Merge branch 'main' of https://github.com/neo4j-labs/llm-graph-builder into STAGING

Author: aashipandya

README.md

@@ -31,6 +31,11 @@ If you are using Neo4j Desktop, you will not be able to use the docker-compose b
 ### Local deployment
 #### Running through docker-compose
 By default only OpenAI and Diffbot are enabled since Gemini requires extra GCP configurations.
+Accoroding to enviornment we are configuring the models which is indicated by VITE_LLM_MODELS_PROD variable we can configure model based on our need.
+EX:
+```env
+VITE_LLM_MODELS_PROD="openai_gpt_4o,openai_gpt_4o_mini,diffbot,gemini_1.5_flash"
+```
 According to the environment, we are configuring the models which indicated by VITE_LLM_MODELS_PROD variable we can configure models based on our needs.
 EX:
 ```env
@@ -40,12 +45,14 @@ VITE_LLM_MODELS_PROD="openai_gpt_4o,openai_gpt_4o_mini,diffbot,gemini_1.5_flash"
 if you only want OpenAI:
 ```env
 VITE_LLM_MODELS_PROD="diffbot,openai-gpt-3.5,openai-gpt-4o"
+VITE_LLM_MODELS_PROD="diffbot,openai-gpt-3.5,openai-gpt-4o"
 OPENAI_API_KEY="your-openai-key"
 ```
 
 if you only want Diffbot:
 ```env
 VITE_LLM_MODELS_PROD="diffbot"
+VITE_LLM_MODELS_PROD="diffbot"
 DIFFBOT_API_KEY="your-diffbot-key"
 ```
 
@@ -71,6 +78,7 @@ You can of course combine all (local, youtube, wikipedia, s3 and gcs) or remove
 
 ### Chat Modes
 
+By default,all of the chat modes will be available: vector, graph_vector, graph, fulltext, graph_vector_fulltext , entity_vector and global_vector.
 By default,all of the chat modes will be available: vector, graph_vector, graph, fulltext, graph_vector_fulltext , entity_vector and global_vector.
 If none of the mode is mentioned in the chat modes variable all modes will be available:
 ```env
@@ -80,6 +88,7 @@ VITE_CHAT_MODES=""
 If however you want to specify the only vector mode or only graph mode you can do that by specifying the mode in the env:
 ```env
 VITE_CHAT_MODES="vector,graph"
+VITE_CHAT_MODES="vector,graph"
 ```
 
 #### Running Backend and Frontend separately (dev environment)
@@ -114,7 +123,7 @@ Alternatively, you can run the backend and frontend separately:
 To deploy the app and packages on Google Cloud Platform, run the following command on google cloud run:
 ```bash
 # Frontend deploy 
-gcloud run deploy 
+gcloud run deploy dev-frontend --set-env-vars "VITE_BACKEND_API_URL=" --set-env-vars "VITE_FRONTEND_HOSTNAME=hostname.us-central1.run.app" --set-env-vars "VITE_SEGMENT_API_URL=https://cdn.segment.com/v1/projects/4SGwdwzuDm5WkFvQtz7D6ATQlo14yjmW/settings"
 source location current directory > Frontend
 region : 32 [us-central 1]
 Allow unauthenticated request : Yes

backend/score.py

@@ -36,7 +36,10 @@
 from src.ragas_eval import *
 from starlette.types import ASGIApp, Message, Receive, Scope, Send
 import gzip
+<<<<<<< HEAD
 from langchain_neo4j import Neo4jGraph
+=======
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
 
 logger = CustomLogger()
 CHUNK_DIR = os.path.join(os.path.dirname(__file__), "chunks")
@@ -82,9 +85,16 @@ async def __call__(self, scope: Scope, receive: Receive, send: Send):
         await gzip_middleware(scope, receive, send)
 app = FastAPI()
 # SecWeb(app=app, Option={'referrer': False, 'xframe': False})
+<<<<<<< HEAD
 # app.add_middleware(ContentSecurityPolicy, Option={'default-src': ["'self'"], 'base-uri': ["'self'"], 'block-all-mixed-content': []}, script_nonce=False, style_nonce=False, report_only=False)
 app.add_middleware(XContentTypeOptions)
 app.add_middleware(XFrame, Option={'X-Frame-Options': 'DENY'})
+=======
+app.add_middleware(ContentSecurityPolicy, Option={'default-src': ["'self'"], 'base-uri': ["'self'"], 'block-all-mixed-content': []}, script_nonce=False, style_nonce=False, report_only=False)
+app.add_middleware(XContentTypeOptions)
+app.add_middleware(XFrame, Option={'X-Frame-Options': 'DENY'})
+#app.add_middleware(GZipMiddleware, minimum_size=1000, compresslevel=5)
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
