enhance: avoid context limit #832
Merged
+72
−8
Conversation
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
Signed-off-by: Grant Linville <[email protected]>
Signed-off-by: Grant Linville <[email protected]>
Signed-off-by: Grant Linville <[email protected]>
g-linville
requested review from
ibuildthecloud,
cjellick,
thedadams,
njhale,
StrongMonkey and
iwilltry42
ibuildthecloud
approved these changes
Aug 30, 2024
|
@ibuildthecloud correct. The way I implemented this will never change how the system role messages are handled. Those will always stick around. |
thedadams
approved these changes
Aug 30, 2024
pkg/openai/client.go
Outdated
| @@ -317,6 +320,14 @@ func (c *Client) Call(ctx context.Context, messageRequest types.CompletionReques | |||
| } | |||
|
|
|||
| if messageRequest.Chat { | |||
| // Check the last message. If it is from a tool call, and if it takes up more than 80% of the budget on its own, reject it. | |||
| lastMessage := msgs[len(msgs)-1] | |||
| if lastMessage.Role == string(types.CompletionMessageRoleTypeTool) && countMessage(lastMessage) > int(math.Round(float64(getBudget(messageRequest.MaxTokens))*0.8)) { | |||
There was a problem hiding this comment.
nit: probably don't need to math.Round here. Not much of a difference between 102,399 and 102,400.
pkg/openai/client.go
Outdated
|
|
||
| // If we got back a context length exceeded error, keep retrying and shrinking the message history until we pass. | ||
| var apiError *openai.APIError | ||
| if err != nil && errors.As(err, &apiError) && apiError.Code == "context_length_exceeded" && messageRequest.Chat { |
There was a problem hiding this comment.
nit: errors.As takes care of the err != nil check
Suggested change
| if err != nil && errors.As(err, &apiError) && apiError.Code == "context_length_exceeded" && messageRequest.Chat { | |
| if errors.As(err, &apiError) && apiError.Code == "context_length_exceeded" && messageRequest.Chat { |
| err error | ||
| ) | ||
|
|
||
| for range 10 { // maximum 10 tries |
There was a problem hiding this comment.
Is this the first use in our code base?
pkg/openai/count.go
Outdated
|
|
||
| func decreaseTenPercent(maxTokens int) int { | ||
| maxTokens = getBudget(maxTokens) | ||
| return int(math.Round(float64(maxTokens) * 0.9)) |
There was a problem hiding this comment.
same nit about math.Round
Signed-off-by: Grant Linville <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
for gptscript-ai/desktop#283
This PR introduces three new measures to try to help the user avoid hitting the context length error:
With these three measures, I am fairly confident that users will no longer encounter the error.