Is this bug or I am missing something . I have a pdf of 307 token, I am ingesting into chromadb with llamaindex IngestionPipeline, My chunk size is 1024, after ingestion i see it creates 2 vectors in chroma collection , i am expecting one collection because the pdf is of 307 token and my chunk size is 1024. when i set chunk size to 210 it creates 7 vectors (I mean chroma_collection.count()=7)

Hi , can anyone give me some ideas about how i can stream ReAct agent's activity on react js frontend

Hi, "How can I build this with llamaindex", suppose I have 1000 questions-answer set in a pdf file on a topic by different expert , i want to build an application where , people will ask question and if there is one or more answer to his/her question , he/she will get the answer from the document with reference (reference means , he/she will get the answer and also the name of the expert who gave the answer)

I was going through the Agent tutorial ,I am just curious, what are core capability difference between llamaindex ReACT agent and FunctionCallingAgent from RAG application building perspective?

"Should I create tools for every file and save that in database?"
Hi,

I am building a RAG SaaS project where users will upload hundreds or thousands of PDFs, docs, and other file types. I need the agent to answer questions based on these documents. What is the most efficient way to create query engine tools for the agent?

1. Should I provide the agent with a single query engine tool and indicate that it can handle any type of question?
2. Alternatively, should I create and save separate query engine tools for each document upon upload and provide the agent with a list of these tools?

Additionally, does saving individual query engine tools for each document even work effectively?

Thank you for your help!

Hi, I am thinking about adding functionality like sending email, creating jira ticket , creating event in calendar etc in my llamaindex project , can anyone please suggest resource regarding that. Thank you.