 app.add_middleware(CustomGZipMiddleware, minimum_size=1000, compresslevel=5,paths=["/sources_list","/url/scan","/extract","/chat_bot","/chunk_entities","/get_neighbours","/graph_query","/schema","/populate_graph_schema","/get_unconnected_nodes_list","/get_duplicate_nodes","/fetch_chunktext"])
 app.add_middleware(
     CORSMiddleware,
@@ -829,11 +839,15 @@ async def retry_processing(uri=Form(), userName=Form(), password=Form(), databas
         start = time.time()
         graph = create_graph_database_connection(uri, userName, password, database)
         await asyncio.to_thread(set_status_retry, graph,file_name,retry_condition)
+<<<<<<< HEAD
         end = time.time()
         elapsed_time = end - start
         json_obj = {'api_name':'retry_processing', 'db_url':uri, 'userName':userName, 'database':database, 'file_name':file_name,'retry_condition':retry_condition,
                             'logging_time': formatted_time(datetime.now(timezone.utc)), 'elapsed_api_time':f'{elapsed_time:.2f}'}
         logger.log_struct(json_obj, "INFO")
+=======
+        #set_status_retry(graph,file_name,retry_condition)
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
         return create_api_response('Success',message=f"Status set to Ready to Reprocess for filename : {file_name}")
     except Exception as e:
         job_status = "Failed"
@@ -949,8 +963,11 @@ async def fetch_chunktext(
        json_obj = {
            'api_name': 'fetch_chunktext',
            'db_url': uri,
+<<<<<<< HEAD
            'userName': userName,
            'database': database,
+=======
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
            'document_name': document_name,
            'page_no': page_no,
            'logging_time': formatted_time(datetime.now(timezone.utc)),
@@ -968,6 +985,7 @@ async def fetch_chunktext(
        gc.collect()
 
 
+<<<<<<< HEAD
 @app.post("/backend_connection_configuation")
 async def backend_connection_configuation():
     try:
@@ -997,5 +1015,7 @@ async def backend_connection_configuation():
     finally:
         gc.collect()    
 
+=======
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
 if __name__ == "__main__":
     uvicorn.run(app)

backend/src/graphDB_dataAccess.py

@@ -362,7 +362,7 @@ def get_duplicate_nodes_list(self):
         score_value = float(os.environ.get('DUPLICATE_SCORE_VALUE'))
         text_distance = int(os.environ.get('DUPLICATE_TEXT_DISTANCE'))
         query_duplicate_nodes = """
-                MATCH (n:!Chunk&!Session&!Document&!`__Community__`) with n 
+                MATCH (n:!Chunk&!Session&!Document&!`__Community__`&!`__Entity__`) with n 
                 WHERE n.embedding is not null and n.id is not null // and size(toString(n.id)) > 3
                 WITH n ORDER BY count {{ (n)--() }} DESC, size(toString(n.id)) DESC // updated
                 WITH collect(n) as nodes

frontend/src/App.css

@@ -408,4 +408,4 @@
   z-index: 111;
   opacity: 0.8;
   background-color: rgb(201 201 201 / 40%);
-}
+}

frontend/src/components/ChatBot/Chatbot.tsx

@@ -445,6 +445,7 @@ const Chatbot: FC<ChatbotProps> = (props) => {
                         status={connectionStatus ? 'online' : 'offline'}
                         shape='square'
                         type='image'
+                        shape='square'
                       />
                     ) : (
                       <Avatar
@@ -455,6 +456,7 @@ const Chatbot: FC<ChatbotProps> = (props) => {
                         status={connectionStatus ? 'online' : 'offline'}
                         shape='square'
                         type='image'
+                        shape='square'
                       />
                     )}
                   </div>

frontend/src/components/Content.tsx

@@ -208,7 +208,7 @@ const Content: React.FC<ContentProps> = ({
     }
     toggleChunksLoading();
   };
-
+  
   const extractData = async (uid: string, isselectedRows = false, filesTobeProcess: CustomFile[]) => {
     if (!isselectedRows) {
       const fileItem = filesData.find((f) => f.id == uid);

frontend/src/components/Graph/GraphViewModal.tsx

@@ -349,7 +349,15 @@ const GraphViewModal: React.FunctionComponent<GraphViewModalProps> = ({
