I’m encountering an issue when trying to retrieve the top K base nodes using the RecursiveRetriever from LlamaIndex. Instead of retrieving only the top K base nodes, it retrieves from all top K nodes (including base and reference nodes) and then selects unique base nodes from this list.

I am trying to load index like this
load_index_from_storage(retrieved_sentence)

from llama_index.readers.database import DatabaseReader ModuleNotFoundError: No module named ‘llama_index.readers.database’ llama-index Use the below command to install pip install llama-index-readers-database

I am using Llama Index for the first time and I started with the tutorial here

I’m trying to experiment with LlamaIndex and build up a chatbot answering on provided documents and doing some research I ended up with a code like the following (I’ve purged out irrelevant parts):

i want to customize the system prompt for the ReAct agent in LlamaIndex and ,i cant seem to access any predefined prompt, nor be able to change

I’m using llama-index with the following code:

When I create VectorStoreIndex object, why does it require ChatGPT or some other LLM that will be used at the query time?

I am using LLamaindex SQLTableRetrieverQueryEngine for natural language to SQL interface. My schema has one of the table called ‘Suppliers’ which has the columns ‘Name’ and ‘ContactInfo’. One of the row values are ‘FitLife Sports Gear’ for Name, ‘[email protected]’ for ContactInfo.

I’m using RelevancyEvaluator when looping through the source_nodes of a query_engine response, and the .evaluate() says that every source node is passing (result.passing returns True). This is of course not correct, and is preventing me from obtaining the correct source node that was used by the llm to answer my query.