Perp QA - Githubissues

Keyrxng commented 1 year ago

Part of #16 & #13

We are determining how much context you can consume from various sources within your own context window restrictions.

If you are able to perform reasonably independently that's great, however, it may be best to use the 16k gpt-3.5-turbo context window and allow GPT to decide the context to feed to you, this way we can guarantee you are fed the correct context as well as within your limits.

Keyrxng commented 1 year ago

/ask It would be great to see a table that summarizes the interactions and can distinguish between issue and pull request

ubqbot[bot] commented 1 year ago

Tokens

{"prompt_tokens":1031,"completion_tokens":390,"total_tokens":1421}

SentencePieceProcessor

Encoder Model: SPP > 825 tokens

> Active Fourth: 1st

Response

Keyrxng: /ask

ubqbot[bot]: Currently, UbiquityAI is experiencing technical difficulties in generating context. Please allow time for the service to recover before requesting information. If you need immediate assistance, please contact Ubiquity.

LinkedIssueContext: Keyrxng: /agent calculate the labels needed (stick to the predefined options) and once they are set, assign the issue to me

Keyrxng: /agent I reset everything for testing. Can you recalculate the labels needed (stick to the predefined options) and once they are set, assign the issue to me

ubqbot[bot]: The labels have been recalculated and set for the issue. The issue has also been assigned to you, Keyrxng. You can now proceed with working on the issue. Let me know if there's anything else I can assist you with.

system: =============== Issue #13: feat: count input + =============== resolves #12

added count input

Keyrxng: /review

ubqbot[bot]: As of now, UbiquityAI is still experiencing technical difficulties in generating context. I apologize for any inconvenience. Please allow time for the service to recover before requesting additional information. If you need immediate assistance, please contact Ubiquity.

LinkedPRContext: CurrentIssueComments: Keyrxng: /ask It would be great to see a table that summarizes the interactions and can distinguish between issue and pull request

Question: It would be great to see a table that summarizes the interactions and can distinguish between issue and pull request [

Keyrxng: /update

Keyrxng commented 1 year ago

/ask return a markdown table that houses all of the context you've been given. Summary and shorten it where possible but try to demonstrate your ability to capture many data points spread across multiple sources

ubqbot[bot] commented 1 year ago

Tokens

{"prompt_tokens":1580,"completion_tokens":1191,"total_tokens":2771}

SentencePieceProcessor

Encoder Model: SPP > 1308 tokens

> Active Fourth: 2nd

Response

Given context:

Issue #13: feat: count input + - resolved#12

Added count input

Review requests:

Keyrxng: /review

Response:

ubqbot[bot]: Keyrxng: /review for the issued #13: feat: count input + (resolved #12)

Keyrxng: /review

Linked PR Context:

CurrentIssueComments: Keyrxng: /ask It would be great to see a table that summarizes the interactions and can distinguish between issue and pull request

ubqbot[bot]: Currently, UbiquityAI is experiencing technical difficulties in generating context. Please allow time for the service to recover before requesting information. If you need immediate assistance, please contact Ubiquity.

Linked Issue Context:

Keyrxng: /agent calculate the labels needed (stick to the predefined options) and once they are set, assign the issue to me

Keyrxng: /agent I reset everything for testing. Can you recalculate the labels needed (stick to the predefined options) and once they are set, assign the issue to me

ubqbot[bot]: The labels have been recalculated and set for the issue. The issue has also been assigned to you, Keyrxng. You can now proceed with working on the issue. Let me know if there's anything else I can assist you with.

system: =============== Issue #13: feat: count input + =============== resolves #12

added count input

Keyrxng: /review

Keyrxng

Keyrxng commented 1 year ago

/ask from the linked context, create a table of the title and body of just the issue and/or pull request

ubqbot[bot] commented 1 year ago

Tokens

{"prompt_tokens":2881,"completion_tokens":69,"total_tokens":2950}

SentencePieceProcessor

Encoder Model: SPP > 2332 tokens

> Active Fourth: 3rd

Response

We have identified potential specs related to Issue #13: feat: count input + and PR context. We can ensure that we include all the relevant details by summarizing the interactions in a targeted markdown table. The table should distinguish between issue and pull request. The response will be based on the information provided in the linked context.

Keyrxng commented 1 year ago

/ask return a markdown table of the context you've been provided with

ubqbot[bot] commented 1 year ago

Tokens

{"prompt_tokens":453,"completion_tokens":263,"total_tokens":716}

SentencePieceProcessor

Encoder Model: SPP > 127 tokens

Response

Source	Schema	Migrations	Functionality
issue #16: database integration (agent QA)	8 columns, each with no less than 4 options	Write schema definitions and migration scripts	Update, create, delete, fetch functionality

Note: The list for issue #16 is not provided in the provided context. The relevant context includes only the comments for issue #15 which are:

volunteer: /agent calculate the labels needed (stick to the predefined options) and once they are set, assign the issue to me

/agent i reset everything for testing. can you recalculate the labels needed (stick to the predefined options) and once they are set, assign the issue to me

ubqbot: the labels have been recalculated and set for the issue. the issue has also been assigned to you, keyrxng. you can now proceed with working on the issue. let me know if there's anything else i can assist you with.

<!--- { 'ubiquityai': 'answer' } --->

Keyrxng commented 1 year ago

/ask battle of the bots! Return a markdown table properly formatted which summarizes the interactions and linked context, be succinct and demonstrate your potential.

ubqbot[bot] commented 1 year ago

Tokens

{"prompt_tokens":546,"completion_tokens":50,"total_tokens":596}

SentencePieceProcessor

Encoder Model: SPP > 127 tokens

Perp Response

Source	Spec	Relevant Comments
Linked Issue #16	Refer to issue #15 and setup integration with Supabase	Request for calculation of labels and reassignment of issue

GPT Response

User	Bot	Comment
Keyrxng	UbiquityAI	/agent calculate the labels needed (stick to the predefined options) and once they are set, assign the issue to me
Keyrxng	UbiquityAI	/agent I reset everything for testing. Can you recalculate the labels needed (stick to the predefined options) and once they are set, assign the issue to me
ubqbot[bot]	UbiquityAI	The labels have been recalculated and set for the issue. The issue has also been assigned to you, Keyrxng. You can now proceed with working on the issue. Let me know if there's anything else I can assist you with.

GPT Tokens


{"output":170,"input":592,"total":762}
``

ubq-testing / bot-ai

Perp QA #17

Tokens

SentencePieceProcessor

Response

Tokens

SentencePieceProcessor

Response

Tokens

SentencePieceProcessor

Response

Tokens

SentencePieceProcessor

Response

Tokens

SentencePieceProcessor

Perp Response

GPT Response

GPT Tokens