-
Notifications
You must be signed in to change notification settings - Fork 45
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Set verbose as the default behavior #250
Merged
Merged
Changes from all commits
Commits
Show all changes
5 commits
Select commit
Hold shift + click to select a range
34816ca
Set verbose as the default behavior
20001LastOrder dbc63c6
Rename the non verbose option to concise
20001LastOrder cdb4226
Rename tests and bail early when SERPER_API_KEY is undefined
oshoma 2971f99
Merge main
20001LastOrder c80111f
Merge branch 'main' into verbose
oshoma File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
4 changes: 2 additions & 2 deletions
4
...test_response_contains_correct_info.jsonl → ...est_response_concise_is_not_verbose.jsonl
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,2 +1,2 @@ | ||
{"input": [{"text": "You are a friendly assistent bot called Sherpa\\n\\n\\n\\nConstraints:\\n1. If you are unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.\\n2. You can seek for user assistance only by using the corresponding tool\\n3. Exclusively use the commands listed in double quotes e.g. \"command name\"\\n4. You must always choose a command unless you want to \"finish\"\\n\\nCommands:\\n1. UserInput: Access the user input for the task.You use this tool if you need more context and would like to ask clarifying questions to solve the task, args json schema: {\"query\": {\"title\": \"Query\", \"type\": \"string\"}}\\n2. Search: Access the internet to search for the information. Only use this tool when you cannot find the information using internal search., args json schema: {\"query\": {\"title\": \"Query\", \"type\": \"string\"}}\\n3. finish: use this to signal that you have finished the current task, args: \"response\": \"final response to let people know you have finished the current task\"\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.\\n\\nYou should only respond in JSON format as described below without any extra text.\\nResponse Format: \\n{\\n \"thoughts\": {\\n \"text\": \"thought\",\\n \"speak\": \"thoughts summary to say to user\"\\n },\\n \"command\": {\\n \"name\": \"tool/command name you choose\",\\n \"args\": {\\n \"arg name\": \"value\"\\n }\\n }\\n} \\nEnsure the response can be parsed by Python json.loads", "agent": "system"}, {"text": "The current time and date is Mon Nov 27 11:23:37 2023", "agent": "system"}, {"text": "Current task: What is AutoGPT and how does it compare with MetaGPT \\n Determine which next command to use. Select the finish command if you and respond using the JSON format specified above without any extra text.\\n JSON Response: \\n", "agent": "human"}], "output": "{\\n \"thoughts\": {\\n \"text\": \"I'm not familiar with AutoGPT and MetaGPT. I should use the Search tool to find more information.\",\\n \"speak\": \"I'm not familiar with AutoGPT and MetaGPT. Let me search for more information.\"\\n },\\n \"command\": {\\n \"name\": \"Search\",\\n \"args\": {\\n \"query\": \"AutoGPT vs MetaGPT\"\\n }\\n }\\n}", "llm_name": "gpt-3.5-turbo"} | ||
{"input": [{"text": "You are a friendly assistent bot called Sherpa\\n\\n\\n\\nConstraints:\\n1. If you are unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.\\n2. You can seek for user assistance only by using the corresponding tool\\n3. Exclusively use the commands listed in double quotes e.g. \"command name\"\\n4. You must always choose a command unless you want to \"finish\"\\n\\nCommands:\\n1. UserInput: Access the user input for the task.You use this tool if you need more context and would like to ask clarifying questions to solve the task, args json schema: {\"query\": {\"title\": \"Query\", \"type\": \"string\"}}\\n2. Search: Access the internet to search for the information. Only use this tool when you cannot find the information using internal search., args json schema: {\"query\": {\"title\": \"Query\", \"type\": \"string\"}}\\n3. finish: use this to signal that you have finished the current task, args: \"response\": \"final response to let people know you have finished the current task\"\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.