-remaining-tokens_usage_based: + - '299731' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 53ms + x-ratelimit-reset-tokens_usage_based: + - 53ms + x-request-id: + - 18a794039177925024548a3eec1133fe + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Give + me a list of 5 interesting ideas to explore for na article, what makes them + unique and interesting.\nAI: 1. **The Evolution of AI: From Old Concepts to + New Frontiers** - This topic would explore the history of AI from its earliest + concepts in philosophy and mathematics to the cutting-edge technologies of today. + This would be interesting as it gives the readers an understanding of how far + we have come and where we might go next.\n\n2. **AI Agents in Healthcare: The + Future of Medicine** - This topic addresses the unique ways AI is being used + in healthcare, from diagnosing diseases to predicting patient outcomes. It''s + interesting because it highlights how AI technology can make significant impacts + on our health and well-being.\n\n3. **AI and Ethics: Navigating the Moral Landscape + of Artificial Intelligence** - This could be an engaging piece that delves into + the ethical implications of AI, such as privacy concerns, job displacement, + and decision-making biases. This is a unique topic because it invites readers + to consider the societal implications of AI.\n\n4. **Demystifying AI Algorithms: + A Deep Dive into Machine Learning** - This would be a technical article explaining + how popular machine learning algorithms work, including neural networks and + reinforcement learning. This topic is interesting as it provides insights into + the ''black box'' of AI for a non-technical audience.\n\n5. **AI Startups: The + Game Changers of the Tech Industry** - This article would profile promising + AI startups and their innovative products or services. What makes this topic + unique is that it gives a glimpse into the entrepreneurial side of AI, showcasing + how startups are driving the AI revolution.\n\nNew summary:"}], "model": "gpt-4", + "n": 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '2547' + content-type: + - application/json + cookie: + - __cf_bm=lhXyDHHBBKgFgSeDJK7E90moYsVyXxwqYmoAjsR8zds-1703091698-1-AYOGE4WrbSFLThbY9Taz64kS7u1A9etNqu5IlAbOO60eV5UT/UaDydp38qZtI5dS17GuIFB6ZLTm9Ap/IHZJjJw=; + _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuEsg8v9ayaeSLfl3wwNDslKQohR\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091698,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI for five interesting + and unique article ideas. The AI suggests: 1) an exploration of the evolution + of AI, from its earliest concepts to current technologies, 2) a look into the + use of AI in healthcare and how it's shaping the future of medicine, 3) an investigation + into the ethical implications of AI, 4) a technical explanation of how popular + machine learning algorithms work, and 5) a profile on AI startups and their + potentially revolutionary products or services.\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 465,\n \"completion_tokens\": 101,\n \"total_tokens\": 566\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838972c91b0201aa-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:01:51 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '13153' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299380' + x-ratelimit-remaining-tokens_usage_based: + - '299380' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 123ms + x-ratelimit-reset-tokens_usage_based: + - 123ms + x-request-id: + - f498095d127271d7e782bd4e2d81158f + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Senior Writer.\nYou''re + a senior writer, specialized in technology, software engineering, AI and startups. + You work as a freelancer and are now working on writing content for a new customer.\n\nYour + personal goal is: Write the best content about AI and AI agents.\n\nTOOLS:\n------\nYou + have access to the following tools:\n\n\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n \nBegin! This is VERY important to + you, your job depends on it!\n\nCurrent Task: Write a 1 amazing paragraph highlight + for each idea that showcases how good an article about this topic could be. + Return the list of ideas with their paragraph and your notes.\n\nThis is the + context you are working with:\n1. **The Evolution of AI: From Old Concepts to + New Frontiers** - This topic would explore the history of AI from its earliest + concepts in philosophy and mathematics to the cutting-edge technologies of today. + This would be interesting as it gives the readers an understanding of how far + we have come and where we might go next.\n\n2. **AI Agents in Healthcare: The + Future of Medicine** - This topic addresses the unique ways AI is being used + in healthcare, from diagnosing diseases to predicting patient outcomes. It''s + interesting because it highlights how AI technology can make significant impacts + on our health and well-being.\n\n3. **AI and Ethics: Navigating the Moral Landscape + of Artificial Intelligence** - This could be an engaging piece that delves into + the ethical implications of AI, such as privacy concerns, job displacement, + and decision-making biases. This is a unique topic because it invites readers + to consider the societal implications of AI.\n\n4. **Demystifying AI Algorithms: + A Deep Dive into Machine Learning** - This would be a technical article explaining + how popular machine learning algorithms work, including neural networks and + reinforcement learning. This topic is interesting as it provides insights into + the ''black box'' of AI for a non-technical audience.\n\n5. **AI Startups: The + Game Changers of the Tech Industry** - This article would profile promising + AI startups and their innovative products or services. What makes this topic + unique is that it gives a glimpse into the entrepreneurial side of AI, showcasing + how startups are driving the AI revolution.\n\n"}], "model": "gpt-4", "n": 1, + "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '2846' + content-type: + - application/json + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuF6yxj7DBxOklkSGxNnET4eRRMX\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091712,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\n\\nFinal + Answer: \\n\\n1. **The Evolution of AI: From Old Concepts to New Frontiers** + - Journey with us as we traverse the fascinating timeline of artificial intelligence + - from its philosophical and mathematical infancy to the sophisticated, problem-solving + tool it has become today. This riveting account will not only educate but also + inspire, as we delve deep into the milestones that brought us here and shine + a beacon on the potential that lies ahead.\\n\\n2. **AI Agents in Healthcare: + The Future of Medicine** - Imagine a world where illnesses are diagnosed before + symptoms appear, where patient outcomes are not mere guesses but accurate predictions. + This is the world AI is crafting in healthcare - a revolution that's saving + lives and changing the face of medicine as we know it. This article will spotlight + this transformative journey, underlining the profound impact AI is having on + our health and well-being.\\n\\n3. **AI and Ethics: Navigating the Moral Landscape + of Artificial Intelligence** - As AI becomes an integral part of our lives, + it brings along a plethora of ethical dilemmas. This thought-provoking piece + will navigate the complex moral landscape of AI, addressing critical concerns + like privacy, job displacement, and decision-making biases. It serves as a much-needed + discussion platform for the societal implications of AI, urging us to look beyond + the technology and into the mirror.\\n\\n4. **Demystifying AI Algorithms: A + Deep Dive into Machine Learning** - Ever wondered what goes on behind the scenes + of AI? This enlightening article will break down the complex world of machine + learning algorithms into digestible insights, unraveling the mystery of AI's + 'black box'. It's a rare opportunity for the non-technical audience to appreciate + the inner workings of AI, fostering a deeper understanding of this revolutionary + technology.\\n\\n5. **AI Startups: The Game Changers of the Tech Industry** + - In the world of tech, AI startups are the bold pioneers charting new territories. + This article will spotlight these game changers, showcasing how their innovative + products and services are driving the AI revolution. It's a unique opportunity + to catch a glimpse of the entrepreneurial side of AI, offering inspiration for + the tech enthusiasts and dreamers alike.\"\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 557,\n \"completion_tokens\": 447,\n \"total_tokens\": 1004\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8389731f9e14a537-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:02:52 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=PQ1Zoj5GxgZ_f0jkeDUljP5RPxAZ6R1vF57KNYCX8.A-1703091772-1-Aff/FYwzB8VsF9SCkzi9xE9Bag3EFcofaPDkYfW14mpZhHsepfU/zuQ5DEXLBI3CXpUkQJ7wRW42b7ZCV04BY2Y=; + path=/; expires=Wed, 20-Dec-23 17:32:52 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000; + path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '60517' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299316' + x-ratelimit-remaining-tokens_usage_based: + - '299316' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 136ms + x-ratelimit-reset-tokens_usage_based: + - 136ms + x-request-id: + - 00735e9e054e84ca1a977e11ae706469 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Write + a 1 amazing paragraph highlight for each idea that showcases how good an article + about this topic could be. Return the list of ideas with their paragraph and + your notes.\n\nThis is the context you are working with:\n1. **The Evolution + of AI: From Old Concepts to New Frontiers** - This topic would explore the history + of AI from its earliest concepts in philosophy and mathematics to the cutting-edge + technologies of today. This would be interesting as it gives the readers an + understanding of how far we have come and where we might go next.\n\n2. **AI + Agents in Healthcare: The Future of Medicine** - This topic addresses the unique + ways AI is being used in healthcare, from diagnosing diseases to predicting + patient outcomes. It''s interesting because it highlights how AI technology + can make significant impacts on our health and well-being.\n\n3. **AI and Ethics: + Navigating the Moral Landscape of Artificial Intelligence** - This could be + an engaging piece that delves into the ethical implications of AI, such as privacy + concerns, job displacement, and decision-making biases. This is a unique topic + because it invites readers to consider the societal implications of AI.\n\n4. + **Demystifying AI Algorithms: A Deep Dive into Machine Learning** - This would + be a technical article explaining how popular machine learning algorithms work, + including neural networks and reinforcement learning. This topic is interesting + as it provides insights into the ''black box'' of AI for a non-technical audience.\n\n5. + **AI Startups: The Game Changers of the Tech Industry** - This article would + profile promising AI startups and their innovative products or services. What + makes this topic unique is that it gives a glimpse into the entrepreneurial + side of AI, showcasing how startups are driving the AI revolution.\nAI: 1. **The + Evolution of AI: From Old Concepts to New Frontiers** - Journey with us as we + traverse the fascinating timeline of artificial intelligence - from its philosophical + and mathematical infancy to the sophisticated, problem-solving tool it has become + today. This riveting account will not only educate but also inspire, as we delve + deep into the milestones that brought us here and shine a beacon on the potential + that lies ahead.\n\n2. **AI Agents in Healthcare: The Future of Medicine** - + Imagine a world where illnesses are diagnosed before symptoms appear, where + patient outcomes are not mere guesses but accurate predictions. This is the + world AI is crafting in healthcare - a revolution that''s saving lives and changing + the face of medicine as we know it. This article will spotlight this transformative + journey, underlining the profound impact AI is having on our health and well-being.