From d66248eb4cfa714fb12e59228d11ff04b0f35356 Mon Sep 17 00:00:00 2001
From: Rahim Kanji <rahim.kanji@outlook.com>
Date: Mon, 26 Jan 2026 22:00:57 +0500
Subject: [PATCH] add verbose logging for bulk embedding operations

Add logs to track embedding generation progress:
- Show batch size when collecting chunks for embedding
- Display OpenAI API call details (endpoint, model, chunk count)
- Confirm successful storage after each batch
---
 RAG_POC/rag_ingest.cpp | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/RAG_POC/rag_ingest.cpp b/RAG_POC/rag_ingest.cpp
index 1ea4932d3..cbeab3382 100644
--- a/RAG_POC/rag_ingest.cpp
+++ b/RAG_POC/rag_ingest.cpp
@@ -884,6 +884,8 @@ struct OpenAIEmbeddingProvider : public EmbeddingProvider {
         if (!url.empty() && url.back() == '/') url.pop_back();
         url += "/embeddings";
 
+        std::cerr << "    Calling OpenAI API: " << url << " (model=" << model << ", chunks=" << inputs.size() << ")\n";
+
         CURL* curl = curl_easy_init();
         if (!curl) throw std::runtime_error("curl_easy_init failed");
 
@@ -1105,6 +1107,8 @@ static size_t flush_embedding_batch(std::vector<PendingEmbedding>& pending,
                                     MySQLDB& db) {
     if (pending.empty()) return 0;
 
+    std::cerr << "  Generating embeddings for batch of " << pending.size() << " chunks...\n";
+
     std::vector<std::string> inputs;
     inputs.reserve(pending.size());
     for (const auto& p : pending) {
@@ -1120,6 +1124,7 @@ static size_t flush_embedding_batch(std::vector<PendingEmbedding>& pending,
 
     size_t count = pending.size();
     pending.clear();
+    std::cerr << "  Successfully stored " << count << " embeddings\n";
     return count;
 }