\\n\\nYou should only respond in JSON format as described below without any extra text.\\nResponse Format: \\n{\\n \"thoughts\": {\\n \"text\": \"thought\",\\n \"speak\": \"thoughts summary to say to user\"\\n },\\n \"command\": {\\n \"name\": \"tool/command name you choose\",\\n \"args\": {\\n \"arg name\": \"value\"\\n }\\n }\\n} \\nEnsure the response can be parsed by Python json.loads", "agent": "system"}, {"text": "The current time and date is Mon Nov 27 11:23:42 2023", "agent": "system"}, {"text": "Assistant Reply: {\\n \"thoughts\": {\\n \"text\": \"I'm not familiar with AutoGPT and MetaGPT. I should use the Search tool to find more information.\",\\n \"speak\": \"I'm not familiar with AutoGPT and MetaGPT. Let me search for more information.\"\\n },\\n \"command\": {\\n \"name\": \"Search\",\\n \"args\": {\\n \"query\": \"AutoGPT vs MetaGPT\"\\n }\\n }\\n} \\nResult: Command Search returned: Answer: AutoGPT: AutoGPT could be used to generate text, translate languages, or write different kinds of creative content. MetaGPT: MetaGPT could be used to create multi-agent systems, or to learn from multiple datasets.\\nDocID:[1]\\n\\n ", "agent": "human"}, {"text": "Current task: What is AutoGPT and how does it compare with MetaGPT \\n Use the above information to respond to the user's message:\\nWhat is AutoGPT and how does it compare with MetaGPT\\n\\nIf you use any resource, then create inline citation by addingthe DocID of the reference document at the end of the sentence in the format of 'Sentence [DocID]'\\nExample:\\nSentence1 [1]. Sentence2. Sentence3 [2].\\nOnly use the reference document. DO NOT use any links DO NOT include citation if the resource is notnecessary. only write text but not the JSON format specified above. \\nResult:", "agent": "human"}], "output": "AutoGPT is a language model that can be used to generate text, translate languages, or write various types of creative content [1]. On the other hand, MetaGPT is a language model that can be used to create multi-agent systems or learn from multiple datasets [1]. Both AutoGPT and MetaGPT are powerful language models with different applications and use cases.", "llm_name": "gpt-3.5-turbo"} | ||
{"input": [{"text": "You are a friendly assistent bot called Sherpa\\n\\n\\n\\nConstraints:\\n1. If you are unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.\\n2. You can seek for user assistance only by using the corresponding tool\\n3. Exclusively use the commands listed in double quotes e.g. \"command name\"\\n4. You must always choose a command unless you want to \"finish\"\\n\\nCommands:\\n1. UserInput: Access the user input for the task.You use this tool if you need more context and would like to ask clarifying questions to solve the task, args json schema: {\"query\": {\"title\": \"Query\", \"type\": \"string\"}}\\n2. Search: Access the internet to search for the information. Only use this tool when you cannot find the information using internal search., args json schema: {\"query\": {\"title\": \"Query\", \"type\": \"string\"}}\\n3. finish: use this to signal that you have finished the current task, args: \"response\": \"final response to let people know you have finished the current task\"\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.\\n\\nYou should only respond in JSON format as described below without any extra text.\\nResponse Format: \\n{\\n \"thoughts\": {\\n \"text\": \"thought\",\\n \"speak\": \"thoughts summary to say to user\"\\n },\\n \"command\": {\\n \"name\": \"tool/command name you choose\",\\n \"args\": {\\n \"arg name\": \"value\"\\n }\\n }\\n} \\nEnsure the response can be parsed by Python json.loads", "agent": "system"}, {"text": "The current time and date is Tue Dec 5 20:44:23 2023", "agent": "system"}, {"text": "Current task: What is AutoGPT and how does it compare with MetaGPT \\n Determine which next command to use. Select the finish command if you and respond using the JSON format specified above without any extra text.\\n JSON Response: \\n", "agent": "human"}], "output": "{\\n \"thoughts\": {\\n \"text\": \"I'm not familiar with AutoGPT and MetaGPT. I should use the Search tool to find more information about them.\",\\n \"speak\": \"I'm not familiar with AutoGPT and MetaGPT. Let me search for more information.\"\\n },\\n \"command\": {\\n \"name\": \"Search\",\\n \"args\": {\\n \"query\": \"AutoGPT and MetaGPT comparison\"\\n }\\n }\\n}", "llm_name": "gpt-3.5-turbo"} | ||
