Merge branch 'main' into manage-conversational-memory

CHANGELOG.md

@@ -4,27 +4,49 @@ All notable changes to this project will be documented in this file.
 
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
+## [0.3.1] - 2023-11-22
+
+### Added
+
++ Include biblio in embeddings by @lfoppiano in #21
+
+### Fixed
+
++ Fix conversational memory by @lfoppiano in #20
+
+## [0.3.0] - 2023-11-18
+
+### Added
+
++ add zephyr-7b by @lfoppiano in #15
++ add conversational memory in #18
+
+## [0.2.1] - 2023-11-01
+
+### Fixed
+
++ fix env variables by @lfoppiano in #9
 
 ## [0.2.0] – 2023-10-31
 
 ### Added
+
 + Selection of chunk size on which embeddings are created upon
-+ Mistral model to be used freely via the Huggingface free API 
++ Mistral model to be used freely via the Huggingface free API
 
 ### Changed
-+ Improved documentation, adding privacy statement 
+
++ Improved documentation, adding privacy statement
 + Moved settings on the sidebar
 + Disable NER extraction by default, and allow user to activate it
 + Read API KEY from the environment variables and if present, avoid asking the user
 + Avoid changing model after update
 
-
-
 ## [0.1.3] – 2023-10-30
 
 ### Fixed
 
-+ ChromaDb accumulating information even when new papers were uploaded 
++ ChromaDb accumulating information even when new papers were uploaded
 
 ## [0.1.2] – 2023-10-26
 
@@ -36,9 +58,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ### Fixed
 
-+ Github action build 
-+ dependencies of langchain and chromadb 
-
++ Github action build
++ dependencies of langchain and chromadb
 
 ## [0.1.0] – 2023-10-26
 
@@ -54,8 +75,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 + Kick off application
 + Support for GPT-3.5
 + Support for Mistral + SentenceTransformer
-+ Streamlit application 
-+ Docker image 
++ Streamlit application
++ Docker image
 + pypi package
 
 <!-- markdownlint-disable-file MD024 MD033 -->

README.md

@@ -14,6 +14,8 @@ license: apache-2.0
 
 **Work in progress** :construction_worker: 
 
+<img src="https://github.com/lfoppiano/document-qa/assets/15426/f0a04a86-96b3-406e-8303-904b93f00015" width=300 align="right" />
+
 ## Introduction
 
 Question/Answering on scientific documents using LLMs: ChatGPT-3.5-turbo, Mistral-7b-instruct and Zephyr-7b-beta.
@@ -25,9 +27,11 @@ Additionally, this frontend provides the visualisation of named entities on LLM
 
 The conversation is kept in memory up by a buffered sliding window memory (top 4 more recent messages) and the messages are injected in the context as "previous messages".   
 
+(The image on the right was generated with https://huggingface.co/spaces/stabilityai/stable-diffusion)
+
 **Demos**: 
- - (on HuggingFace spaces): https://lfoppiano-document-qa.hf.space/
- - (on the Streamlit cloud): https://document-insights.streamlit.app/
+ - (stable version): https://lfoppiano-document-qa.hf.space/
+ - (unstable version): https://document-insights.streamlit.app/
 
 ## Getting started