Migrate classifier to chat completions
This commit is contained in:
parent
22d87bc759
commit
d48557fe5b
5 changed files with 170 additions and 87 deletions
|
|
@ -4,7 +4,7 @@ import { DEFAULT_AI_PARAMS } from "./defaultParams.js";
|
|||
|
||||
const storage = (globalThis.messenger ?? globalThis.browser).storage;
|
||||
|
||||
const COMPLETIONS_PATH = "/v1/completions";
|
||||
const CHAT_COMPLETIONS_PATH = "/v1/chat/completions";
|
||||
const MODELS_PATH = "/v1/models";
|
||||
|
||||
const SYSTEM_PREFIX = `You are an email-classification assistant.
|
||||
|
|
@ -14,11 +14,26 @@ Read the email below and the classification criterion provided by the user.
|
|||
const DEFAULT_CUSTOM_SYSTEM_PROMPT = "Determine whether the email satisfies the user's criterion.";
|
||||
|
||||
const SYSTEM_SUFFIX = `
|
||||
Return ONLY a JSON object on a single line of the form:
|
||||
{"match": true, "reason": "<short explanation>"} - if the email satisfies the criterion
|
||||
{"match": false, "reason": "<short explanation>"} - otherwise
|
||||
Return JSON that matches the requested schema exactly.
|
||||
Set "match" to true when the email satisfies the criterion, otherwise false.
|
||||
Set "reason" to a short explanation grounded in the email contents.`;
|
||||
|
||||
Do not add any other keys, text, or formatting.`;
|
||||
const RESPONSE_FORMAT = {
|
||||
type: "json_schema",
|
||||
json_schema: {
|
||||
name: "email_classification",
|
||||
strict: true,
|
||||
schema: {
|
||||
type: "object",
|
||||
properties: {
|
||||
match: { type: "boolean" },
|
||||
reason: { type: "string" },
|
||||
},
|
||||
required: ["match", "reason"],
|
||||
additionalProperties: false,
|
||||
},
|
||||
},
|
||||
};
|
||||
|
||||
let gEndpointBase = "http://127.0.0.1:5000";
|
||||
let gEndpoint = buildEndpointUrl(gEndpointBase);
|
||||
|
|
@ -44,7 +59,7 @@ function normalizeEndpointBase(endpoint) {
|
|||
if (!base) {
|
||||
return "";
|
||||
}
|
||||
base = base.replace(/\/v1\/(completions|models)\/?$/i, "");
|
||||
base = base.replace(/\/v1(?:\/(?:chat\/completions|completions|models))?\/?$/i, "");
|
||||
return base;
|
||||
}
|
||||
|
||||
|
|
@ -55,7 +70,7 @@ function buildEndpointUrl(endpointBase) {
|
|||
}
|
||||
const withScheme = /^https?:\/\//i.test(base) ? base : `https://${base}`;
|
||||
const needsSlash = withScheme.endsWith("/");
|
||||
const path = COMPLETIONS_PATH.replace(/^\//, "");
|
||||
const path = CHAT_COMPLETIONS_PATH.replace(/^\//, "");
|
||||
return `${withScheme}${needsSlash ? "" : "/"}${path}`;
|
||||
}
|
||||
|
||||
|
|
@ -201,7 +216,9 @@ async function setConfig(config = {}) {
|
|||
if (typeof config.debugLogging === "boolean") {
|
||||
setDebug(config.debugLogging);
|
||||
}
|
||||
if (gTemplateName === "custom") {
|
||||
if (gTemplateName === "openai") {
|
||||
gTemplateText = "";
|
||||
} else if (gTemplateName === "custom") {
|
||||
gTemplateText = gCustomTemplate;
|
||||
} else {
|
||||
gTemplateText = await loadTemplate(gTemplateName);
|
||||
|
|
@ -243,6 +260,35 @@ function buildPrompt(body, criterion) {
|
|||
return template.replace(/{{\s*(\w+)\s*}}/g, (m, key) => data[key] || "");
|
||||
}
|
||||
|
||||
function buildUserMessage(body, criterion) {
|
||||
return `Email contents:
|
||||
${body}
|
||||
|
||||
Classification criterion: ${criterion}`;
|
||||
}
|
||||
|
||||
function buildMessages(body, criterion) {
|
||||
if (gTemplateName === "openai") {
|
||||
return [
|
||||
{
|
||||
role: "system",
|
||||
content: buildSystemPrompt(),
|
||||
},
|
||||
{
|
||||
role: "user",
|
||||
content: buildUserMessage(body, criterion),
