X-Pipe/flash

Merge pull request #2 from NickNYU/feature/multi-docs

change to tree-summarize to try map-reduce

[bugfix]fix the cut-off issue due to LLM predict token limit(256 for openai python lib default), by setting temperature to 0 and set LLM predict method from compact-refine to refine

add pip install reqiurement

Merge pull request #1 from NickNYU/main

add dependency for dotenv

reformat well

fix changes

reformat

refactor

reformat

Merge branch 'master' of https://github.com/NickNYU/llama-xpipe

first edition

remove unused file

add dataset and change langchain directory name to langchain_manager, incase of a name consuming in python

app.py fixable to match hugging-face's app portal

pylint and py format ready

add tools

add modulars

refactor directory construct

Add files via upload

Initial commit