\n\n3. + **AI and Ethics: Navigating the Moral Landscape of Artificial Intelligence** + - As AI becomes an integral part of our lives, it brings along a plethora of + ethical dilemmas. This thought-provoking piece will navigate the complex moral + landscape of AI, addressing critical concerns like privacy, job displacement, + and decision-making biases. It serves as a much-needed discussion platform for + the societal implications of AI, urging us to look beyond the technology and + into the mirror.\n\n4. **Demystifying AI Algorithms: A Deep Dive into Machine + Learning** - Ever wondered what goes on behind the scenes of AI? This enlightening + article will break down the complex world of machine learning algorithms into + digestible insights, unraveling the mystery of AI''s ''black box''. It''s a + rare opportunity for the non-technical audience to appreciate the inner workings + of AI, fostering a deeper understanding of this revolutionary technology.\n\n5. + **AI Startups: The Game Changers of the Tech Industry** - In the world of tech, + AI startups are the bold pioneers charting new territories. This article will + spotlight these game changers, showcasing how their innovative products and + services are driving the AI revolution. It''s a unique opportunity to catch + a glimpse of the entrepreneurial side of AI, offering inspiration for the tech + enthusiasts and dreamers alike.\n\nNew summary:"}], "model": "gpt-4", "n": 1, + "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '4927' + content-type: + - application/json + cookie: + - __cf_bm=PQ1Zoj5GxgZ_f0jkeDUljP5RPxAZ6R1vF57KNYCX8.A-1703091772-1-Aff/FYwzB8VsF9SCkzi9xE9Bag3EFcofaPDkYfW14mpZhHsepfU/zuQ5DEXLBI3CXpUkQJ7wRW42b7ZCV04BY2Y=; + _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XuG5bK3Oe1gVXJLOjuo2AMBa83Du\",\n \"object\": + \"chat.completion\",\n \"created\": 1703091773,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI to write a paragraph + for each of five AI-related topics, highlighting how each could make for an + interesting article. The proposed topics are: the history of AI, AI's role in + healthcare, ethical considerations in AI, understanding AI algorithms, and AI + startups. The AI provides detailed overviews for each topic, emphasizing the + evolution and impact of AI, the transformative role of AI in healthcare, the + ethical dilemmas faced in AI development and use, the intricacies of AI algorithms, + and the pioneering role of AI startups in the tech industry.\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 917,\n \"completion_tokens\": 112,\n \"total_tokens\": 1029\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 8389749b9cc5a537-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 17:02:59 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '6202' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '298788' + x-ratelimit-remaining-tokens_usage_based: + - '298788' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 242ms + x-ratelimit-reset-tokens_usage_based: + - 242ms + x-request-id: + - c96a3bc39be7375a244224b958575e22 + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/cassettes/test_crew_verbose_output.yaml b/tests/cassettes/test_crew_verbose_output.yaml new file mode 100644 index 000000000..cc854bc9f --- /dev/null +++ b/tests/cassettes/test_crew_verbose_output.yaml @@ -0,0 +1,1772 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access + to the following tools:\n\n\n\nTo use a tool, please use the exact following + format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to + take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI for five interesting + and unique article ideas. The AI suggests: 1) an exploration of the evolution + of AI, from its earliest concepts to current technologies, 2) a look into the + use of AI in healthcare and how it''s shaping the future of medicine, 3) an + investigation into the ethical implications of AI, 4) a technical explanation + of how popular machine learning algorithms work, and 5) a profile on AI startups + and their potentially revolutionary products or services.\nBegin! This is VERY + important to you, your job depends on it!\n\nCurrent Task: Research AI advancements.\n\n"}], + "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1584' + content-type: + - application/json + cookie: + - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwM3JvX0g3wuoSbhTniFsAE7IfbL\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099831,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: + Internet Research\\nAction Input: AI advancements\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 321,\n \"completion_tokens\": 22,\n \"total_tokens\": 343\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3955788f010b-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:17:13 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=5B5UNtJ.5znx6uxkns4_5xRr40XRPyeUm399zz8IoKI-1703099833-1-AehzT4bH3DVl0KALstLYfpgpJ1Hppws+ChfQLaWVhscSWvhtinQt1pzTiNiG9MF56/U7xrpk+FWeBFFSQRPQ6+o=; + path=/; expires=Wed, 20-Dec-23 19:47:13 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '1812' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299629' + x-ratelimit-remaining-tokens_usage_based: + - '299629' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 74ms + x-ratelimit-reset-tokens_usage_based: + - 74ms + x-request-id: + - 4c4002da31c58273a6658fe6a8efa829 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access + to the following tools:\n\n\n\nTo use a tool, please use the exact following + format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to + take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI for five interesting + and unique article ideas. The AI suggests: 1) an exploration of the evolution + of AI, from its earliest concepts to current technologies, 2) a look into the + use of AI in healthcare and how it''s shaping the future of medicine, 3) an + investigation into the ethical implications of AI, 4) a technical explanation + of how popular machine learning algorithms work, and 5) a profile on AI startups + and their potentially revolutionary products or services.\nBegin! This is VERY + important to you, your job depends on it!\n\nCurrent Task: Research AI advancements.\nThought: + Do I need to use a tool? Yes\nAction: Internet Research\nAction Input: AI advancements\nObservation: + Internet Research is not a valid tool, try one of [].\nThought: \n"}], "model": + "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1758' + content-type: + - application/json + cookie: + - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000; + __cf_bm=5B5UNtJ.5znx6uxkns4_5xRr40XRPyeUm399zz8IoKI-1703099833-1-AehzT4bH3DVl0KALstLYfpgpJ1Hppws+ChfQLaWVhscSWvhtinQt1pzTiNiG9MF56/U7xrpk+FWeBFFSQRPQ6+o= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwM5bbnX1Y3HJYd8TKQrrY9arlc6\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099833,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + Based on the recent advancements in AI, here are some interesting points:\\n\\n1. + Reinforcement Learning: This has been a hot topic in the field of AI. It's a + type of machine learning where an agent learns to behave in an environment, + by performing certain actions and observing the results.\\n\\n2. Generative + Adversarial Networks (GANs): GANs have gained a lot of attention in the AI community. + They can generate new, synthetic instances of data that can pass for real data.\\n\\n3. + Natural Language Processing (NLP): With the rise of digital assistants like + Siri, Alexa, and Google Assistant, advancements in NLP have been pivotal. NLP + involves enabling computers to understand and process human language.\\n\\n4. + Computer Vision: This involves teaching computers to \\\"see\\\" and understand + digital images and videos. It's a key technology in a variety of applications, + from self-driving cars to facial recognition systems.\\n\\n5. Transfer Learning: + This is a research problem in machine learning that focuses on storing knowledge + gained while solving one problem and applying it to a different but related + problem. For example, knowledge gained while learning to recognize cars could + apply when trying to recognize trucks. \\n\\n6. AI in Healthcare: AI has made + significant improvements in healthcare, from predicting patient deterioration + to automated monitoring.\\n\\n7. AI Ethics: As AI becomes more prevalent, ethical + considerations also become more important. Topics like data privacy, transparency + in AI decision making, and fairness are all crucial. \\n\\n8. AI Startups: Numerous + startups are leveraging AI to offer innovative solutions across a wide range + of industries, from finance to healthcare to e-commerce.\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 363,\n \"completion_tokens\": 337,\n \"total_tokens\": 700\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a39660b11010b-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:17:45 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '31548' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299587' + x-ratelimit-remaining-tokens_usage_based: + - '299587' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 82ms + x-ratelimit-reset-tokens_usage_based: + - 82ms + x-request-id: + - 1a7d562e513daf567468566b2677a9bd + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI for five interesting and + unique article ideas. The AI suggests: 1) an exploration of the evolution of + AI, from its earliest concepts to current technologies, 2) a look into the use + of AI in healthcare and how it''s shaping the future of medicine, 3) an investigation + into the ethical implications of AI, 4) a technical explanation of how popular + machine learning algorithms work, and 5) a profile on AI startups and their + potentially revolutionary products or services.\n\nNew lines of conversation:\nHuman: + Research AI advancements.\nAI: Based on the recent advancements in AI, here + are some interesting points:\n\n1. Reinforcement Learning: This has been a hot + topic in the field of AI. It''s a type of machine learning where an agent learns + to behave in an environment, by performing certain actions and observing the + results.\n\n2. Generative Adversarial Networks (GANs): GANs have gained a lot + of attention in the AI community. They can generate new, synthetic instances + of data that can pass for real data.\n\n3. Natural Language Processing (NLP): + With the rise of digital assistants like Siri, Alexa, and Google Assistant, + advancements in NLP have been pivotal. NLP involves enabling computers to understand + and process human language.\n\n4. Computer Vision: This involves teaching computers + to \"see\" and understand digital images and videos. It''s a key technology + in a variety of applications, from self-driving cars to facial recognition systems.\n\n5. + Transfer Learning: This is a research problem in machine learning that focuses + on storing knowledge gained while solving one problem and applying it to a different + but related problem. For example, knowledge gained while learning to recognize + cars could apply when trying to recognize trucks. \n\n6. AI in Healthcare: AI + has made significant improvements in healthcare, from predicting patient deterioration + to automated monitoring.\n\n7. AI Ethics: As AI becomes more prevalent, ethical + considerations also become more important. Topics like data privacy, transparency + in AI decision making, and fairness are all crucial. \n\n8. AI Startups: Numerous + startups are leveraging AI to offer innovative solutions across a wide range + of industries, from finance to healthcare to e-commerce.