initial version #228
initial version #228
Conversation
i want to refactor this to use the fixie SDK after it supports list agent conversations.
mdwelsh
left a comment
mdwelsh
left a comment
There was a problem hiding this comment.
LGTM for now, run this by @petersalas though
| const response = await axios({ | ||
| method: 'get', | ||
| maxBodyLength: Infinity, | ||
| url: `https://api.fixie.ai/api/v1/agents/${agentId}/conversations`, |
There was a problem hiding this comment.
Is this endpoint paginated?
There was a problem hiding this comment.
yes it is. changed the implementation to handle paging.
| numTokens += encoded.length; | ||
|
|
||
| numConvoChars += message.response.length; | ||
| numConvoTokens += encoded.length; |
There was a problem hiding this comment.
This ignores the quadratic effect where messages become input tokens to subsequent generations (e.g. a conversation with 10 messages uses >> 10 times the number of input tokens as a conversation with 1 message)
But old messages also get pruned as well as they fill up the context window, so calculating it accurately is even trickier. The easiest thing to get approximately correct is to calculate the number of output tokens, because that's just the assistant text/functionCall messages, but I'm guessing you want an estimate for both :)
3 participants
i want to refactor this to use the fixie SDK after it supports list agent conversations.