snassimr

@jerryjliu Spectacular !!! Thanks a lot . If the upgrade will tackle multi-pdf as multi-document problem or each agent would be responsible for its own PDF ? Optionality for multi-document...

Hi , Looks like I wanted too much . I thought it's possible to add , i.e. keyword_query_engine (SimpleKeywordTableIndex) and agent_util.py code (create_agent function) to be updated accordingly. It will...

Hi , I've got a chance to set filepath during this conversation at Home page :   But bot at Generated RAG Agent still unable to answer questions about...

Hi , Sorry for late answer . The issue was with pdf file name . Linux doesn't suffer blanks and file actually wasn't loaded at home page. After @jerryjliu point...

Regarding setting filepath - use bot at home page . Here the example for first filepath setting 👍  And continue with the bot until you get : 

Hi , @anoopshrma I see agent created , but looks some more data should persisted to let know the Agent what PDF it aware of to answer question about ....

Hi ! I think I passed this step and can help here . You should create subfolder .streamlit and secrets.toml file in it with openai_key value. Here my case :...

> Thanks! That gave me another idea which ended up working too, it seems. Any concerns doing it this way? > > ```python > import os > from nemoguardrails.rails.llm.config import...

Hi , @ChuckHend and @drazvan , I tried both solutions and at some step I am getting error due to missing OPENAI_API_KEY (each solution provide similar , bit not exactly...

Hi , @omarrayyman I didn't succeeded to drop dependency on OpenAI as ChuckHend proposed . I guess it's due to langchain's . Eventually , I switched to OpenAI due to...