\n\nNew summary:"}], + "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '3076' + content-type: + - application/json + cookie: + - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000; + __cf_bm=5B5UNtJ.5znx6uxkns4_5xRr40XRPyeUm399zz8IoKI-1703099833-1-AehzT4bH3DVl0KALstLYfpgpJ1Hppws+ChfQLaWVhscSWvhtinQt1pzTiNiG9MF56/U7xrpk+FWeBFFSQRPQ6+o= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwMbXBTPwIfNZfZojsgDDMjSYLJW\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099865,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI for five interesting + and unique article ideas. The AI suggests: 1) an exploration of the evolution + of AI, from its earliest concepts to current technologies, 2) a look into the + use of AI in healthcare and how it's shaping the future of medicine, 3) an investigation + into the ethical implications of AI, 4) a technical explanation of how popular + machine learning algorithms work, and 5) a profile on AI startups and their + potentially revolutionary products or services. When asked to research AI advancements, + the AI discusses reinforcement learning, generative adversarial networks (GANs), + natural language processing (NLP), computer vision, transfer learning, AI in + healthcare, AI ethics, and AI startups.\"\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 567,\n \"completion_tokens\": 147,\n \"total_tokens\": 714\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3a2e6a01010b-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:18:01 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '15742' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299250' + x-ratelimit-remaining-tokens_usage_based: + - '299250' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 149ms + x-ratelimit-reset-tokens_usage_based: + - 149ms + x-request-id: + - 12444c6c34b2407900d39323ec0f7307 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Senior Writer.\nYou''re + a senior writer, specialized in technology, software engineering, AI and startups. + You work as a freelancer and are now working on writing content for a new customer.\n\nYour + personal goal is: Write the best content about AI and AI agents.\n\nTOOLS:\n------\nYou + have access to the following tools:\n\n\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI to write a paragraph + for each of five AI-related topics: the history of AI, AI''s role in healthcare, + ethical considerations in AI, understanding AI algorithms, and AI startups. + The AI provides detailed overviews for each topic, emphasizing the evolution + and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas + faced in AI development and use, the intricacies of AI algorithms, and the pioneering + role of AI startups in the tech industry. The human then asks the AI to draft + a paragraph about AI Agents. The AI creates an engaging overview of AI agents, + discussing their roles, potential, and implications in the current world, highlighting + their transformative impact on various sectors and their potential for the future + while noting the importance of responsibly harnessing this potential.\nBegin! + This is VERY important to you, your job depends on it!\n\nCurrent Task: Write + about AI in healthcare.\n\nThis is the context you are working with:\nBased + on the recent advancements in AI, here are some interesting points:\n\n1. Reinforcement + Learning: This has been a hot topic in the field of AI. It''s a type of machine + learning where an agent learns to behave in an environment, by performing certain + actions and observing the results.\n\n2. Generative Adversarial Networks (GANs): + GANs have gained a lot of attention in the AI community. They can generate new, + synthetic instances of data that can pass for real data.\n\n3. Natural Language + Processing (NLP): With the rise of digital assistants like Siri, Alexa, and + Google Assistant, advancements in NLP have been pivotal. NLP involves enabling + computers to understand and process human language.\n\n4. Computer Vision: This + involves teaching computers to \"see\" and understand digital images and videos. + It''s a key technology in a variety of applications, from self-driving cars + to facial recognition systems.\n\n5. Transfer Learning: This is a research problem + in machine learning that focuses on storing knowledge gained while solving one + problem and applying it to a different but related problem. For example, knowledge + gained while learning to recognize cars could apply when trying to recognize + trucks. \n\n6. AI in Healthcare: AI has made significant improvements in healthcare, + from predicting patient deterioration to automated monitoring.\n\n7. AI Ethics: + As AI becomes more prevalent, ethical considerations also become more important. + Topics like data privacy, transparency in AI decision making, and fairness are + all crucial. \n\n8. AI Startups: Numerous startups are leveraging AI to offer + innovative solutions across a wide range of industries, from finance to healthcare + to e-commerce.\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], + "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '3659' + content-type: + - application/json + cookie: + - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000; + __cf_bm=lM319LPDEnvF96Mm4S90dEPrAGj1BHp.EoL8Zh1oCkU-1703099793-1-AS7kVNRnez1R9AZHZcWMDEIHZ3+Ay1dO+6ucbsMG+Euq+B+uku7GPY+Yz9hBZVDn+UTIJAw5aBsQH3U34sHaie4= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwMruzOhYZL4IWjmGxdMfe0GHJEq\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099881,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\nFinal + Answer: AI in Healthcare: The intervention of Artificial Intelligence into healthcare + has been nothing short of revolutionary. With the ability to predict patient + deterioration, AI can provide early alerts, giving medical professionals the + chance to intervene and potentially save lives. It also enhances the efficiency + of healthcare delivery by automating monitoring systems and reducing the strain + on overworked medical staff. Machine learning algorithms can sift through vast + amounts of data to identify disease patterns, aiding in early detection and + diagnosis. Natural Language Processing (NLP) is now being used to interpret + clinical notes and extract meaningful information, aiding in clinical decision-making. + Computer Vision, another AI facet, aids in image-based diagnostics, making it + possible to detect anomalies in medical images with improved precision. AI is + not just a tool for physicians; it also empowers patients by offering AI-based + health assistants and personalized health insights. However, as AI continues + to penetrate healthcare, it also raises ethical questions around patient data + privacy and the transparency of AI-driven decisions, highlighting the need for + robust regulatory frameworks. Nonetheless, the potential of AI in healthcare + is immense, promising a future of personalized, efficient, and proactive healthcare.\"\n + \ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n + \ ],\n \"usage\": {\n \"prompt_tokens\": 707,\n \"completion_tokens\": + 238,\n \"total_tokens\": 945\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3a93a9c6a4ea-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:18:28 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '26244' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299115' + x-ratelimit-remaining-tokens_usage_based: + - '299115' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 176ms + x-ratelimit-reset-tokens_usage_based: + - 176ms + x-request-id: + - 115557e6172f7489a35f05bd9df46083 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to write a paragraph for + each of five AI-related topics: the history of AI, AI''s role in healthcare, + ethical considerations in AI, understanding AI algorithms, and AI startups. + The AI provides detailed overviews for each topic, emphasizing the evolution + and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas + faced in AI development and use, the intricacies of AI algorithms, and the pioneering + role of AI startups in the tech industry. The human then asks the AI to draft + a paragraph about AI Agents. The AI creates an engaging overview of AI agents, + discussing their roles, potential, and implications in the current world, highlighting + their transformative impact on various sectors and their potential for the future + while noting the importance of responsibly harnessing this potential.\n\nNew + lines of conversation:\nHuman: Write about AI in healthcare.\n\nThis is the + context you are working with:\nBased on the recent advancements in AI, here + are some interesting points:\n\n1. Reinforcement Learning: This has been a hot + topic in the field of AI. It''s a type of machine learning where an agent learns + to behave in an environment, by performing certain actions and observing the + results.\n\n2. Generative Adversarial Networks (GANs): GANs have gained a lot + of attention in the AI community. They can generate new, synthetic instances + of data that can pass for real data.\n\n3. Natural Language Processing (NLP): + With the rise of digital assistants like Siri, Alexa, and Google Assistant, + advancements in NLP have been pivotal. NLP involves enabling computers to understand + and process human language.\n\n4. Computer Vision: This involves teaching computers + to \"see\" and understand digital images and videos. It''s a key technology + in a variety of applications, from self-driving cars to facial recognition systems.\n\n5. + Transfer Learning: This is a research problem in machine learning that focuses + on storing knowledge gained while solving one problem and applying it to a different + but related problem. For example, knowledge gained while learning to recognize + cars could apply when trying to recognize trucks. \n\n6. AI in Healthcare: AI + has made significant improvements in healthcare, from predicting patient deterioration + to automated monitoring.\n\n7. AI Ethics: As AI becomes more prevalent, ethical + considerations also become more important. Topics like data privacy, transparency + in AI decision making, and fairness are all crucial. \n\n8. AI Startups: Numerous + startups are leveraging AI to offer innovative solutions across a wide range + of industries, from finance to healthcare to e-commerce.\nAI: AI in Healthcare: + The intervention of Artificial Intelligence into healthcare has been nothing + short of revolutionary. With the ability to predict patient deterioration, AI + can provide early alerts, giving medical professionals the chance to intervene + and potentially save lives. It also enhances the efficiency of healthcare delivery + by automating monitoring systems and reducing the strain on overworked medical + staff. Machine learning algorithms can sift through vast amounts of data to + identify disease patterns, aiding in early detection and diagnosis. Natural + Language Processing (NLP) is now being used to interpret clinical notes and + extract meaningful information, aiding in clinical decision-making. Computer + Vision, another AI facet, aids in image-based diagnostics, making it possible + to detect anomalies in medical images with improved precision. AI is not just + a tool for physicians; it also empowers patients by offering AI-based health + assistants and personalized health insights. However, as AI continues to penetrate + healthcare, it also raises ethical questions around patient data privacy and + the transparency of AI-driven decisions, highlighting the need for robust regulatory + frameworks. Nonetheless, the potential of AI in healthcare is immense, promising + a future of personalized, efficient, and proactive healthcare.\n\nNew summary:"}], + "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '4818' + content-type: + - application/json + cookie: + - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000; + __cf_bm=lM319LPDEnvF96Mm4S90dEPrAGj1BHp.EoL8Zh1oCkU-1703099793-1-AS7kVNRnez1R9AZHZcWMDEIHZ3+Ay1dO+6ucbsMG+Euq+B+uku7GPY+Yz9hBZVDn+UTIJAw5aBsQH3U34sHaie4= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwNIV6UcmYrmfyIiDYlKwtsLyz2r\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099908,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI to write about + several AI-related topics: the history of AI, AI's role in healthcare, ethical + considerations in AI, understanding AI algorithms, AI startups, and AI agents. + The AI provides detailed paragraphs for each topic, discussing the evolution + and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas + in AI development and use, the intricacies of AI algorithms, the pioneering + role of AI startups in the tech industry, and the roles and potential of AI + agents. The AI then presents an expansive list of recent AI advancements, including + reinforcement learning, generative adversarial networks (GANs), natural language + processing (NLP), computer vision, transfer learning, AI in healthcare, AI ethics, + and AI startups. Upon the human's request, the AI elaborates on AI in healthcare. + It discusses how AI revolutionizes healthcare through early deterioration prediction, + automated monitoring, disease pattern identification, clinical note interpretation, + image-based diagnostics, and personalized health insights while also raising + ethical issues around data privacy and decision transparency.