@larkup/cli 0.2.24 → 0.2.26

package/dist/{pinecone-OHOY4YYM.js → pinecone-ME3YOCQJ.js}

@@ -1,4 +1,4 @@
-import "./chunk-3RG5ZIWI.js";
+import "./chunk-QGM4M3NI.js";
 
 // ../../packages/vector-stores/src/adapters/pinecone.ts
 import { Pinecone } from "@pinecone-database/pinecone";
@@ -36,7 +36,6 @@ var PineconeAdapter = class {
   get needsSparse() {
     return this.config.indexType === "lexical" || this.config.indexType === "hybrid";
   }
-  // ── Lifecycle ──────────────────────────────────────────────────────────────
   async init(dimensions) {
     const pc = this.getClient();
     const { indexes } = await pc.listIndexes();
@@ -71,12 +70,7 @@ var PineconeAdapter = class {
       console.error("Failed to delete vectors by documentIds in Pinecone:", err);
     }
   }
-  // ── Sparse vector generation with rate-limit handling ─────────────────────
-  /**
-   * Call Pinecone Inference API for one batch of texts, retrying on 429.
-   * Before each retry-sleep the `onRateLimit` hook is called so the indexer
-   * can patch the run store with a warning that the UI polls.
-   */
+  /** Build sparse vectors, retrying provider rate limits. */
   async embedSparseWithRetry(texts) {
     const pc = this.getClient();
     for (let attempt = 1; attempt <= RATE_LIMIT_MAX_RETRIES + 1; attempt++) {
@@ -145,7 +139,6 @@ var PineconeAdapter = class {
     }
     throw new Error("Sparse query embedding failed after max retries.");
   }
-  // ── Upsert ─────────────────────────────────────────────────────────────────
   async upsert(records) {
     if (records.length === 0) return;
     const sanitizeMeta = (meta) => {
@@ -192,7 +185,6 @@ var PineconeAdapter = class {
       }))
     });
   }
-  // ── Query ──────────────────────────────────────────────────────────────────
   async query(vector, topK, queryText) {
     const canHybrid = this.needsSparse && this.config.sparseModel && queryText;
     if (!canHybrid) {
@@ -209,15 +201,7 @@ var PineconeAdapter = class {
     const res = await this.ns().query({ vector, topK, includeMetadata: true });
     return (res.matches ?? []).map(hitFromMatch);
   }
-  /**
-   * Sparse-weighted query for hybrid search.
-   *
-   * Pinecone's dotproduct index ALWAYS requires a non-empty dense `vector`
-   * array — even when the call is primarily sparse. Passing `[]` triggers the
-   * "You must enter an array of RecordValues" error. We pass the real dense
-   * query vector here; Pinecone's scoring blends both dimensions and the RRF
-   * merge downstream takes care of the final ranking.
-   */
+  /** Run sparse-weighted hybrid search with the required dense vector. */
   async sparseQuery(denseVector, queryText, topK) {
     const sparseVector = await this.buildQuerySparseVector(queryText);
     const res = await this.ns().query({
@@ -228,7 +212,6 @@ var PineconeAdapter = class {
     });
     return (res.matches ?? []).map(hitFromMatch);
   }
-  // ── Count ──────────────────────────────────────────────────────────────────
   async count() {
     try {
       const stats = await this.ns().describeIndexStats();
@@ -237,7 +220,6 @@ var PineconeAdapter = class {
       return null;
     }
   }
-  // ── Connection test ────────────────────────────────────────────────────────
   async testConnection(dimensions) {
     const pc = this.getClient();
     let indexList;