update docker image documentation for multi-model

Makefile

@@ -4,8 +4,8 @@
 VERSION := $(shell grep -m1 version pyproject.toml | cut -d'"' -f2)
 IMAGE_NAME := lfnovo/open_notebook
 
-# Plataformas mais comumente suportadas pela imagem Python
-PLATFORMS=linux/amd64,linux/arm64,linux/arm/v7,linux/386
+PLATFORMS=linux/amd64,linux/arm64
+#,linux/arm/v7,linux/386
 
 database:
 	docker compose up -d

README.md

@@ -50,7 +50,7 @@ services:
 
 Go to the [Usage](docs/USAGE.md) page to learn how to use all features.
 
-## 🚀 Features
+## Features
 
 ![New Notebook](docs/assets/asset_list.png)
 
@@ -63,6 +63,17 @@ Go to the [Usage](docs/USAGE.md) page to learn how to use all features.
 - **Fine-Grained Context Management**: Choose exactly what to share with the AI to maintain control.
 - **Cost Estimation**: Estimate costs for large context processing to keep budget control in check.
 
+## 🚀 New Features
+
+  ### v0.0.2 - Several new providers are supported now:
+
+- OpenAI
+- Anthropic
+- Open Router
+- LiteLLM
+- Vertex AI
+- Ollama
+
 ### 📝 Notebook Page
 
 Three intuitive columns to streamline your work:

docs/SETUP.md

@@ -1,7 +1,9 @@
-# Installing Open Notebook
+# Configuration and Setup
+
+## Installing Open Notebook
 
 
-## 📦 Installing from Source
+### 📦 Installing from Source
 
 Quickly get started by cloning and installing the dependencies.
 
@@ -9,24 +11,11 @@ Quickly get started by cloning and installing the dependencies.
 git clone https://github.com/lfnovo/open_notebook.git
 cd open_notebook
 poetry install
+cp .env.example .env
+poetry run streamlit run app_home.py
 ```
 
-Make a copy of `example.env` and rename it to `.env`.
-
-You need to enter at least your OPENAI_API_KEY and the Surreal DB connection details. 
-
-```
-OPENAI_API_KEY=
-
-# CONNECTION DETAILS FOR YOUR SURREAL DB
-SURREAL_ADDRESS="ws://localhost:8000/rpc"
-SURREAL_USER="root"
-SURREAL_PASS="root"
-SURREAL_NAMESPACE="open_notebook"
-SURREAL_DATABASE="staging"
-```
-
-Then, run it by using:
+Run the app with: 
 
 ```sh
 poetry run streamlit run app_home.py
@@ -38,9 +27,13 @@ or the shourcut
 make run
 ```
 
-## 🐳 Docker Setup
+> ⚠️ **Important:** Be sure to edit the `.env` file before running the app.
+
+
+### 🐳 Docker Setup
 
 Alternatively, you can use Docker for easy setup.
+
 Copy the `.env.example` file and name it `docker.env`
 
 ```sh
@@ -121,8 +114,55 @@ services:
     pull_policy: always
 ```
 
+
+## Setting up the providers
+
+Several new providers are supported now:
+
+- OpenAI
+- Anthropic
+- Open Router
+- LiteLLM
+- Vertex AI
+- Ollama
+
+All providers are installed out of the box. All you need to do is to setup the environment variable configurations (API Keys, etc) for your selected provider and decide which models to use. 
+
+Please refer to the `.env.example` file for instructions on which ENV variables are necessary for each. 
+
+### Use provider-modelname convention
+
+You should prepend the provider name to the model_name when setting up your env variables, examples: 
+
+- openai/gpt-4o-mini
+- anthropic/claude-3-5-sonnet-20240620
+- ollama/gemma2
+- openrouter/nvidia/llama-3.1-nemotron-70b-instruct
+- vertexai/gemini-1.5-flash-001
+
+__There will be a UI configuration for models in the coming days.__
+
+## Setup 2 models for more flexibility
+
+There are 2 configurations for models at this point: 
+
+```
+DEFAULT_MODEL="openai/gpt-4o-mini"
+SUMMARIZATION_MODEL="openrouter/nvidia/llama-3.1-nemotron-70b-instruct"
+```
+
+- **DEFAULT_MODEL** is used by the chat tool
+- **SUMMARIZATION_MODEL (optional)** is used on the content summarization
+
+The reason for opting for this route is because different LLMs, will behave better/worse depending on the type of request and type of tools offered. So it makes sense to build a more refined system to decide which model should process which task.
+
+For instance, we can use an Ollama based model, like `gemma2` to do summarization and document query, and use openai/claude for the chat. The whole idea is to allow you to experiment on cost/performance.
+
+
 ## Running the app
 
 After the app is running, you can access it at http://localhost:8080.
 
-The first time you connect, it will check for the database and see if the schema is ready. If not, it will create the database for you. 
+The first time you connect, it will check for the database and see if the schema is ready. If not, it will create the database for you. 
+
+Go to the [Usage](USAGE.md) page to learn how to use all features.