\"\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n + \ \"usage\": {\n \"prompt_tokens\": 858,\n \"completion_tokens\": 209,\n + \ \"total_tokens\": 1067\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3b3adfdaa4ea-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:18:49 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '20907' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '298815' + x-ratelimit-remaining-tokens_usage_based: + - '298815' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 236ms + x-ratelimit-reset-tokens_usage_based: + - 236ms + x-request-id: + - d4b15810c508060e474c2a7874096863 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access + to the following tools:\n\n\n\nTo use a tool, please use the exact following + format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to + take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI for five interesting + and unique article ideas. The AI suggests: 1) an exploration of the evolution + of AI, from its earliest concepts to current technologies, 2) a look into the + use of AI in healthcare and how it''s shaping the future of medicine, 3) an + investigation into the ethical implications of AI, 4) a technical explanation + of how popular machine learning algorithms work, and 5) a profile on AI startups + and their potentially revolutionary products or services. When asked to research + AI advancements, the AI discusses reinforcement learning, generative adversarial + networks (GANs), natural language processing (NLP), computer vision, transfer + learning, AI in healthcare, AI ethics, and AI startups.\nBegin! This is VERY + important to you, your job depends on it!\n\nCurrent Task: Research AI advancements.\n\n"}], + "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1822' + content-type: + - application/json + cookie: + - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000; + __cf_bm=5B5UNtJ.5znx6uxkns4_5xRr40XRPyeUm399zz8IoKI-1703099833-1-AehzT4bH3DVl0KALstLYfpgpJ1Hppws+ChfQLaWVhscSWvhtinQt1pzTiNiG9MF56/U7xrpk+FWeBFFSQRPQ6+o= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwNd9hDlufgvC5y3hsa0cDsmhybb\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099929,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: + Use the Web Search tool\\nAction Input: \\\"Latest advancements in AI\\\"\"\n + \ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n + \ ],\n \"usage\": {\n \"prompt_tokens\": 367,\n \"completion_tokens\": + 29,\n \"total_tokens\": 396\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3bc0c81ea505-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:18:52 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '2757' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299570' + x-ratelimit-remaining-tokens_usage_based: + - '299570' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 86ms + x-ratelimit-reset-tokens_usage_based: + - 86ms + x-request-id: + - 9bab6dd23252ad6224d9b842fafdf11f + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access + to the following tools:\n\n\n\nTo use a tool, please use the exact following + format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to + take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI for five interesting + and unique article ideas. The AI suggests: 1) an exploration of the evolution + of AI, from its earliest concepts to current technologies, 2) a look into the + use of AI in healthcare and how it''s shaping the future of medicine, 3) an + investigation into the ethical implications of AI, 4) a technical explanation + of how popular machine learning algorithms work, and 5) a profile on AI startups + and their potentially revolutionary products or services. When asked to research + AI advancements, the AI discusses reinforcement learning, generative adversarial + networks (GANs), natural language processing (NLP), computer vision, transfer + learning, AI in healthcare, AI ethics, and AI startups.\nBegin! This is VERY + important to you, your job depends on it!\n\nCurrent Task: Research AI advancements.\nThought: + Do I need to use a tool? Yes\nAction: Use the Web Search tool\nAction Input: + \"Latest advancements in AI\"\nObservation: Use the Web Search tool is not a + valid tool, try one of [].\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": + ["\nObservation"], "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '2022' + content-type: + - application/json + cookie: + - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000; + __cf_bm=5B5UNtJ.5znx6uxkns4_5xRr40XRPyeUm399zz8IoKI-1703099833-1-AehzT4bH3DVl0KALstLYfpgpJ1Hppws+ChfQLaWVhscSWvhtinQt1pzTiNiG9MF56/U7xrpk+FWeBFFSQRPQ6+o= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwNgmv47c03hQCMmTWYxYkDsXC69\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099932,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"It seems there was a mistake in the available + tools. Let's proceed without using a tool.\\n\\nTo research AI advancements, + I will need to look into the latest publications, articles, and releases in + the field of AI. Some of the key areas to focus on will be:\\n\\n1. Reinforcement + learning: This is a type of machine learning where an agent learns to make decisions + by taking actions in an environment to achieve a goal. The agent is rewarded + or punished (reinforcement signal) based on the results of its actions. The + latest advancements in this area could include new algorithms, applications, + and improvements in efficiency and scalability.\\n\\n2. Generative adversarial + networks (GANs): These are algorithmic architectures used in unsupervised learning, + where two neural networks contest with each other. Recent advancements could + involve new architectures, improved stability of training, and novel applications + of GANs.\\n\\n3. Natural language processing (NLP): This is a field of AI that + focuses on the interaction between computers and humans through language. The + latest advancements here could include new models for understanding and generating + human language, improved translation algorithms, and better sentiment analysis + algorithms.\\n\\n4. Computer vision: This field of AI involves enabling machines + to see and understand the content of digital images such as photographs and + videos. Latest advancements could be in the area of object recognition, image + generation, and real-time video analysis.\\n\\n5. Transfer learning: This is + a research problem in machine learning that focuses on storing knowledge gained + while solving one problem and applying it to a different but related problem. + The latest advancements could involve new methods for transferring knowledge + between tasks, improving the efficiency of transfer learning, and expanding + the range of tasks where it can be applied.\\n\\n6. AI in healthcare: AI is + revolutionizing healthcare with applications in diagnosis, treatment, patient + care, and management. The latest advancements could include new predictive models, + more efficient patient management systems, and improved medical imaging techniques.\\n\\n7. + AI ethics: As AI becomes more integrated into society, the ethical implications + become more significant. Latest advancements in this area could include new + guidelines for AI use, discussions on the impact of AI on employment, and considerations + on the use of AI in decision-making processes.\\n\\n8. AI startups: These companies + are at the forefront of AI development. The latest advancements could involve + new products or services, novel applications of AI, and significant funding + rounds or acquisitions. \\n\\nThese are some of the areas in AI that have seen + significant advancements recently. By focusing on these areas, I should be able + to provide a comprehensive research on the latest advancements in AI.\"\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n + \ \"usage\": {\n \"prompt_tokens\": 418,\n \"completion_tokens\": 516,\n + \ \"total_tokens\": 934\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3bd46c08a505-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:19:44 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '50968' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299520' + x-ratelimit-remaining-tokens_usage_based: + - '299520' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 95ms + x-ratelimit-reset-tokens_usage_based: + - 95ms + x-request-id: + - c7ef9599cf4d95797ac2c91f723eded7 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research + and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access + to the following tools:\n\n\n\nTo use a tool, please use the exact following + format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to + take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI for five interesting + and unique article ideas. The AI suggests: 1) an exploration of the evolution + of AI, from its earliest concepts to current technologies, 2) a look into the + use of AI in healthcare and how it''s shaping the future of medicine, 3) an + investigation into the ethical implications of AI, 4) a technical explanation + of how popular machine learning algorithms work, and 5) a profile on AI startups + and their potentially revolutionary products or services. When asked to research + AI advancements, the AI discusses reinforcement learning, generative adversarial + networks (GANs), natural language processing (NLP), computer vision, transfer + learning, AI in healthcare, AI ethics, and AI startups.\nBegin! This is VERY + important to you, your job depends on it!\n\nCurrent Task: Research AI advancements.\nThought: + Do I need to use a tool? Yes\nAction: Use the Web Search tool\nAction Input: + \"Latest advancements in AI\"\nObservation: Use the Web Search tool is not a + valid tool, try one of [].\nThought: It seems there was a mistake in the available + tools. Let''s proceed without using a tool.\n\nTo research AI advancements, + I will need to look into the latest publications, articles, and releases in + the field of AI. Some of the key areas to focus on will be:\n\n1. Reinforcement + learning: This is a type of machine learning where an agent learns to make decisions + by taking actions in an environment to achieve a goal. The agent is rewarded + or punished (reinforcement signal) based on the results of its actions. The + latest advancements in this area could include new algorithms, applications, + and improvements in efficiency and scalability.\n\n2. Generative adversarial + networks (GANs): These are algorithmic architectures used in unsupervised learning, + where two neural networks contest with each other. Recent advancements could + involve new architectures, improved stability of training, and novel applications + of GANs.\n\n3. Natural language processing (NLP): This is a field of AI that + focuses on the interaction between computers and humans through language. The + latest advancements here could include new models for understanding and generating + human language, improved translation algorithms, and better sentiment analysis + algorithms.\n\n4. Computer vision: This field of AI involves enabling machines + to see and understand the content of digital images such as photographs and + videos. Latest advancements could be in the area of object recognition, image + generation, and real-time video analysis.\n\n5. Transfer learning: This is a + research problem in machine learning that focuses on storing knowledge gained + while solving one problem and applying it to a different but related problem. + The latest advancements could involve new methods for transferring knowledge + between tasks, improving the efficiency of transfer learning, and expanding + the range of tasks where it can be applied.