Skip to content

feat: add DEFAULT_MAX_TOKENS env variable for global token limit #2069

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.

Sign up for GitHub

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

Open
AviadHayumi wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: add DEFAULT_MAX_TOKENS env variable for global token limit #2069

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion src/lib/server/config.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,7 +160,8 @@ type ExtraConfigKeys =
| "MCP_SERVERS"
| "MCP_FORWARD_HF_USER_TOKEN"
| "MCP_TOOL_TIMEOUT_MS"
| "EXA_API_KEY";
| "EXA_API_KEY"
| "DEFAULT_MAX_TOKENS";

type ConfigProxy = ConfigManager & { [K in ConfigKey | ExtraConfigKeys]: string };

Expand Down
13 changes: 10 additions & 3 deletions src/lib/server/endpoints/openai/endpointOai.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,11 +130,14 @@ export async function endpointOai(
});

const parameters = { ...model.parameters, ...generateSettings };
const parsedMaxTokens = Number(config.DEFAULT_MAX_TOKENS);
const defaultMaxTokens =
Number.isInteger(parsedMaxTokens) && parsedMaxTokens > 0 ? parsedMaxTokens : undefined;
const body: CompletionCreateParamsStreaming = {
model: model.id ?? model.name,
prompt,
stream: true,
max_tokens: parameters?.max_tokens,
max_tokens: parameters?.max_tokens ?? defaultMaxTokens,
stop: parameters?.stop,
temperature: parameters?.temperature,
top_p: parameters?.top_p,
Expand Down Expand Up @@ -195,14 +198,18 @@ export async function endpointOai(

// Combine model defaults with request-specific parameters
const parameters = { ...model.parameters, ...generateSettings };
const parsedMaxTokens = Number(config.DEFAULT_MAX_TOKENS);
const defaultMaxTokens =
Number.isInteger(parsedMaxTokens) && parsedMaxTokens > 0 ? parsedMaxTokens : undefined;
const effectiveMaxTokens = parameters?.max_tokens ?? defaultMaxTokens;
const body = {
model: model.id ?? model.name,
messages: messagesOpenAI,
stream: streamingSupported,
// Support two different ways of specifying token limits depending on the model
...(useCompletionTokens
? { max_completion_tokens: parameters?.max_tokens }
: { max_tokens: parameters?.max_tokens }),
? { max_completion_tokens: effectiveMaxTokens }
: { max_tokens: effectiveMaxTokens }),
stop: parameters?.stop,
temperature: parameters?.temperature,
top_p: parameters?.top_p,
Expand Down