θΏ™ζ˜―indexlocζδΎ›ηš„ζœεŠ‘οΌŒδΈθ¦θΎ“ε…₯任何密码
Skip to content

1417 completion timeout #2374

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

Merged
merged 7 commits into from
Sep 25, 2024
Merged

1417 completion timeout #2374

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
7985f38
Refactor handleDefaultStreamResponseV2 function for better error hand…
Rrojaski Sep 23, 2024
b2e7ff0
Merge branch 'master' into 1417-completion-timeout
Rrojaski Sep 23, 2024
d64eb93
run yarn lint
Rrojaski Sep 23, 2024
ce407ed
small error handling changes
timothycarambat Sep 25, 2024
fe302ce
update error handling flow and scope of vars
timothycarambat Sep 25, 2024
2e33488
add back space
timothycarambat Sep 25, 2024
988a798
Merge branch 'master' into 1417-completion-timeout
timothycarambat Sep 25, 2024
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
82 changes: 48 additions & 34 deletions server/utils/helpers/chat/responses.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,41 +22,55 @@ function handleDefaultStreamResponseV2(response, stream, responseProps) {
const handleAbort = () => clientAbortedHandler(resolve, fullText);
response.on("close", handleAbort);

for await (const chunk of stream) {
const message = chunk?.choices?.[0];
const token = message?.delta?.content;

if (token) {
fullText += token;
writeResponseChunk(response, {
uuid,
sources: [],
type: "textResponseChunk",
textResponse: token,
close: false,
error: false,
});
}

// LocalAi returns '' and others return null on chunks - the last chunk is not "" or null.
// Either way, the key `finish_reason` must be present to determine ending chunk.
if (
message?.hasOwnProperty("finish_reason") && // Got valid message and it is an object with finish_reason
message.finish_reason !== "" &&
message.finish_reason !== null
) {
writeResponseChunk(response, {
uuid,
sources,
type: "textResponseChunk",
textResponse: "",
close: true,
error: false,
});
response.removeListener("close", handleAbort);
resolve(fullText);
break; // Break streaming when a valid finish_reason is first encountered
// Now handle the chunks from the streamed response and append to fullText.
try {
for await (const chunk of stream) {
const message = chunk?.choices?.[0];
const token = message?.delta?.content;

if (token) {
fullText += token;
writeResponseChunk(response, {
uuid,
sources: [],
type: "textResponseChunk",
textResponse: token,
close: false,
error: false,
});
}

// LocalAi returns '' and others return null on chunks - the last chunk is not "" or null.
// Either way, the key `finish_reason` must be present to determine ending chunk.
if (
message?.hasOwnProperty("finish_reason") && // Got valid message and it is an object with finish_reason
message.finish_reason !== "" &&
message.finish_reason !== null
) {
writeResponseChunk(response, {
uuid,
sources,
type: "textResponseChunk",
textResponse: "",
close: true,
error: false,
});
response.removeListener("close", handleAbort);
resolve(fullText);
break; // Break streaming when a valid finish_reason is first encountered
}
}
} catch (e) {
console.log(`\x1b[43m\x1b[34m[STREAMING ERROR]\x1b[0m ${e.message}`);
writeResponseChunk(response, {
uuid,
type: "abort",
textResponse: null,
sources: [],
close: true,
error: e.message,
});
resolve(fullText); // Return what we currently have - if anything.
}
});
}
Expand Down