Merge branch 'master' into joanne-tutorialagent

1 files changed, 9 insertions, 9 deletions

diff --git a/src/client/views/nodes/chatbot/vectorstore/Vectorstore.ts b/src/client/views/nodes/chatbot/vectorstore/Vectorstore.ts
index afd34f28d..6d524e40f 100644
--- a/src/client/views/nodes/chatbot/vectorstore/Vectorstore.ts
+++ b/src/client/views/nodes/chatbot/vectorstore/Vectorstore.ts
@@ -15,7 +15,6 @@ import { Networking } from '../../../../Network';
 import { AI_Document, CHUNK_TYPE, RAGChunk } from '../types/types';
 import OpenAI from 'openai';
 import { Embedding } from 'openai/resources';
-import { PineconeEnvironmentVarsNotSupportedError } from '@pinecone-database/pinecone/dist/errors';
 
 dotenv.config();
 
@@ -42,7 +41,8 @@ export class Vectorstore {
     constructor(id: string, doc_ids: () => string[]) {
         const pineconeApiKey = process.env.PINECONE_API_KEY;
         if (!pineconeApiKey) {
-            throw new Error('PINECONE_API_KEY is not defined.');
+            console.log('PINECONE_API_KEY is not defined - Vectorstore will be unavailable');
+            return;
         }
 
         // Initialize Pinecone and OpenAI clients with API keys from the environment.
@@ -100,7 +100,7 @@ export class Vectorstore {
         } else {
             // Start processing the document.
             doc.ai_document_status = 'PROGRESS';
-            const local_file_path: string = CsvCast(doc.data)?.url?.pathname ?? PDFCast(doc.data)?.url?.pathname ?? VideoCast(doc.data)?.url?.pathname ?? AudioCast(doc.data)?.url?.pathname;
+            const local_file_path = CsvCast(doc.data)?.url?.pathname ?? PDFCast(doc.data)?.url?.pathname ?? VideoCast(doc.data)?.url?.pathname ?? AudioCast(doc.data)?.url?.pathname;
 
             if (!local_file_path) {
                 console.log('Invalid file path.');
@@ -111,13 +111,13 @@ export class Vectorstore {
             let result: AI_Document & { doc_id: string };
             if (isAudioOrVideo) {
                 console.log('Processing media file...');
-                const response = await Networking.PostToServer('/processMediaFile', { fileName: path.basename(local_file_path) });
+                const response = (await Networking.PostToServer('/processMediaFile', { fileName: path.basename(local_file_path) })) as { [key: string]: unknown };
                 const segmentedTranscript = response.condensed;
                 console.log(segmentedTranscript);
-                const summary = response.summary;
+                const summary = response.summary as string;
                 doc.summary = summary;
                 // Generate embeddings for each chunk
-                const texts = segmentedTranscript.map((chunk: any) => chunk.text);
+                const texts = (segmentedTranscript as { text: string }[])?.map(chunk => chunk.text);
 
                 try {
                     const embeddingsResponse = await this.openai.embeddings.create({
@@ -137,7 +137,7 @@ export class Vectorstore {
                         file_name: local_file_path,
                         num_pages: 0,
                         summary: '',
-                        chunks: segmentedTranscript.map((chunk: any, index: number) => ({
+                        chunks: (segmentedTranscript as { text: string; start: number; end: number; indexes: string[] }[]).map((chunk, index) => ({
                             id: uuidv4(),
                             values: (embeddingsResponse.data as Embedding[])[index].embedding, // Assign embedding
                             metadata: {
@@ -172,7 +172,7 @@ export class Vectorstore {
             } else {
                 // Existing document processing logic remains unchanged
                 console.log('Processing regular document...');
-                const { jobId } = await Networking.PostToServer('/createDocument', { file_path: local_file_path });
+                const { jobId } = (await Networking.PostToServer('/createDocument', { file_path: local_file_path })) as { jobId: string };
 
                 while (true) {
                     await new Promise(resolve => setTimeout(resolve, 2000));
@@ -296,7 +296,7 @@ export class Vectorstore {
                 encoding_format: 'float',
             });
 
-            let queryEmbedding = queryEmbeddingResponse.data[0].embedding;
+            const queryEmbedding = queryEmbeddingResponse.data[0].embedding;
 
             // Extract the embedding from the response.