doc: updated readme for initial release

Author: limcheekin

.github/workflows/create-release.yml

@@ -0,0 +1,19 @@
+name: Create Release
+
+on:
+  push:
+    tags:
+      - "*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ncipollo/release-action@v1
+        with:
+          artifacts: "release.tar.gz"
+          bodyFile: "release.md"
+          draft: true

CONTRIBUTING.md

@@ -0,0 +1 @@
+**Working on your first Pull Request?** You can learn how from this *free* series [How to Contribute to an Open Source Project on GitHub](https://kcd.im/pull-request)

README.md

@@ -1,5 +1,7 @@
 # Open Source Text Embedding Models with OpenAI API-Compatible Endpoint
 
+[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com)
+
 Many open source projects support the compatibility of the `completions` and the `chat/completions` endpoints of the OpenAI API, but do not support the `embeddings` endpoint.
 
 The goal of this project is to create an OpenAI API-compatible version of the `embeddings` endpoint, which serves open source sentence-transformers models and other models supported by the LangChain's [HuggingFaceEmbeddings](https://api.python.langchain.com/en/latest/embeddings/langchain.embeddings.huggingface.HuggingFaceEmbeddings.html), HuggingFaceInstructEmbeddings and HuggingFaceBgeEmbeddings class.
@@ -22,25 +24,33 @@ To run the embeddings endpoint locally as a standalone FastAPI server, follow th
 
 1. Install the dependencies by executing the following commands:
 
-```bash
-pip install --no-cache-dir -r server-requirements.txt
-pip install --no-cache-dir uvicorn
-```
+   ```bash
+   pip install --no-cache-dir -r server-requirements.txt
+   pip install --no-cache-dir uvicorn
+   ```
 
 2. Run the server with the desired model using the following command which enabled normalize embeddings (Omit the `NORMALIZE_EMBEDDINGS` if the model don't support normalize embeddings):
 
-```bash
-MODEL=intfloat/e5-large-v2 NORMALIZE_EMBEDDINGS=1 python -m open.text.embeddings.server
-```
+   ```bash
+   MODEL=intfloat/e5-large-v2 NORMALIZE_EMBEDDINGS=1 python -m open.text.embeddings.server
+   ```
+
+   If a GPU is detected in the runtime environment, the server will automatically execute using the `cuba` mode. However, you have the flexibility to specify the `DEVICE` environment variable to choose between `cpu` and `cuba`. Here's an example of how to run the server with your desired configuration:
+
+   ```bash
+   MODEL=intfloat/e5-large-v2 NORMALIZE_EMBEDDINGS=1 DEVICE=cpu python -m open.text.embeddings.server
+   ```
+
+   This setup allows you to seamlessly switch between CPU and GPU modes, giving you control over the server's performance based on your specific requirements.
 
 3. You will see the following text from your console once the server has started:
 
-```bash
-INFO:     Started server process [19705]
-INFO:     Waiting for application startup.
-INFO:     Application startup complete.
-INFO:     Uvicorn running on http://localhost:8000 (Press CTRL+C to quit)
-```
+   ```bash
+   INFO:     Started server process [19705]
+   INFO:     Waiting for application startup.
+   INFO:     Application startup complete.
+   INFO:     Uvicorn running on http://localhost:8000 (Press CTRL+C to quit)
+   ```
 
 ## AWS Lambda Function
 
@@ -58,8 +68,12 @@ To get started:
 
 1. Install the dependencies by executing the following command:
 
-```bash
-pip install --no-cache-dir -r test-requirements.txt
-```
+   ```bash
+   pip install --no-cache-dir -r test-requirements.txt
+   ```
 
 2. Execute the cells in the notebook to test the embeddings endpoint.
+
+## Contributions
+
+@Vokturz contributed #2: support for CPU/GPU choice and initialization before starting the app.

open/text/embeddings/server/app.py

@@ -23,7 +23,7 @@ def create_app():
     initialize_embeddings()
     app = FastAPI(
         title="Open Text Embeddings API",
-        version="0.0.2",
+        version="1.0.0",
     )
     app.add_middleware(
         CORSMiddleware,

release.md

@@ -0,0 +1 @@
+@Vokturz contributed #2: support for CPU/GPU choice and initialization before starting the app