index = VectorStoreIndex.from_documents(documents, service_context=service_context, storage_context=storage_context) ## OR define service context globally and no need to pass it to anywhere from llama_index import set_global_service_context set_global_service_context(service_context) index = VectorStoreIndex.from_documents(documents,storage_context=storage_context)
index = VectorStoreIndex.from_documents(documents, service_context=service_context, storage_context=storage_context)
from llama_index import set_global_service_context
mongodb_client = pymongo.MongoClient(_mongoURI)
db_name = f"{dossier}"
store = MongoDBAtlasVectorSearch(mongodb_client, db_name=db_name)
storage_context = StorageContext.from_defaults(vector_store=store)
# You need to create the service context above this line
set_global_service_context(service_context)
documents = SimpleDirectoryReader("./Sources").load_data()
index = VectorStoreIndex.from_documents(documents,storage_context=storage_context)
from flask import Flask, jsonify
import threading
app = Flask(__name__)
def process_data(data):
# Perofrm the indexing here!!!
# Process data here (simulated by printing)
print(f"Processing data: {data}")
# Simulate a long-running task
# Replace this with your actual data processing logic
import time
time.sleep(5)
return f"Processed data: {data}"
@app.route('/process', methods=['POST'])
def process():
# Recieve your files and send it to the method
data = request.json # Assuming data is sent in JSON format
# Start a new thread to process the data
thread = threading.Thread(target=process_data, args=(data,))
thread.start()
# Return an immediate response to the client
return jsonify({"message": "Indexing data on a separate thread."})
if __name__ == '__main__':
app.run(debug=True) embed_model = AzureOpenAIEmbedding(
model=model.LearningModel.Model,
deployment_name=model.LearningModel.Name,
api_key=openai.api_key,
azure_endpoint=openai.base_url,
api_version=openai.api_version,
embed_batch_size=50 # This is by default 10
)