-
Pandas
Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more
-
pandas-ai
Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
I think that the model should be able to understand to use a tool like [pandas](https://pandas.pydata.org/) and not to analyze the data with it's capabilities.
you could use this https://github.com/gventuri/pandas-ai
It sounds like you're asking for similar functionality to https://github.com/imartinez/privateGPT. PrivateGPT lets you ingest multiple file types (including csv) into a local vector db that you can searching using any local LLM. I would recommend checking it out, it's been fun tinkering with so far.