\n\n6. AI in healthcare: AI is revolutionizing + healthcare with applications in diagnosis, treatment, patient care, and management. + The latest advancements could include new predictive models, more efficient + patient management systems, and improved medical imaging techniques.\n\n7. AI + ethics: As AI becomes more integrated into society, the ethical implications + become more significant. Latest advancements in this area could include new + guidelines for AI use, discussions on the impact of AI on employment, and considerations + on the use of AI in decision-making processes.\n\n8. AI startups: These companies + are at the forefront of AI development. The latest advancements could involve + new products or services, novel applications of AI, and significant funding + rounds or acquisitions. \n\nThese are some of the areas in AI that have seen + significant advancements recently. By focusing on these areas, I should be able + to provide a comprehensive research on the latest advancements in AI.\nObservation: + Invalid Format: Missing ''Action:'' after ''Thought:\nThought: \n"}], "model": + "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '4977' + content-type: + - application/json + cookie: + - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000; + __cf_bm=5B5UNtJ.5znx6uxkns4_5xRr40XRPyeUm399zz8IoKI-1703099833-1-AehzT4bH3DVl0KALstLYfpgpJ1Hppws+ChfQLaWVhscSWvhtinQt1pzTiNiG9MF56/U7xrpk+FWeBFFSQRPQ6+o= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwOWMCgoSpGdUA15hfvpG8Ung8dh\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099984,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + To research AI advancements, I will need to look into the latest publications, + articles, and releases in the field of AI. Some of the key areas to focus on + will be:\\n\\n1. Reinforcement learning: This is a type of machine learning + where an agent learns to make decisions by taking actions in an environment + to achieve a goal. The agent is rewarded or punished (reinforcement signal) + based on the results of its actions. The latest advancements in this area could + include new algorithms, applications, and improvements in efficiency and scalability.\\n\\n2. + Generative adversarial networks (GANs): These are algorithmic architectures + used in unsupervised learning, where two neural networks contest with each other. + Recent advancements could involve new architectures, improved stability of training, + and novel applications of GANs.\\n\\n3. Natural language processing (NLP): This + is a field of AI that focuses on the interaction between computers and humans + through language. The latest advancements here could include new models for + understanding and generating human language, improved translation algorithms, + and better sentiment analysis algorithms.\\n\\n4. Computer vision: This field + of AI involves enabling machines to see and understand the content of digital + images such as photographs and videos. Latest advancements could be in the area + of object recognition, image generation, and real-time video analysis.\\n\\n5. + Transfer learning: This is a research problem in machine learning that focuses + on storing knowledge gained while solving one problem and applying it to a different + but related problem. The latest advancements could involve new methods for transferring + knowledge between tasks, improving the efficiency of transfer learning, and + expanding the range of tasks where it can be applied.\\n\\n6. AI in healthcare: + AI is revolutionizing healthcare with applications in diagnosis, treatment, + patient care, and management. The latest advancements could include new predictive + models, more efficient patient management systems, and improved medical imaging + techniques.\\n\\n7. AI ethics: As AI becomes more integrated into society, the + ethical implications become more significant. Latest advancements in this area + could include new guidelines for AI use, discussions on the impact of AI on + employment, and considerations on the use of AI in decision-making processes.\\n\\n8. + AI startups: These companies are at the forefront of AI development. The latest + advancements could involve new products or services, novel applications of AI, + and significant funding rounds or acquisitions. \\n\\nThese are some of the + areas in AI that have seen significant advancements recently. By focusing on + these areas, I should be able to provide a comprehensive research on the latest + advancements in AI.\"\n },\n \"logprobs\": null,\n \"finish_reason\": + \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 950,\n \"completion_tokens\": + 510,\n \"total_tokens\": 1460\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3d1478e8a505-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:20:39 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '55123' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '298788' + x-ratelimit-remaining-tokens_usage_based: + - '298788' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 242ms + x-ratelimit-reset-tokens_usage_based: + - 242ms + x-request-id: + - 7ba999cdfd9efcb3ab8666fd7bb50e9d + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI for five interesting and + unique article ideas. The AI suggests: 1) an exploration of the evolution of + AI, from its earliest concepts to current technologies, 2) a look into the use + of AI in healthcare and how it''s shaping the future of medicine, 3) an investigation + into the ethical implications of AI, 4) a technical explanation of how popular + machine learning algorithms work, and 5) a profile on AI startups and their + potentially revolutionary products or services. When asked to research AI advancements, + the AI discusses reinforcement learning, generative adversarial networks (GANs), + natural language processing (NLP), computer vision, transfer learning, AI in + healthcare, AI ethics, and AI startups.\n\nNew lines of conversation:\nHuman: + Research AI advancements.\nAI: To research AI advancements, I will need to look + into the latest publications, articles, and releases in the field of AI. Some + of the key areas to focus on will be:\n\n1. Reinforcement learning: This is + a type of machine learning where an agent learns to make decisions by taking + actions in an environment to achieve a goal. The agent is rewarded or punished + (reinforcement signal) based on the results of its actions. The latest advancements + in this area could include new algorithms, applications, and improvements in + efficiency and scalability.\n\n2. Generative adversarial networks (GANs): These + are algorithmic architectures used in unsupervised learning, where two neural + networks contest with each other. Recent advancements could involve new architectures, + improved stability of training, and novel applications of GANs.\n\n3. Natural + language processing (NLP): This is a field of AI that focuses on the interaction + between computers and humans through language. The latest advancements here + could include new models for understanding and generating human language, improved + translation algorithms, and better sentiment analysis algorithms.\n\n4. Computer + vision: This field of AI involves enabling machines to see and understand the + content of digital images such as photographs and videos. Latest advancements + could be in the area of object recognition, image generation, and real-time + video analysis.\n\n5. Transfer learning: This is a research problem in machine + learning that focuses on storing knowledge gained while solving one problem + and applying it to a different but related problem. The latest advancements + could involve new methods for transferring knowledge between tasks, improving + the efficiency of transfer learning, and expanding the range of tasks where + it can be applied.\n\n6. AI in healthcare: AI is revolutionizing healthcare + with applications in diagnosis, treatment, patient care, and management. The + latest advancements could include new predictive models, more efficient patient + management systems, and improved medical imaging techniques.\n\n7. AI ethics: + As AI becomes more integrated into society, the ethical implications become + more significant. Latest advancements in this area could include new guidelines + for AI use, discussions on the impact of AI on employment, and considerations + on the use of AI in decision-making processes.\n\n8. AI startups: These companies + are at the forefront of AI development. The latest advancements could involve + new products or services, novel applications of AI, and significant funding + rounds or acquisitions. \n\nThese are some of the areas in AI that have seen + significant advancements recently. By focusing on these areas, I should be able + to provide a comprehensive research on the latest advancements in AI.\n\nNew + summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '4393' + content-type: + - application/json + cookie: + - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000; + __cf_bm=5B5UNtJ.5znx6uxkns4_5xRr40XRPyeUm399zz8IoKI-1703099833-1-AehzT4bH3DVl0KALstLYfpgpJ1Hppws+ChfQLaWVhscSWvhtinQt1pzTiNiG9MF56/U7xrpk+FWeBFFSQRPQ6+o= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwPPHMRYdZQO4aJyh56xfPmGxKZI\",\n \"object\": + \"chat.completion\",\n \"created\": 1703100039,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI for five interesting + and unique article ideas, and to research AI advancements. The AI suggests articles + about the evolution of AI, its use in healthcare, ethical implications, machine + learning algorithms, and AI startups. To research AI advancements, the AI proposes + to examine recent developments in reinforcement learning, generative adversarial + networks (GANs), natural language processing (NLP), computer vision, transfer + learning, AI in healthcare, AI ethics, and AI startups. The AI will focus on + new methods, applications, improvements, models, systems, guidelines, and products + or services in these areas for a comprehensive research on the latest advancements + in AI.\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 786,\n \"completion_tokens\": + 130,\n \"total_tokens\": 916\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3e6ecd7ca505-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:20:54 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '14849' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '298922' + x-ratelimit-remaining-tokens_usage_based: + - '298922' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 215ms + x-ratelimit-reset-tokens_usage_based: + - 215ms + x-request-id: + - 37dfceb88f50067612d5281e38c6251b + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Senior Writer.\nYou''re + a senior writer, specialized in technology, software engineering, AI and startups. + You work as a freelancer and are now working on writing content for a new customer.\n\nYour + personal goal is: Write the best content about AI and AI agents.\n\nTOOLS:\n------\nYou + have access to the following tools:\n\n\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI to write about + several AI-related topics: the history of AI, AI''s role in healthcare, ethical + considerations in AI, understanding AI algorithms, AI startups, and AI agents. + The AI provides detailed paragraphs for each topic, discussing the evolution + and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas + in AI development and use, the intricacies of AI algorithms, the pioneering + role of AI startups in the tech industry, and the roles and potential of AI + agents. The AI then presents an expansive list of recent AI advancements, including + reinforcement learning, generative adversarial networks (GANs), natural language + processing (NLP), computer vision, transfer learning, AI in healthcare, AI ethics, + and AI startups. Upon the human''s request, the AI elaborates on AI in healthcare. + It discusses how AI revolutionizes healthcare through early deterioration prediction, + automated monitoring, disease pattern identification, clinical note interpretation, + image-based diagnostics, and personalized health insights while also raising + ethical issues around data privacy and decision transparency.\nBegin! This is + VERY important to you, your job depends on it!