Updated OpenAI configuration and documentation.

- Added OpenAI alike example in .env.example
- Updated README for OpenAI alike server
- Modified API key handling in lightrag_server.py

.env.example

@@ -12,6 +12,12 @@ LLM_BINDING=ollama
 LLM_BINDING_HOST=http://host.docker.internal:11434
 LLM_MODEL=mistral-nemo:latest
 
+# OpenAI alike example
+# LLM_BINDING=openai
+# LLM_BINDING_HOST=https://localhost:11434/api
+# LLM_MODEL=deepseek-chat
+# LLM_BINDING_API_KEY=your_api_key
+
 # Lollms example
 # LLM_BINDING=lollms
 # LLM_BINDING_HOST=http://host.docker.internal:9600

lightrag/api/README.md

@@ -38,10 +38,9 @@ For example, you have the possibility to use ollama for the embedding and openai
 - Default connection: http://localhost:11434
 - Configure using --ollama-host if running on a different host/port
 
-#### For OpenAI Server
+#### For OpenAI Alike Server
 - Requires valid OpenAI API credentials set in environment variables
-- OPENAI_API_KEY must be set
-- LLM_BINDING or LLM_MODEL must be set by command line on in environment variables
+- LLM_BINDING, LLM_MODEL, LLM_BINDING_API_KEY  must be set by command line on in environment variables
 
 #### For Azure OpenAI Server
 Azure OpenAI API can be created using the following commands in Azure CLI (you need to install Azure CLI first from [https://docs.microsoft.com/en-us/cli/azure/install-azure-cli](https://docs.microsoft.com/en-us/cli/azure/install-azure-cli)):

lightrag/api/lightrag_server.py

@@ -616,7 +616,7 @@ def create_app(args):
             system_prompt=system_prompt,
             history_messages=history_messages,
             base_url=args.llm_binding_host,
-            api_key=os.getenv("OPENAI_API_KEY"),
+            api_key=args.llm_binding_api_key,
             **kwargs,
         )