@aliyunrds/ctxdb 1.0.1 → 1.0.3

package/dist/chunk-UH7AJF6F.js

@@ -1,204 +0,0 @@
-#!/usr/bin/env node
-
-// src/lib/kb.ts
-import { readFileSync, existsSync, statSync } from "fs";
-import { basename, extname } from "path";
-import { homedir } from "os";
-import { resolve } from "path";
-import {
-  buildNormalizedGraphContext,
-  extractKnowledgeBaseIds,
-  extractKnowledgeChunkContent,
-  extractKnowledgeChunkSourceLabel,
-  extractKnowledgeChunkTags,
-  partitionKnowledgeChunks
-} from "@aliyunrds/ctxdb-shared";
-var KB_COLLECTION = "/v1/knowledge/knowledge_bases";
-var DOCUMENTS = "/v1/knowledge/documents";
-var FILES = "/v1/knowledge/files";
-var DOCUMENT_DETAIL = "/v1/knowledge/documents/detail";
-var DEFAULT_POLL_INTERVAL_MS = 1500;
-var DEFAULT_INGEST_TIMEOUT_MS = 3e4;
-var DEFAULT_FILE_INGEST_TIMEOUT_MS = 6e4;
-var MIME_BY_EXT = {
-  ".pdf": "application/pdf",
-  ".txt": "text/plain",
-  ".md": "text/markdown",
-  ".markdown": "text/markdown",
-  ".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-  ".doc": "application/msword",
-  ".html": "text/html",
-  ".htm": "text/html",
-  ".json": "application/json",
-  ".csv": "text/csv",
-  ".xml": "application/xml",
-  ".rtf": "application/rtf"
-};
-async function listKnowledgeBases(client) {
-  const resp = await client.get(KB_COLLECTION);
-  if (Array.isArray(resp)) return resp;
-  if (resp && typeof resp === "object") {
-    const o = resp;
-    return o.knowledge_bases ?? o.results ?? [];
-  }
-  return [];
-}
-async function createKb(client, kbName, description = "") {
-  return client.postJson(KB_COLLECTION, { name: kbName, description: description || "" });
-}
-async function uploadText(client, kbName, docName, text, mimeType = "text/plain", filePath) {
-  const body = {
-    knowledge_base_name: kbName,
-    name: docName,
-    text,
-    mime_type: mimeType
-  };
-  if (filePath !== void 0 && filePath !== "") body.file_path = filePath;
-  return client.postJson(DOCUMENTS, body);
-}
-async function uploadFile(client, kbName, localPath, options = {}) {
-  const MAX_UPLOAD_BYTES = 100 * 1024 * 1024;
-  const expanded = expandHome(localPath);
-  if (!existsSync(expanded)) throw new Error(`file not found: ${expanded}`);
-  const stat = statSync(expanded);
-  if (!stat.isFile()) throw new Error(`not a file: ${expanded}`);
-  if (stat.size > MAX_UPLOAD_BYTES) {
-    throw new Error(
-      `file too large (${(stat.size / 1024 / 1024).toFixed(1)} MB), maximum is 100 MB`
-    );
-  }
-  const filename = basename(expanded);
-  const docName = options.docName ?? filename;
-  const content = readFileSync(expanded);
-  const mime = guessMime(expanded);
-  const fields = {
-    knowledge_base_name: kbName,
-    name: docName
-  };
-  if (options.filePath !== void 0 && options.filePath !== "") {
-    fields.file_path = options.filePath;
-  }
-  return client.postMultipart(
-    FILES,
-    fields,
-    { file: { filename, content, mimeType: mime } },
-    { timeoutMs: options.timeoutMs }
-  );
-}
-function guessMime(path) {
-  const ext = extname(path).toLowerCase();
-  if (ext in MIME_BY_EXT) return MIME_BY_EXT[ext];
-  return "application/octet-stream";
-}
-async function getDocument(client, kbName, docId) {
-  return client.get(DOCUMENT_DETAIL, {
-    knowledge_base_name: kbName,
-    document_id: docId
-  });