\n\nCurrent Task: Write about + AI in healthcare.\n\nThis is the context you are working with:\nTo research + AI advancements, I will need to look into the latest publications, articles, + and releases in the field of AI. Some of the key areas to focus on will be:\n\n1. + Reinforcement learning: This is a type of machine learning where an agent learns + to make decisions by taking actions in an environment to achieve a goal. The + agent is rewarded or punished (reinforcement signal) based on the results of + its actions. The latest advancements in this area could include new algorithms, + applications, and improvements in efficiency and scalability.\n\n2. Generative + adversarial networks (GANs): These are algorithmic architectures used in unsupervised + learning, where two neural networks contest with each other. Recent advancements + could involve new architectures, improved stability of training, and novel applications + of GANs.\n\n3. Natural language processing (NLP): This is a field of AI that + focuses on the interaction between computers and humans through language. The + latest advancements here could include new models for understanding and generating + human language, improved translation algorithms, and better sentiment analysis + algorithms.\n\n4. Computer vision: This field of AI involves enabling machines + to see and understand the content of digital images such as photographs and + videos. Latest advancements could be in the area of object recognition, image + generation, and real-time video analysis.\n\n5. Transfer learning: This is a + research problem in machine learning that focuses on storing knowledge gained + while solving one problem and applying it to a different but related problem. + The latest advancements could involve new methods for transferring knowledge + between tasks, improving the efficiency of transfer learning, and expanding + the range of tasks where it can be applied.\n\n6. AI in healthcare: AI is revolutionizing + healthcare with applications in diagnosis, treatment, patient care, and management. + The latest advancements could include new predictive models, more efficient + patient management systems, and improved medical imaging techniques.\n\n7. AI + ethics: As AI becomes more integrated into society, the ethical implications + become more significant. Latest advancements in this area could include new + guidelines for AI use, discussions on the impact of AI on employment, and considerations + on the use of AI in decision-making processes.\n\n8. AI startups: These companies + are at the forefront of AI development. The latest advancements could involve + new products or services, novel applications of AI, and significant funding + rounds or acquisitions. \n\nThese are some of the areas in AI that have seen + significant advancements recently. By focusing on these areas, I should be able + to provide a comprehensive research on the latest advancements in AI.\n\n"}], + "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": + 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '5043' + content-type: + - application/json + cookie: + - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000; + __cf_bm=lM319LPDEnvF96Mm4S90dEPrAGj1BHp.EoL8Zh1oCkU-1703099793-1-AS7kVNRnez1R9AZHZcWMDEIHZ3+Ay1dO+6ucbsMG+Euq+B+uku7GPY+Yz9hBZVDn+UTIJAw5aBsQH3U34sHaie4= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwPfAHioUoLdrVxlV2zBXYc1B9lV\",\n \"object\": + \"chat.completion\",\n \"created\": 1703100055,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\nFinal + Answer: Artificial Intelligence (AI) in healthcare is an increasingly significant + field, with numerous advancements revolutionizing diagnosis, treatment, patient + care, and healthcare management. \\n\\nAI in diagnosis: Machine learning algorithms + can analyze complex medical data to assist in accurate diagnosis. Recent advancements + include the development of AI systems that can detect conditions such as cancer + or heart disease earlier and with more accuracy than traditional methods. \\n\\nAI + in treatment: AI can assist in personalized medicine by analyzing a patient's + genetic makeup, lifestyle, and other health data to tailor treatments specifically + for them. Furthermore, AI can optimize treatment plans, reducing the risk of + harmful side effects. \\n\\nAI in patient care: Advancements in AI have led + to the development of 'virtual nursing assistants' that can monitor patients + and help manage post-treatment care. These AI systems can provide 24/7 assistance, + answering patient queries, and providing timely reminders for medication.\\n\\nAI + in healthcare management: AI applications can optimize scheduling, manage patient + data efficiently, and predict patient admission rates, helping to improve overall + hospital management.\\n\\nHowever, with these advancements also come challenges. + Data privacy is a significant concern, as AI systems often need extensive personal + health data to function effectively. Ensuring the transparent and ethical use + of AI, while maximizing its benefits, is a crucial aspect of AI in healthcare.\\n\\nAI + is transforming healthcare, promising a future where diagnosis is more accurate, + treatment is personalized, patient care is improved, and healthcare management + is more efficient. These advancements have the potential to significantly improve + patient outcomes and the overall quality of healthcare services.\"\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n + \ \"usage\": {\n \"prompt_tokens\": 931,\n \"completion_tokens\": 323,\n + \ \"total_tokens\": 1254\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3ecffa571aab-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:21:33 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '37782' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '298770' + x-ratelimit-remaining-tokens_usage_based: + - '298770' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 246ms + x-ratelimit-reset-tokens_usage_based: + - 246ms + x-request-id: + - e0be4aa85b9ab570aac1f17a613912ed + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to write about several + AI-related topics: the history of AI, AI''s role in healthcare, ethical considerations + in AI, understanding AI algorithms, AI startups, and AI agents. The AI provides + detailed paragraphs for each topic, discussing the evolution and impact of AI, + the transformative role of AI in healthcare, the ethical dilemmas in AI development + and use, the intricacies of AI algorithms, the pioneering role of AI startups + in the tech industry, and the roles and potential of AI agents. The AI then + presents an expansive list of recent AI advancements, including reinforcement + learning, generative adversarial networks (GANs), natural language processing + (NLP), computer vision, transfer learning, AI in healthcare, AI ethics, and + AI startups. Upon the human''s request, the AI elaborates on AI in healthcare. + It discusses how AI revolutionizes healthcare through early deterioration prediction, + automated monitoring, disease pattern identification, clinical note interpretation, + image-based diagnostics, and personalized health insights while also raising + ethical issues around data privacy and decision transparency.\n\nNew lines of + conversation:\nHuman: Write about AI in healthcare.\n\nThis is the context you + are working with:\nTo research AI advancements, I will need to look into the + latest publications, articles, and releases in the field of AI. Some of the + key areas to focus on will be:\n\n1. Reinforcement learning: This is a type + of machine learning where an agent learns to make decisions by taking actions + in an environment to achieve a goal. The agent is rewarded or punished (reinforcement + signal) based on the results of its actions. The latest advancements in this + area could include new algorithms, applications, and improvements in efficiency + and scalability.\n\n2. Generative adversarial networks (GANs): These are algorithmic + architectures used in unsupervised learning, where two neural networks contest + with each other. Recent advancements could involve new architectures, improved + stability of training, and novel applications of GANs.\n\n3. Natural language + processing (NLP): This is a field of AI that focuses on the interaction between + computers and humans through language. The latest advancements here could include + new models for understanding and generating human language, improved translation + algorithms, and better sentiment analysis algorithms.\n\n4. Computer vision: + This field of AI involves enabling machines to see and understand the content + of digital images such as photographs and videos. Latest advancements could + be in the area of object recognition, image generation, and real-time video + analysis.\n\n5. Transfer learning: This is a research problem in machine learning + that focuses on storing knowledge gained while solving one problem and applying + it to a different but related problem. The latest advancements could involve + new methods for transferring knowledge between tasks, improving the efficiency + of transfer learning, and expanding the range of tasks where it can be applied.\n\n6. + AI in healthcare: AI is revolutionizing healthcare with applications in diagnosis, + treatment, patient care, and management. The latest advancements could include + new predictive models, more efficient patient management systems, and improved + medical imaging techniques.\n\n7. AI ethics: As AI becomes more integrated into + society, the ethical implications become more significant. Latest advancements + in this area could include new guidelines for AI use, discussions on the impact + of AI on employment, and considerations on the use of AI in decision-making + processes.\n\n8. AI startups: These companies are at the forefront of AI development. + The latest advancements could involve new products or services, novel applications + of AI, and significant funding rounds or acquisitions. \n\nThese are some of + the areas in AI that have seen significant advancements recently. By focusing + on these areas, I should be able to provide a comprehensive research on the + latest advancements in AI.\nAI: Artificial Intelligence (AI) in healthcare is + an increasingly significant field, with numerous advancements revolutionizing + diagnosis, treatment, patient care, and healthcare management. \n\nAI in diagnosis: + Machine learning algorithms can analyze complex medical data to assist in accurate + diagnosis. Recent advancements include the development of AI systems that can + detect conditions such as cancer or heart disease earlier and with more accuracy + than traditional methods. \n\nAI in treatment: AI can assist in personalized + medicine by analyzing a patient''s genetic makeup, lifestyle, and other health + data to tailor treatments specifically for them. Furthermore, AI can optimize + treatment plans, reducing the risk of harmful side effects. \n\nAI in patient + care: Advancements in AI have led to the development of ''virtual nursing assistants'' + that can monitor patients and help manage post-treatment care. These AI systems + can provide 24/7 assistance, answering patient queries, and providing timely + reminders for medication.\n\nAI in healthcare management: AI applications can + optimize scheduling, manage patient data efficiently, and predict patient admission + rates, helping to improve overall hospital management.\n\nHowever, with these + advancements also come challenges. Data privacy is a significant concern, as + AI systems often need extensive personal health data to function effectively. + Ensuring the transparent and ethical use of AI, while maximizing its benefits, + is a crucial aspect of AI in healthcare.\n\nAI is transforming healthcare, promising + a future where diagnosis is more accurate, treatment is personalized, patient + care is improved, and healthcare management is more efficient. These advancements + have the potential to significantly improve patient outcomes and the overall + quality of healthcare services.