Fix chunking/snippet logs for clarity (#4129)

update chunking/snippet logs for clarity

server/utils/EmbeddingEngines/native/index.js

@@ -165,7 +165,7 @@ class NativeEmbedder {
 
       data = JSON.stringify(output.tolist());
       await this.#writeToTempfile(tmpFilePath, data);
-      this.log(`Embedded Chunk ${idx + 1} of ${chunkLen}`);
+      this.log(`Embedded Chunk Group ${idx + 1} of ${chunkLen}`);
       if (chunkLen - 1 !== idx) await this.#writeToTempfile(tmpFilePath, ",");
       if (chunkLen - 1 === idx) await this.#writeToTempfile(tmpFilePath, "]");
       pipeline = null;

server/utils/vectorDbProviders/astra/index.js

@@ -209,7 +209,7 @@ const AstraDB = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      console.log("Chunks created from document:", textChunks.length);
+      console.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const vectorValues = await EmbedderEngine.embedChunks(textChunks);

server/utils/vectorDbProviders/chroma/index.js

@@ -255,7 +255,7 @@ const Chroma = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      console.log("Chunks created from document:", textChunks.length);
+      console.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const vectorValues = await EmbedderEngine.embedChunks(textChunks);

server/utils/vectorDbProviders/lance/index.js

@@ -331,7 +331,7 @@ const LanceDb = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      console.log("Chunks created from document:", textChunks.length);
+      console.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const submissions = [];

server/utils/vectorDbProviders/milvus/index.js

@@ -207,7 +207,7 @@ const Milvus = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      console.log("Chunks created from document:", textChunks.length);
+      console.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const vectorValues = await EmbedderEngine.embedChunks(textChunks);

server/utils/vectorDbProviders/pgvector/index.js

@@ -539,7 +539,7 @@ const PGVector = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      this.log("Chunks created from document:", textChunks.length);
+      this.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const submissions = [];

server/utils/vectorDbProviders/pinecone/index.js

@@ -153,7 +153,7 @@ const PineconeDB = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      console.log("Chunks created from document:", textChunks.length);
+      console.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const vectorValues = await EmbedderEngine.embedChunks(textChunks);

server/utils/vectorDbProviders/qdrant/index.js

@@ -225,7 +225,7 @@ const QDrant = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      console.log("Chunks created from document:", textChunks.length);
+      console.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const vectorValues = await EmbedderEngine.embedChunks(textChunks);

server/utils/vectorDbProviders/weaviate/index.js

@@ -266,7 +266,7 @@ const Weaviate = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      console.log("Chunks created from document:", textChunks.length);
+      console.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const vectorValues = await EmbedderEngine.embedChunks(textChunks);

server/utils/vectorDbProviders/zilliz/index.js

@@ -200,7 +200,7 @@ const Zilliz = {
       });
       const textChunks = await textSplitter.splitText(pageContent);
 
-      console.log("Chunks created from document:", textChunks.length);
+      console.log("Snippets created from document:", textChunks.length);
       const documentVectors = [];
       const vectors = [];
       const vectorValues = await EmbedderEngine.embedChunks(textChunks);