You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hey all, first I have to say thanks to McKay Wrigley for this amazing work. I have been working with the codebase for a couple days. I have a successful setup and can run the ui on localhost. I even have a local mistral 7b model working with prompts and queries so this is amazing. I will be looking through the codebase to investigate how to do this but I thought I would join in the discussion and ask if anyone has any ideas or experience on how to connect the UI to an Elasticsearch vector index. I have been building a rag pipeline into an Elasticsearch deep vector index for a project. I am training a mistral 7b model on some historical data that comes from pdf documents. The process goes, parse pdf documents with llama-parse to text or JSon, extract important data using python scripts and send to Elasticsearch index as structured documents. I have the documents stored in vector index in a nicely mapped way and can query the data from the elastic playground. I would like to connect the Elasticsearch index to the chatbot-ui to allow the models to have access to my index data. Does anyone have an idea on how to do this? I will be working through the codebase and will add what I find here as well. Thanks and keep on the innovation everyone!!!
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hey all, first I have to say thanks to McKay Wrigley for this amazing work. I have been working with the codebase for a couple days. I have a successful setup and can run the ui on localhost. I even have a local mistral 7b model working with prompts and queries so this is amazing. I will be looking through the codebase to investigate how to do this but I thought I would join in the discussion and ask if anyone has any ideas or experience on how to connect the UI to an Elasticsearch vector index. I have been building a rag pipeline into an Elasticsearch deep vector index for a project. I am training a mistral 7b model on some historical data that comes from pdf documents. The process goes, parse pdf documents with llama-parse to text or JSon, extract important data using python scripts and send to Elasticsearch index as structured documents. I have the documents stored in vector index in a nicely mapped way and can query the data from the elastic playground. I would like to connect the Elasticsearch index to the chatbot-ui to allow the models to have access to my index data. Does anyone have an idea on how to do this? I will be working through the codebase and will add what I find here as well. Thanks and keep on the innovation everyone!!!
Beta Was this translation helpful? Give feedback.
All reactions