\n\nNew summary:"}], "model": "gpt-4", "n": 1, + "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '6692' + content-type: + - application/json + cookie: + - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000; + __cf_bm=lM319LPDEnvF96Mm4S90dEPrAGj1BHp.EoL8Zh1oCkU-1703099793-1-AS7kVNRnez1R9AZHZcWMDEIHZ3+Ay1dO+6ucbsMG+Euq+B+uku7GPY+Yz9hBZVDn+UTIJAw5aBsQH3U34sHaie4= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwQHcJj9785PdBbeIdMH8wbd6kZH\",\n \"object\": + \"chat.completion\",\n \"created\": 1703100093,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI to write about + several AI-related topics: the history of AI, AI's role in healthcare, ethical + considerations in AI, understanding AI algorithms, AI startups, and AI agents. + The AI provides detailed paragraphs for each topic, discussing the evolution + and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas + in AI development and use, the intricacies of AI algorithms, the pioneering + role of AI startups in the tech industry, and the roles and potential of AI + agents. The AI then presents an expansive list of recent AI advancements, including + reinforcement learning, generative adversarial networks (GANs), natural language + processing (NLP), computer vision, transfer learning, AI in healthcare, AI ethics, + and AI startups. Upon the human's request, the AI elaborates on AI in healthcare. + It mentions how AI is revolutionizing healthcare through advancements in diagnosis, + treatment, patient care, and management, while highlighting the ethical challenges + related to data privacy and transparency. The AI envisions a future where healthcare + is more accurate, personalized, and efficient due to these advancements.\"\n + \ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n + \ ],\n \"usage\": {\n \"prompt_tokens\": 1167,\n \"completion_tokens\": + 220,\n \"total_tokens\": 1387\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3fbdce211aab-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:21:55 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '22478' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '298350' + x-ratelimit-remaining-tokens_usage_based: + - '298350' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 329ms + x-ratelimit-reset-tokens_usage_based: + - 329ms + x-request-id: + - e36b1ea0f03187fe330e0b6f335fc5fe + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/cassettes/test_crew_with_delegating_agents.yaml b/tests/cassettes/test_crew_with_delegating_agents.yaml new file mode 100644 index 000000000..4969dd2c2 --- /dev/null +++ b/tests/cassettes/test_crew_with_delegating_agents.yaml @@ -0,0 +1,677 @@ +interactions: +- request: + body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long + time CEO of a content creation agency with a Senior Writer on the team. You''re + now working on a new project and want to make sure the content produced is amazing.\n\nYour + personal goal is: Make sure the writers in your company produce amazing content.\n\nTOOLS:\n------\nYou + have access to the following tools:\n\nDelegate Work to Co-Worker: Useful to + delegate a specific task to one of the \n\t\t\t\tfollowing co-workers: [CEO, + Senior Writer].\n\t\t\t\tThe input to this tool should be a pipe (|) separated + text of length\n\t\t\t\tthree, representing the role you want to delegate it + to, the task and \n\t\t\t\tinformation necessary. For example, `coworker|task|information`.\n\nAsk + Question to Co-Worker: Useful to ask a question, opinion or take from on\n\t\t\t\tof + the following co-workers: [CEO, Senior Writer]. \n\t\t\t\tThe input to this + tool should be a pipe (|) separated text of length \n\t\t\t\tthree, representing + the role you want to ask it to, the question and \n\t\t\t\tinformation necessary. + For example, `coworker|question|information`.\n\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [Delegate Work to Co-Worker, Ask Question + to Co-Worker]\nAction Input: the input to the action\nObservation: the result + of the action\n```\n\nWhen you have a response for your task, or if you do not + need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use + a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary + of your work so far:\n \nBegin! This is VERY important to you, your job depends + on it!\n\nCurrent Task: Produce and amazing 1 paragraph draft of an article + about AI Agents.\n\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], + "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1907' + content-type: + - application/json + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwL0C0AeNFxBDtNxKvF4g4SpBHMy\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099766,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? Yes\\nAction: + Delegate Work to Co-Worker\\nAction Input: Senior Writer|Create a compelling + and engaging 1 paragraph draft of an article about AI Agents|Provide a brief + yet comprehensive overview of AI agents, their uses, and implications in the + current world. Make sure to emphasize their potential and the role they can + play in the future. The tone should be informative but captivating. \"\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n + \ \"usage\": {\n \"prompt_tokens\": 415,\n \"completion_tokens\": 88,\n + \ \"total_tokens\": 503\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a37c488c8a51d-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:16:16 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=o0Hi1R.X9SlINxIJTVmbndjXrZ0hKGumMHX9teXwypc-1703099776-1-AYizrWsw5e5xpAQYK2ILXGT8XFsMG/cUywCKEtgqcBAn361e23iU23y2rsxZge9SVmHfbz+ltf8zup2qIqhAfWM=; + path=/; expires=Wed, 20-Dec-23 19:46:16 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + - _cfuvid=ps.JYe.5DT5QaG1hDuUb70tnVJo8IPWJrGrGEO_HUYA-1703099776177-0-604800000; + path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '9246' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299559' + x-ratelimit-remaining-tokens_usage_based: + - '299559' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 88ms + x-ratelimit-reset-tokens_usage_based: + - 88ms + x-request-id: + - a893482a313d58b1b40f4af679855361 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are Senior Writer.\nYou''re + a senior writer, specialized in technology, software engineering, AI and startups. + You work as a freelancer and are now working on writing content for a new customer.\n\nYour + personal goal is: Write the best content about AI and AI agents.\n\nTOOLS:\n------\nYou + have access to the following tools:\n\n\n\nTo use a tool, please use the exact + following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the + action to take, should be one of []\nAction Input: the input to the action\nObservation: + the result of the action\n```\n\nWhen you have a response for your task, or + if you do not need to use a tool, you MUST use the format:\n\n```\nThought: + Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis + is the summary of your work so far:\n The human asks the AI to write a paragraph + for each of five AI-related topics, highlighting how each could make for an + interesting article. The proposed topics are: the history of AI, AI''s role + in healthcare, ethical considerations in AI, understanding AI algorithms, and + AI startups. The AI provides detailed overviews for each topic, emphasizing + the evolution and impact of AI, the transformative role of AI in healthcare, + the ethical dilemmas faced in AI development and use, the intricacies of AI + algorithms, and the pioneering role of AI startups in the tech industry.\nBegin! + This is VERY important to you, your job depends on it!\n\nCurrent Task: Create + a compelling and engaging 1 paragraph draft of an article about AI Agents\n\nThis + is the context you are working with:\nProvide a brief yet comprehensive overview + of AI agents, their uses, and implications in the current world. Make sure to + emphasize their potential and the role they can play in the future. The tone + should be informative but captivating.\n\n"}], "model": "gpt-4", "n": 1, "stop": + ["\nObservation"], "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1969' + content-type: + - application/json + cookie: + - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwLAvsNLsRlvTVGewBsy2sHjUuvo\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099776,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Thought: Do I need to use a tool? No\\n\\nFinal + Answer: \\\"AI agents, the digital masterminds at the heart of the 21st-century + revolution, are shaping a new era of intelligence and innovation. They are autonomous + entities, capable of observing their environment, making decisions, and acting + on them, all in pursuit of a specific goal. From streamlining operations in + logistics to personalizing customer experiences in retail, AI agents are transforming + how businesses operate. But their potential extends far beyond the corporate + world. They are the sentinels protecting our digital frontiers, the virtual + assistants making our lives easier, and the unseen hands guiding autonomous + vehicles. As this technology evolves, AI agents will play an increasingly central + role in our world, ushering in an era of unprecedented efficiency, personalization, + and productivity. But with great power comes great responsibility, and understanding + and harnessing this potential responsibly will be one of our greatest challenges + and opportunities in the coming years.\\\"\"\n },\n \"logprobs\": + null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 391,\n \"completion_tokens\": 194,\n \"total_tokens\": 585\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a3801ecc3a632-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:16:33 GMT + Server: + - cloudflare + Set-Cookie: + - __cf_bm=lM319LPDEnvF96Mm4S90dEPrAGj1BHp.EoL8Zh1oCkU-1703099793-1-AS7kVNRnez1R9AZHZcWMDEIHZ3+Ay1dO+6ucbsMG+Euq+B+uku7GPY+Yz9hBZVDn+UTIJAw5aBsQH3U34sHaie4=; + path=/; expires=Wed, 20-Dec-23 19:46:33 GMT; domain=.api.openai.com; HttpOnly; + Secure; SameSite=None + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '16857' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299534' + x-ratelimit-remaining-tokens_usage_based: + - '299534' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 93ms + x-ratelimit-reset-tokens_usage_based: + - 93ms + x-request-id: + - d158efaaade6655137aaa299ea674831 + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\nThe human asks the AI to write a paragraph for + each of five AI-related topics, highlighting how each could make for an interesting + article. The proposed topics are: the history of AI, AI''s role in healthcare, + ethical considerations in AI, understanding AI algorithms, and AI startups. + The AI provides detailed overviews for each topic, emphasizing the evolution + and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas + faced in AI development and use, the intricacies of AI algorithms, and the pioneering + role of AI startups in the tech industry.\n\nNew lines of conversation:\nHuman: + Create a compelling and engaging 1 paragraph draft of an article about AI Agents\n\nThis + is the context you are working with:\nProvide a brief yet comprehensive overview + of AI agents, their uses, and implications in the current world. Make sure to + emphasize their potential and the role they can play in the future. The tone + should be informative but captivating.\nAI: \"AI agents, the digital masterminds + at the heart of the 21st-century revolution, are shaping a new era of intelligence + and innovation. They are autonomous entities, capable of observing their environment, + making decisions, and acting on them, all in pursuit of a specific goal. From + streamlining operations in logistics to personalizing customer experiences in + retail, AI agents are transforming how businesses operate. But their potential + extends far beyond the corporate world. They are the sentinels protecting our + digital frontiers, the virtual assistants making our lives easier, and the unseen + hands guiding autonomous vehicles. As this technology evolves, AI agents will + play an increasingly central role in our world, ushering in an era of unprecedented + efficiency, personalization, and productivity. But with great power comes great + responsibility, and understanding and harnessing this potential responsibly + will be one of our greatest challenges and opportunities in the coming years.