|
||||
},
|
||||
];
|
||||
}
|
||||
|
||||
return [
|
||||
{
|
||||
role: "user",
|
||||
content: buildPrompt(body, criterion),
|
||||
},
|
||||
];
|
||||
}
|
||||
|
||||
function getCachedResult(cacheKey) {
|
||||
if (!gCacheLoaded) {
|
||||
return null;
|
||||
|
|
@ -263,14 +309,41 @@ function getReason(cacheKey) {
|
|||
return cacheKey && entry ? entry.reason || null : null;
|
||||
}
|
||||
|
||||
function buildPayload(text, criterion) {
|
||||
let payloadObj = Object.assign({
|
||||
prompt: buildPrompt(text, criterion)
|
||||
}, gAiParams);
|
||||
function buildOpenAiParams() {
|
||||
const params = {};
|
||||
|
||||
if (Number.isFinite(gAiParams.max_tokens) && gAiParams.max_tokens > 0) {
|
||||
params.max_completion_tokens = Math.trunc(gAiParams.max_tokens);
|
||||
}
|
||||
if (Number.isFinite(gAiParams.temperature)) {
|
||||
params.temperature = gAiParams.temperature;
|
||||
}
|
||||
if (Number.isFinite(gAiParams.top_p)) {
|
||||
params.top_p = gAiParams.top_p;
|
||||
}
|
||||
if (Number.isFinite(gAiParams.presence_penalty)) {
|
||||
params.presence_penalty = gAiParams.presence_penalty;
|
||||
}
|
||||
if (Number.isFinite(gAiParams.frequency_penalty)) {
|
||||
params.frequency_penalty = gAiParams.frequency_penalty;
|
||||
}
|
||||
if (Number.isInteger(gAiParams.seed) && gAiParams.seed >= 0) {
|
||||
params.seed = gAiParams.seed;
|
||||
}
|
||||
|
||||
return params;
|
||||
}
|
||||
|
||||
function buildPayloadObject(text, criterion) {
|
||||
const payloadObj = {
|
||||
messages: buildMessages(text, criterion),
|
||||
response_format: RESPONSE_FORMAT,
|
||||
...buildOpenAiParams(),
|
||||
};
|
||||
if (gModel) {
|
||||
payloadObj.model = gModel;
|
||||
}
|
||||
return JSON.stringify(payloadObj);
|
||||
return payloadObj;
|
||||
}
|
||||
|
||||
function reportParseError(message, detail) {
|
||||
|
|
@ -290,78 +363,81 @@ function reportParseError(message, detail) {
|
|||
}
|
||||
}
|
||||
|
||||
function extractLastJsonObject(text) {
|
||||
let last = null;
|
||||
let start = -1;
|
||||
let depth = 0;
|
||||
let inString = false;
|
||||
let escape = false;
|
||||
function extractMessageContent(content) {
|
||||
if (typeof content === "string") {
|
||||
return { text: content, refusal: "" };
|
||||
}
|
||||
if (!Array.isArray(content)) {
|
||||
return { text: "", refusal: "" };
|
||||
}
|
||||
|
||||
for (let i = 0; i < text.length; i += 1) {
|
||||
const ch = text[i];
|
||||
if (inString) {
|
||||
if (escape) {
|
||||
escape = false;
|
||||
continue;
|
||||
}
|
||||
if (ch === "\\") {
|
||||
escape = true;
|
||||
continue;
|
||||
}
|
||||
if (ch === "\"") {
|
||||
inString = false;
|
||||
}
|
||||
const textParts = [];
|
||||
const refusalParts = [];
|
||||
for (const part of content) {
|
||||
if (!part || typeof part !== "object") {
|
||||
continue;
|
||||
}
|
||||
if (ch === "\"") {
|
||||
inString = true;
|
||||
continue;
|
||||
if (part.type === "text" && typeof part.text === "string") {
|
||||
textParts.push(part.text);
|
||||
}
|
||||
if (ch === "{") {
|
||||
if (depth === 0) {
|
||||
start = i;
|
||||
}
|
||||
depth += 1;
|
||||
continue;
|
||||
}
|
||||
if (ch === "}" && depth > 0) {
|
||||
depth -= 1;
|
||||
if (depth === 0 && start !== -1) {
|
||||
last = text.slice(start, i + 1);
|
||||
start = -1;
|
||||
}
|
||||
if (part.type === "refusal" && typeof part.refusal === "string") {
|
||||
refusalParts.push(part.refusal);
|
||||
}
|
||||
}
|
||||
|
||||
return last;
|
||||
return {
|
||||
text: textParts.join("\n").trim(),
|
||||
refusal: refusalParts.join("\n").trim(),
