From c432666d18fbf78de8b3523eaf9626d8a20856a1 Mon Sep 17 00:00:00 2001
From: Gustaf Rydholm <gustaf.rydholm@gmail.com>
Date: Tue, 9 Apr 2024 00:49:34 +0200
Subject: Update README

---
 README.md | 44 ++++++++++++++++++++++++++++++++++++++------
 1 file changed, 38 insertions(+), 6 deletions(-)

(limited to 'README.md')

diff --git a/README.md b/README.md
index ff86560..39c954b 100644
--- a/README.md
+++ b/README.md
@@ -24,9 +24,17 @@ DOCUMENT_DB_USER = <DOCUMENT_DB_USER>
 
 QDRANT_URL = <QDRANT_URL>
 QDRANT_COLLECTION_NAME = <QDRANT_COLLECTION_NAME>
+
+COHERE_API_KEY = <COHERE_API_KEY> # OPTIONAL
 ```
 
-### Ollama 
+### Ollama
+
+Make sure ollama is running:
+
+```sh
+ollama serve
+```
 
 Download the encoder and generator models with ollama:
 
@@ -43,18 +51,40 @@ Download and run qdrant.
 
 ### Postgres
 
-Postgres is used to save hashes of the document chunks to prevent document chunks from 
+Postgres is used to save hashes of the document chunks to prevent document chunks from
 being added to the vector db more than ones.
 
 Download and run qdrant.
 
-#### Running
+### Cohere
+
+Get an API from their website.
+
+### Running
+
+#### Prerequisites
+
+##### Python Environment
+
+Activate the poetry shell:
 
-Build script/or FE for adding pdfs or retrieve information
+```sh
+poetry shell
+```
+
+#### CLI
+
+```sh
+python rag/cli.py
+```
 
-### Frontend (Low priority)
+#### UI
 
-[streamlit](https://github.com/streamlit/streamlit)
+Run the web app with streamlit:
+
+```sh
+streamlit run rag/ui.py
+```
 
 ### Notes
 
@@ -68,3 +98,5 @@ I took some inspiration from these tutorials.
 [rag-openai-qdrant](https://colab.research.google.com/github/qdrant/examples/blob/master/rag-openai-qdrant/rag-openai-qdrant.ipynb)
 
 [building-rag-application-using-langchain-openai-faiss](https://medium.com/@solidokishore/building-rag-application-using-langchain-openai-faiss-3b2af23d98ba)
+
+[knowledge_gpt](https://github.com/mmz-001/knowledge_gpt)
-- 
cgit v1.2.3-70-g09d2