Hello Experts,
We are using chat engine for our ChatBot implementation (on top of our documents RAG). We want the chat engine to only respond to queries in context on our documents and should not respond to any other general questions like 'Who created Harry Potter'. How can we enforce ChatBot to behave/respond just for our documents context?

Hello Everyone,
Hope all of you are having a great day!
Couple of questions:
1: As part of RAG implementation, how can we return back link to the original document from where the chatbot gave the answer?
2: As part of RAG implementation, the pdf doc text might contain some external links, how can we retain that as part of the answer being returned from the chatbot?

Hey Everyone!! Hope you guys are having amazing day/evening!
Do we have a sample code for text-to-sql for teradata and snowflakes?

when trying to initialize OpensearchVectorClient for AWS OpenSearch Service instance, getting ConnectionTimeout error. Please help 🥺

credentials = boto3.Session().get_credentials() awsauth = AWS4Auth(region = region, service=service, refreshable_credential=credentials) client = OpensearchVectorClient( endpoint, idx, 4096, http_auth=awsauth, embedding_field=embedding_field, text_field=text_field, use_ssl=true, verify_certs=true,connection_class=RequestsHttpConnection, timeout=30, port=443, )

Hello Everyone,
In my usecase for LlamaIndex, I want to create Knowledge base from very large number of PDFs and website pages, and then have question and answer system build on top of that. Is there a way through which the query_engine would return the relevant answers along with link to the website page or the PDF name?

Hello Everyone,
I have a simple use-case. I have list of several pdfs (overall size could be 100s of MBs). I want to create a question-answering system on top of these pdfs. How can I build my RAG pipeline using LlamaIndex and ChatGPT? Sample notebook would be really helpful! Thanks in advance!!

Hey LlamaIndex CoreTeam,
Could you please enable streaming options for NLSQLTableQueryEngine, SQLTableRetrieverQueryEngine, RetrieverQueryEngine? It will be really helpful showing the response back as streaming

Hello Experts,
How to use llama_index with quantized llama2 models?

I am new to the whole LLM ecosystem, trying to wrap my head around llama_index and langchain. Could someone help me understand the difference between gptvectorstoreindex/gptlistindex/gptsimplevectorindex?