|
||||
};
|
||||
}
|
||||
|
||||
function parseMatch(result) {
|
||||
const rawText = result.choices?.[0]?.text || "";
|
||||
const candidate = extractLastJsonObject(rawText);
|
||||
if (!candidate) {
|
||||
reportParseError("No JSON object found in AI response.", rawText.slice(0, 800));
|
||||
const message = result?.choices?.[0]?.message;
|
||||
if (!message || typeof message !== "object") {
|
||||
reportParseError("AI response missing assistant message.", JSON.stringify(result).slice(0, 800));
|
||||
return { matched: false, reason: "" };
|
||||
}
|
||||
|
||||
if (typeof message.refusal === "string" && message.refusal.trim()) {
|
||||
reportParseError("Model refused classification request.", message.refusal.slice(0, 800));
|
||||
return { matched: false, reason: message.refusal.trim() };
|
||||
}
|
||||
|
||||
if (message.parsed && typeof message.parsed === "object") {
|
||||
const parsed = message.parsed;
|
||||
if (typeof parsed.match === "boolean" && typeof parsed.reason === "string") {
|
||||
return { matched: parsed.match, reason: parsed.reason };
|
||||
}
|
||||
}
|
||||
|
||||
const extracted = extractMessageContent(message.content);
|
||||
if (extracted.refusal) {
|
||||
reportParseError("Model refused classification request.", extracted.refusal.slice(0, 800));
|
||||
return { matched: false, reason: extracted.refusal };
|
||||
}
|
||||
if (!extracted.text) {
|
||||
reportParseError("AI response missing assistant message content.", JSON.stringify(message).slice(0, 800));
|
||||
return { matched: false, reason: "" };
|
||||
}
|
||||
|
||||
let obj;
|
||||
try {
|
||||
obj = JSON.parse(candidate);
|
||||
obj = JSON.parse(extracted.text);
|
||||
} catch (e) {
|
||||
reportParseError("Failed to parse JSON from AI response.", candidate.slice(0, 800));
|
||||
reportParseError("Failed to parse JSON from AI response.", extracted.text.slice(0, 800));
|
||||
return { matched: false, reason: "" };
|
||||
}
|
||||
|
||||
const matchValue = Object.prototype.hasOwnProperty.call(obj, "match") ? obj.match : obj.matched;
|
||||
const matched = matchValue === true;
|
||||
if (matchValue !== true && matchValue !== false) {
|
||||
reportParseError("AI response missing valid match boolean.", candidate.slice(0, 800));
|
||||
if (typeof obj?.match !== "boolean") {
|
||||
reportParseError("AI response missing valid match boolean.", extracted.text.slice(0, 800));
|
||||
return { matched: false, reason: "" };
|
||||
}
|
||||
if (typeof obj?.reason !== "string") {
|
||||
reportParseError("AI response missing valid reason string.", extracted.text.slice(0, 800));
|
||||
return { matched: false, reason: "" };
|
||||
}
|
||||
|
||||
const reasonValue = obj.reason ?? obj.reasoning ?? obj.explaination;
|
||||
const reason = typeof reasonValue === "string" ? reasonValue : "";
|
||||
|
||||
return { matched, reason };
|
||||
return { matched: obj.match, reason: obj.reason };
|
||||
}
|
||||
|
||||
function cacheEntry(cacheKey, matched, reason) {
|
||||
|
|
@ -427,9 +503,10 @@ async function classifyText(text, criterion, cacheKey = null) {
|
|||
return cached;
|
||||
}
|
||||
|
||||
const payload = buildPayload(text, criterion);
|
||||
const payloadObj = buildPayloadObject(text, criterion);
|
||||
const payload = JSON.stringify(payloadObj);
|
||||
try {
|
||||
await storage.local.set({ lastPayload: JSON.parse(payload) });
|
||||
await storage.local.set({ lastPayload: payloadObj });
|
||||
} catch (e) {
|
||||
aiLog('failed to save last payload', { level: 'warn' }, e);
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue