Adding timeouts

Signed-off-by: Denis Jannot <denis.jannot@solo.io>

Author: djannot

content-processor.ts

@@ -1935,7 +1935,12 @@ export class ContentProcessor {
         if (lang) {
             try {
                 const codeChunker = await this.getCodeChunker(lang, sourceConfig.chunk_size);
-                chunks = await codeChunker.chunk(code);
+                chunks = await Promise.race([
+                    codeChunker.chunk(code),
+                    new Promise<never>((_, reject) =>
+                        setTimeout(() => reject(new Error(`CodeChunker timed out after 30s for ${normalizedPath || url}`)), 30000)
+                    )
+                ]);
             } catch (error) {
                 logger.warn(`CodeChunker failed for ${normalizedPath || url}, falling back to token chunking:`, error);
                 const chunker = await this.getTokenChunker(sourceConfig.chunk_size);

doc2vec.ts

@@ -1726,7 +1726,7 @@ export class Doc2Vec {
             const response = await this.openai.embeddings.create({
                 model: this.embeddingModel,
                 input: safeTexts,
-            });
+            }, { timeout: 60000 });
             logger.debug(`Successfully created ${response.data.length} embeddings`);
             return response.data.map(d => d.embedding);
         } catch (error) {
@@ -1743,5 +1743,7 @@ if (require.main === module) {
         process.exit(1);
     }
     const doc2Vec = new Doc2Vec(configPath);
-    doc2Vec.run().catch(console.error);
+    doc2Vec.run()
+        .then(() => process.exit(0))
+        .catch((err) => { console.error(err); process.exit(1); });
 } 

package.json

@@ -1,6 +1,6 @@
 {
     "name": "doc2vec",
-    "version": "2.9.0",
+    "version": "2.9.1",
     "type": "commonjs",
     "description": "",
     "main": "dist/doc2vec.js",