           'aria-labelledby': 'form-dialog-title',
         }}
       >
+<<<<<<< HEAD
         <Dialog.Header htmlAttributes={{ id: 'graph-title' }}>
+=======
+        <Dialog.Header
+          htmlAttributes={{
+            id: 'graph-title',
+          }}
+        >
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
           {headerTitle}
           {viewPoint !== graphLabels.chatInfoView && (
             <div style={{ display: 'flex', alignItems: 'center' }}>
@@ -403,7 +411,11 @@ const GraphViewModal: React.FunctionComponent<GraphViewModalProps> = ({
                       }}
                       nvlCallbacks={nvlCallbacks}
                     />
+<<<<<<< HEAD
                     <IconButtonArray orientation='vertical' isFloating={true} className='absolute bottom-4 right-4'>
+=======
+                    <IconButtonArray orientation='vertical' isFloating className='absolute bottom-4 right-4'>
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
                       {viewPoint !== 'chatInfoView' && (
                         <IconButtonWithToolTip
                           label='Refresh'

frontend/src/components/Graph/ResultOverview.tsx

@@ -114,11 +114,14 @@ const ResultOverview: React.FunctionComponent<OverViewProps> = ({
             <Typography variant='h3'>{graphLabels.resultOverview}</Typography>
             <div className={`text-input-container`}>
               <TextInput
+<<<<<<< HEAD
                 htmlAttributes={{
                   type: 'text',
                   'aria-label': 'search nodes',
                   placeholder: 'Search On Node Properties',
                 }}
+=======
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
                 value={searchQuery}
                 onChange={(e) => {
                   setSearchQuery(e.target.value);
@@ -127,14 +130,27 @@ const ResultOverview: React.FunctionComponent<OverViewProps> = ({
                 leftElement={
                   <IconButton
                     ariaLabel='Search Icon'
+<<<<<<< HEAD
                     isClean={true}
+=======
+                    isClean
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
                     size='small'
                     className='-mt-0.5'
                     htmlAttributes={{ type: 'submit' }}
                   >
+<<<<<<< HEAD
                     <MagnifyingGlassIconOutline className='n-size-token-7' />
+=======
+                    <MagnifyingGlassIconOutline />
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
                   </IconButton>
                 }
+                htmlAttributes={{
+                  type: 'text',
+                  'aria-label': 'search nodes',
+                  placeholder: 'Search On Node Properties',
+                }}
               />
             </div>
             <Typography variant='subheading-small'>

frontend/src/components/UI/ErrroBoundary.tsx

@@ -19,7 +19,11 @@ export default class ErrorBoundary extends React.Component<any, any> {
       return (
         <div className='n-size-full n-flex n-flex-col n-items-center n-justify-center n-rounded-md n-bg-palette-neutral-bg-weak n-box-border'>
           <Banner
+<<<<<<< HEAD
             hasIcon={true}
+=======
+            hasIcon
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
             type='info'
             description={
               this.state.errorMessage === 'Missing required parameter client_id.'
@@ -49,7 +53,11 @@ export default class ErrorBoundary extends React.Component<any, any> {
                     },
                   ]
             }
+<<<<<<< HEAD
             usage='inline'
+=======
+            usage='global'
+>>>>>>> 6a46472dcebfb9282c1c9d7332bcfacb30811661
           ></Banner>
         </div>
       );

frontend/src/types.ts

@@ -773,6 +773,11 @@ export interface GraphContextType {
   setLoadingGraph: Dispatch<SetStateAction<boolean>>;
 }
 
+export interface GraphContextType {
+  loadingGraph: boolean;
+  setLoadingGraph: Dispatch<SetStateAction<boolean>>;
+}
+
 export interface DatabaseStatusProps {
   isConnected: boolean;
   isGdsActive: boolean;