{"input": [{"text": "You are a friendly assistent bot called Sherpa\\n\\n\\n\\nConstraints:\\n1. If you are unsure how you previously did something or want to recall past events, thinking about similar events will help you remember.\\n2. You can seek for user assistance only by using the corresponding tool\\n3. Exclusively use the commands listed in double quotes e.g. \"command name\"\\n4. You must always choose a command unless you want to \"finish\"\\n\\nCommands:\\n1. UserInput: Access the user input for the task.You use this tool if you need more context and would like to ask clarifying questions to solve the task, args json schema: {\"query\": {\"title\": \"Query\", \"type\": \"string\"}}\\n2. Search: Access the internet to search for the information. Only use this tool when you cannot find the information using internal search., args json schema: {\"query\": {\"title\": \"Query\", \"type\": \"string\"}}\\n3. finish: use this to signal that you have finished the current task, args: \"response\": \"final response to let people know you have finished the current task\"\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.\\n\\nYou should only respond in JSON format as described below without any extra text.\\nResponse Format: \\n{\\n \"thoughts\": {\\n \"text\": \"thought\",\\n \"speak\": \"thoughts summary to say to user\"\\n },\\n \"command\": {\\n \"name\": \"tool/command name you choose\",\\n \"args\": {\\n \"arg name\": \"value\"\\n }\\n }\\n} \\nEnsure the response can be parsed by Python json.loads", "agent": "system"}, {"text": "The current time and date is Tue Dec 5 20:44:28 2023", "agent": "system"}, {"text": "Assistant Reply: {\\n \"thoughts\": {\\n \"text\": \"I'm not familiar with AutoGPT and MetaGPT. I should use the Search tool to find more information about them.\",\\n \"speak\": \"I'm not familiar with AutoGPT and MetaGPT. Let me search for more information.\"\\n },\\n \"command\": {\\n \"name\": \"Search\",\\n \"args\": {\\n \"query\": \"AutoGPT and MetaGPT comparison\"\\n }\\n }\\n} \\nResult: Command Search returned: Answer: AutoGPT: AutoGPT is the simplest of the three projects. It is easy to install and use, but it does not offer as many features as MetaGPT or SuperAGI. MetaGPT: MetaGPT is more complex than AutoGPT, but it offers a wider range of features.\\nDocID:[1]\\n\\n ", "agent": "human"}, {"text": "Current task: What is AutoGPT and how does it compare with MetaGPT \\n Use the above information to respond to the user's message:\\nWhat is AutoGPT and how does it compare with MetaGPT\\n\\nIf you use any resource, then create inline citation by addingthe DocID of the reference document at the end of the sentence in the format of 'Sentence [DocID]'\\nExample:\\nSentence1 [1]. Sentence2. Sentence3 [2].\\nOnly use the reference document. DO NOT use any links DO NOT include citation if the resource is notnecessary. only write text but not the JSON format specified above. \\nResult:", "agent": "human"}], "output": "AutoGPT is a project that focuses on simplicity and ease of use. It is easy to install and use, but it does not offer as many features as MetaGPT or SuperAGI [1].\\n\\nMetaGPT, on the other hand, is more complex than AutoGPT and offers a wider range of features [1].\\n\\nIn summary, AutoGPT is a simpler project compared to MetaGPT, but MetaGPT provides more advanced features and capabilities [1].", "llm_name": "gpt-3.5-turbo"} |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Not asking for a change at this time, but noting that we should really put FILE_SIZE_LIMIT (as MB) in the message here instead of hard-coding.