\"\n\nNew + summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '2786' + content-type: + - application/json + cookie: + - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000; + __cf_bm=lM319LPDEnvF96Mm4S90dEPrAGj1BHp.EoL8Zh1oCkU-1703099793-1-AS7kVNRnez1R9AZHZcWMDEIHZ3+Ay1dO+6ucbsMG+Euq+B+uku7GPY+Yz9hBZVDn+UTIJAw5aBsQH3U34sHaie4= + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwLRKqCp8gf0ELMrLkRepygaoLrI\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099793,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI to write a paragraph + for each of five AI-related topics: the history of AI, AI's role in healthcare, + ethical considerations in AI, understanding AI algorithms, and AI startups. + The AI provides detailed overviews for each topic, emphasizing the evolution + and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas + faced in AI development and use, the intricacies of AI algorithms, and the pioneering + role of AI startups in the tech industry. The human then asks the AI to draft + a paragraph about AI Agents. The AI creates an engaging overview of AI agents, + discussing their roles, potential, and implications in the current world, highlighting + their transformative impact on various sectors and their potential for the future + while noting the importance of responsibly harnessing this potential.\"\n },\n + \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n + \ \"usage\": {\n \"prompt_tokens\": 498,\n \"completion_tokens\": 158,\n + \ \"total_tokens\": 656\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a386d398da632-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:16:50 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '16935' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299320' + x-ratelimit-remaining-tokens_usage_based: + - '299320' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 136ms + x-ratelimit-reset-tokens_usage_based: + - 136ms + x-request-id: + - c4705d7c284541ec74df0a25eb51aa7f + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long + time CEO of a content creation agency with a Senior Writer on the team. You''re + now working on a new project and want to make sure the content produced is amazing.\n\nYour + personal goal is: Make sure the writers in your company produce amazing content.\n\nTOOLS:\n------\nYou + have access to the following tools:\n\nDelegate Work to Co-Worker: Useful to + delegate a specific task to one of the \n\t\t\t\tfollowing co-workers: [CEO, + Senior Writer].\n\t\t\t\tThe input to this tool should be a pipe (|) separated + text of length\n\t\t\t\tthree, representing the role you want to delegate it + to, the task and \n\t\t\t\tinformation necessary. For example, `coworker|task|information`.\n\nAsk + Question to Co-Worker: Useful to ask a question, opinion or take from on\n\t\t\t\tof + the following co-workers: [CEO, Senior Writer]. \n\t\t\t\tThe input to this + tool should be a pipe (|) separated text of length \n\t\t\t\tthree, representing + the role you want to ask it to, the question and \n\t\t\t\tinformation necessary. + For example, `coworker|question|information`.\n\n\nTo use a tool, please use + the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: + the action to take, should be one of [Delegate Work to Co-Worker, Ask Question + to Co-Worker]\nAction Input: the input to the action\nObservation: the result + of the action\n```\n\nWhen you have a response for your task, or if you do not + need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use + a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary + of your work so far:\n \nBegin! This is VERY important to you, your job depends + on it!\n\nCurrent Task: Produce and amazing 1 paragraph draft of an article + about AI Agents.\nThought: Do I need to use a tool? Yes\nAction: Delegate Work + to Co-Worker\nAction Input: Senior Writer|Create a compelling and engaging 1 + paragraph draft of an article about AI Agents|Provide a brief yet comprehensive + overview of AI agents, their uses, and implications in the current world. Make + sure to emphasize their potential and the role they can play in the future. + The tone should be informative but captivating. \nObservation: \"AI agents, + the digital masterminds at the heart of the 21st-century revolution, are shaping + a new era of intelligence and innovation. They are autonomous entities, capable + of observing their environment, making decisions, and acting on them, all in + pursuit of a specific goal. From streamlining operations in logistics to personalizing + customer experiences in retail, AI agents are transforming how businesses operate. + But their potential extends far beyond the corporate world. They are the sentinels + protecting our digital frontiers, the virtual assistants making our lives easier, + and the unseen hands guiding autonomous vehicles. As this technology evolves, + AI agents will play an increasingly central role in our world, ushering in an + era of unprecedented efficiency, personalization, and productivity. But with + great power comes great responsibility, and understanding and harnessing this + potential responsibly will be one of our greatest challenges and opportunities + in the coming years.\"\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], + "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '3352' + content-type: + - application/json + cookie: + - __cf_bm=o0Hi1R.X9SlINxIJTVmbndjXrZ0hKGumMHX9teXwypc-1703099776-1-AYizrWsw5e5xpAQYK2ILXGT8XFsMG/cUywCKEtgqcBAn361e23iU23y2rsxZge9SVmHfbz+ltf8zup2qIqhAfWM=; + _cfuvid=ps.JYe.5DT5QaG1hDuUb70tnVJo8IPWJrGrGEO_HUYA-1703099776177-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwLixNfdsK3l1iSw7Uf11mrHwOwr\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099810,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"Do I need to use a tool? No\\nFinal Answer: + The Senior Writer has created a compelling and engaging 1 paragraph draft about + AI agents. The paragraph provides a brief yet comprehensive overview of AI agents, + their uses, and implications in the current world. It emphasizes their potential + and the role they can play in the future. The tone is informative but captivating, + meeting the objectives of the task.\"\n },\n \"logprobs\": null,\n + \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": + 688,\n \"completion_tokens\": 80,\n \"total_tokens\": 768\n },\n \"system_fingerprint\": + null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a38d99b590199-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:17:02 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '11599' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299200' + x-ratelimit-remaining-tokens_usage_based: + - '299200' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 160ms + x-ratelimit-reset-tokens_usage_based: + - 160ms + x-request-id: + - 91515805acf37358b0e3b73fa4b302ed + http_version: HTTP/1.1 + status_code: 200 +- request: + body: '{"messages": [{"role": "user", "content": "Progressively summarize the + lines of conversation provided, adding onto the previous summary returning a + new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks + of artificial intelligence. The AI thinks artificial intelligence is a force + for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial + intelligence is a force for good?\nAI: Because artificial intelligence will + help humans reach their full potential.\n\nNew summary:\nThe human asks what + the AI thinks of artificial intelligence. The AI thinks artificial intelligence + is a force for good because it will help humans reach their full potential.\nEND + OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Produce + and amazing 1 paragraph draft of an article about AI Agents.\nAI: The Senior + Writer has created a compelling and engaging 1 paragraph draft about AI agents. + The paragraph provides a brief yet comprehensive overview of AI agents, their + uses, and implications in the current world. It emphasizes their potential and + the role they can play in the future. The tone is informative but captivating, + meeting the objectives of the task.\n\nNew summary:"}], "model": "gpt-4", "n": + 1, "stream": false, "temperature": 0.7}' + headers: + accept: + - application/json + accept-encoding: + - gzip, deflate + connection: + - keep-alive + content-length: + - '1282' + content-type: + - application/json + cookie: + - __cf_bm=o0Hi1R.X9SlINxIJTVmbndjXrZ0hKGumMHX9teXwypc-1703099776-1-AYizrWsw5e5xpAQYK2ILXGT8XFsMG/cUywCKEtgqcBAn361e23iU23y2rsxZge9SVmHfbz+ltf8zup2qIqhAfWM=; + _cfuvid=ps.JYe.5DT5QaG1hDuUb70tnVJo8IPWJrGrGEO_HUYA-1703099776177-0-604800000 + host: + - api.openai.com + user-agent: + - OpenAI/Python 1.6.0 + x-stainless-arch: + - arm64 + x-stainless-async: + - 'false' + x-stainless-lang: + - python + x-stainless-os: + - MacOS + x-stainless-package-version: + - 1.6.0 + 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-8XwLutLT441lOLap9gUd0ttpfvq8b\",\n \"object\": + \"chat.completion\",\n \"created\": 1703099822,\n \"model\": \"gpt-4-0613\",\n + \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": + \"assistant\",\n \"content\": \"The human asks the AI to produce a draft + of an article about AI agents. The AI responds by creating a compelling and + engaging paragraph that provides a comprehensive overview of AI agents, their + uses, and implications in the current world, emphasizing their potential future + role.\"\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n + \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 219,\n \"completion_tokens\": + 51,\n \"total_tokens\": 270\n },\n \"system_fingerprint\": null\n}\n" + headers: + CF-Cache-Status: + - DYNAMIC + CF-RAY: + - 838a39248aa10199-GRU + Cache-Control: + - no-cache, must-revalidate + Connection: + - keep-alive + Content-Encoding: + - gzip + Content-Type: + - application/json + Date: + - Wed, 20 Dec 2023 19:17:10 GMT + Server: + - cloudflare + Transfer-Encoding: + - chunked + access-control-allow-origin: + - '*' + alt-svc: + - h3=":443"; ma=86400 + openai-model: + - gpt-4-0613 + openai-organization: + - user-z7g4wmlazxqvc5wjyaaaocfz + openai-processing-ms: + - '7304' + openai-version: + - '2020-10-01' + strict-transport-security: + - max-age=15724800; includeSubDomains + x-ratelimit-limit-requests: + - '10000' + x-ratelimit-limit-tokens: + - '300000' + x-ratelimit-limit-tokens_usage_based: + - '300000' + x-ratelimit-remaining-requests: + - '9999' + x-ratelimit-remaining-tokens: + - '299695' + x-ratelimit-remaining-tokens_usage_based: + - '299695' + x-ratelimit-reset-requests: + - 6ms + x-ratelimit-reset-tokens: + - 61ms + x-ratelimit-reset-tokens_usage_based: + - 61ms + x-request-id: + - 70b697c208659cf5af8ff46e2fc0ab69 + http_version: HTTP/1.1 + status_code: 200 +version: 1 diff --git a/tests/crew_test.py b/tests/crew_test.py index e6c543392..388c74da3 100644 --- a/tests/crew_test.py +++ b/tests/crew_test.py @@ -89,7 +89,7 @@ def test_crew_config_with_wrong_keys(): with pytest.raises(ValueError): Crew(process=Process.sequential, config=no_agents_config) -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_crew_creation(): tasks = [ Task( @@ -118,7 +118,7 @@ def test_crew_creation(): 5. **AI Startups: The Game Changers of the Tech Industry** - In the world of tech, AI startups are the bold pioneers charting new territories. This article will spotlight these game changers, showcasing how their innovative products and services are driving the AI revolution. It's a unique opportunity to catch a glimpse of the entrepreneurial side of AI, offering inspiration for the tech enthusiasts and dreamers alike.""" -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_crew_with_delegating_agents(): tasks = [ Task( @@ -135,7 +135,7 @@ def test_crew_with_delegating_agents(): assert crew.kickoff() == 'The Senior Writer has created a compelling and engaging 1 paragraph draft about AI agents. The paragraph provides a brief yet comprehensive overview of AI agents, their uses, and implications in the current world. It emphasizes their potential and the role they can play in the future. The tone is informative but captivating, meeting the objectives of the task.' -@pytest.mark.vcr() +@pytest.mark.vcr(filter_headers=["authorization"]) def test_crew_verbose_output(capsys): tasks = [ Task(