-}
-async function listDocuments(client, kbName) {
-  const resp = await client.get(DOCUMENTS, { knowledge_base_name: kbName });
-  if (Array.isArray(resp)) return resp;
-  if (resp && typeof resp === "object") {
-    const o = resp;
-    return o.documents ?? o.results ?? [];
-  }
-  return [];
-}
-async function pollIngest(client, kbName, docId, options = {}) {
-  const timeoutMs = options.timeoutMs ?? DEFAULT_INGEST_TIMEOUT_MS;
-  const intervalMs = options.intervalMs ?? DEFAULT_POLL_INTERVAL_MS;
-  const sleep = options.sleep ?? ((ms) => new Promise((r) => setTimeout(r, ms)));
-  const now = options.now ?? (() => performance.now());
-  const deadline = now() + timeoutMs;
-  let doc = await getDocument(client, kbName, docId);
-  let timedOut = false;
-  while (ingestInFlight(doc)) {
-    if (now() >= deadline) {
-      timedOut = true;
-      break;
-    }
-    await sleep(intervalMs);
-    try {
-      doc = await getDocument(client, kbName, docId);
-    } catch {
-      break;
-    }
-  }
-  if (doc && typeof doc === "object") {
-    return { ...doc, _pollingTimedOut: timedOut };
-  }
-  return { _pollingTimedOut: timedOut };
-}
-function ingestInFlight(doc) {
-  if (!doc || typeof doc !== "object") return false;
-  const status = doc.ingest_status;
-  return status === "processing" || status === "pending" || status === "in_progress";
-}
-function expandHome(p) {
-  if (p.startsWith("~/") || p === "~") {
-    return resolve(homedir(), p.slice(2));
-  }
-  return resolve(p);
-}
-function compactChunk(raw) {
-  const c = raw ?? {};
-  const content = extractKnowledgeChunkContent(raw);
-  const doc_name = extractKnowledgeChunkSourceLabel(raw);
-  const kb_id = extractKnowledgeBaseIds(raw)[0] ?? "";
-  const docIdRaw = c.doc_id;
-  const scoreRaw = c.similarity ?? c.rerank_score;
-  const tags = extractKnowledgeChunkTags(raw);
-  const out = {
-    content,
-    doc_name,
-    kb_id,
-    score: typeof scoreRaw === "number" ? scoreRaw : 0
-  };
-  if (typeof docIdRaw === "string" && docIdRaw.length > 0) {
-    out.doc_id = docIdRaw;
-  }
-  if (tags.length > 0) {
-    out.tags = tags;
-  }
-  return out;
-}
-function projectKbQueryResponse(raw, projectChunk, options = {}) {
-  if (!raw || typeof raw !== "object") return { chunks: [] };
-  const r = raw;
-  const chunksIn = Array.isArray(r.chunks) ? r.chunks : [];
-  const { graphChunks, documentChunks } = partitionKnowledgeChunks(chunksIn);
-  const graphContext = buildNormalizedGraphContext(graphChunks, {
-    verbose: options.verboseGraph
-  });
-  const out = {
-    chunks: documentChunks.map(projectChunk)
-  };
-  if (typeof r.total === "number") out.total = r.total;
-  if (graphContext) out.graph_context = graphContext;
-  return out;
-}
-function compactKbQueryResponse(raw) {
-  return projectKbQueryResponse(raw, compactChunk, { verboseGraph: true });
-}
-function minimalChunk(raw) {
-  const c = compactChunk(raw);
-  return { content: c.content, score: c.score };
-}
-function minimalKbQueryResponse(raw) {
-  return projectKbQueryResponse(raw, minimalChunk);
-}
-
-export {
-  DEFAULT_INGEST_TIMEOUT_MS,
-  DEFAULT_FILE_INGEST_TIMEOUT_MS,
-  listKnowledgeBases,
-  createKb,
-  uploadText,
-  uploadFile,
-  getDocument,
-  listDocuments,
-  pollIngest,
-  compactKbQueryResponse,
-  minimalKbQueryResponse
-};