feat(docs): explain var env

README.md

@@ -18,13 +18,21 @@ This tool serves as a customizable version of the amazing ClimateQA by Ekimetric
 0. **Fork the Repository**  
    Fork the original HuggingFace space: [Anything Q&A on HuggingFace](https://huggingface.co/spaces/LouisSanna/anything-question-answering).
 
-1. **Install Dependencies**
+1. **Set environment variables**
+
+For OpenAI API:
+
+```env
+OPENAI_API_KEY=...
+```
+
+2. **Install Dependencies**
 
    ```shell
    pip install -r requirements.txt
    ```
 
-2. **Add your data.**
+3. **Add your data.**
    Place the PDFs to be used as sources in the data folder. The subfolder and file names will be used as default identifiers by the tool.
 
    ```txt
@@ -36,13 +44,13 @@ This tool serves as a customizable version of the amazing ClimateQA by Ekimetric
            source_3.pdf
    ```
 
-3. **Build the index of semantic vectors**
+4. **Build the index of semantic vectors**
 
    ```bash
    python -m anyqa.build_index
    ```
 
-4. **Launch the app**
+5. **Launch the app**
 
    ```shell
    python app.py
@@ -53,3 +61,14 @@ And you're done!
 ## Deployment
 
 Deploying via Hugging Face Spaces is the most straightforward approach. Simply push your code to a HuggingFace Gradio space, and it will function as is.
+
+You will need to set the environments variables in the settings.
+
+## AI providers
+
+The following providers are currently supported:
+
+- OpenAI
+- Azure OpenAI
+
+The provider is picked based on the variable variables, see `example.env`.

example.env

@@ -0,0 +1,8 @@
+# To use OpenAI API
+OPENAI_API_KEY=...
+
+# To use Azure OpenAI API
+# AZURE_OPENAI_API_BASE_URL=
+# AZURE_OPENAI_API_VERSION=
+# AZURE_OPENAI_API_DEPLOYMENT_NAME=
+# AZURE_OPENAI_API_KEY=