Concurrent processing of files

.gitignore

@@ -3,7 +3,7 @@
 __pycache__/
 *.py[cod]
 *$py.class
-
+.vennv
 # C extensions
 *.so
 /backend/graph
@@ -170,4 +170,6 @@ google-cloud-cli-469.0.0-linux-x86_64.tar.gz
 /backend/chunks
 google-cloud-cli-linux-x86_64.tar.gz
 .vennv
-newenv
+newenv
+files
+

backend/src/graphDB_dataAccess.py

@@ -185,7 +185,7 @@ def execute_query(self, query, param=None):
 
     def get_current_status_document_node(self, file_name):
         query = """
-                MATCH(d:Document {fileName : $file_name}) RETURN d.stats AS Status , d.processingTime AS processingTime, 
+                MATCH(d:Document {fileName : $file_name}) RETURN d.status AS Status , d.processingTime AS processingTime, 
                 d.nodeCount AS nodeCount, d.model as model, d.relationshipCount as relationshipCount,
                 d.total_pages AS total_pages, d.total_chunks AS total_chunks , d.fileSize as fileSize, 
                 d.is_cancelled as is_cancelled, d.processed_chunk as processed_chunk, d.fileSource as fileSource

docker-compose.yml

@@ -61,6 +61,7 @@ services:
         - CHUNK_SIZE=${CHUNK_SIZE-5242880}
         - ENV=${ENV-DEV}
         - CHAT_MODES=${CHAT_MODES-""}
+        - BATCH_SIZE=${BATCH_SIZE-2}
     volumes:
       - ./frontend:/app
       - /app/node_modules

frontend/Dockerfile

@@ -12,10 +12,10 @@ ARG LARGE_FILE_SIZE=5242880
 ARG CHUNK_SIZE=5242880
 ARG CHAT_MODES=""
 ARG ENV="DEV"
+ARG BATCH_SIZE=2
 
 WORKDIR /app
 COPY package.json yarn.lock ./
-RUN yarn add @neo4j-nvl/base @neo4j-nvl/react
 RUN yarn install
 COPY . ./
 RUN BACKEND_API_URL=$BACKEND_API_URL \
@@ -28,6 +28,7 @@ RUN BACKEND_API_URL=$BACKEND_API_URL \
     ENV=$ENV \
     LARGE_FILE_SIZE=${LARGE_FILE_SIZE} \
     CHAT_MODES=$CHAT_MODES \
+    BATCH_SIZE=$BATCH_SIZE \
     yarn run build
 
 # Step 2: Serve the application using Nginx

frontend/example.env

@@ -8,4 +8,5 @@ TIME_PER_PAGE=50
 CHUNK_SIZE=5242880
 LARGE_FILE_SIZE=5242880
 GOOGLE_CLIENT_ID=""
-CHAT_MODES=""
+CHAT_MODES=""
+BATCH_SIZE=2