Merge branch 'HKUDS:main' into main

.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

@@ -35,13 +35,18 @@ For example, you have the possibility to use ollama for the embedding and openai
 
 #### For Ollama Server
 - Ollama must be running and accessible
-- Default connection: http://localhost:11434
+- Requires environment variables setup or command line argument provided
-- Configure using --ollama-host if running on a different host/port
+- Environment variables: LLM_BINDING=ollama, LLM_BINDING_HOST, LLM_MODEL
+- Command line arguments: --llm-binding=ollama, --llm-binding-host, --llm-model
+- Default connection is  http://localhost:11434 if not priveded
 
-#### For OpenAI Server
+> The default MAX_TOKENS(num_ctx) for Ollama is 32768. If your Ollama server is lacking or GPU memory, set it to a lower value.
-- Requires valid OpenAI API credentials set in environment variables
+
-- OPENAI_API_KEY must be set
+#### For OpenAI Alike Server
-- LLM_BINDING or LLM_MODEL must be set by command line on in environment variables
+- Requires environment variables setup or command line argument provided
+- Environment variables: LLM_BINDING=ollama, LLM_BINDING_HOST, LLM_MODEL, LLM_BINDING_API_KEY
+- Command line arguments: --llm-binding=ollama, --llm-binding-host, --llm-model, --llm-binding-api-key
+- Default connection is https://api.openai.com/v1 if not priveded
 
 #### 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)):
@@ -62,6 +67,13 @@ az cognitiveservices account keys list --name $RESOURCE_NAME -g $RESOURCE_GROUP_
 ```
 The output of the last command will give you the endpoint and the key for the OpenAI API. You can use these values to set the environment variables in the `.env` file.
 
+```
+LLM_BINDING=azure_openai
+LLM_BINDING_HOST=endpoint_of_azure_ai
+LLM_MODEL=model_name_of_azure_ai
+LLM_BINDING_API_KEY=api_key_of_azure_ai
+```
+
 ### About Ollama API
 
 We provide an Ollama-compatible interfaces for LightRAG, aiming to emulate LightRAG as an Ollama chat model. This allows AI chat frontends supporting Ollama, such as Open WebUI, to access LightRAG easily.
@@ -159,6 +171,7 @@ PORT=7000 python lightrag.py
 | --llm-binding | ollama | LLM binding to be used. Supported: lollms, ollama, openai |
 | --llm-binding-host | (dynamic) | LLM server host URL. Defaults based on binding: http://localhost:11434 (ollama), http://localhost:9600 (lollms), https://api.openai.com/v1 (openai) |
 | --llm-model | mistral-nemo:latest | LLM model name |
+| --llm-binding-api-key | None | API Key for OpenAI Alike LLM |
 | --embedding-binding | ollama | Embedding binding to be used. Supported: lollms, ollama, openai |
 | --embedding-binding-host | (dynamic) | Embedding server host URL. Defaults based on binding: http://localhost:11434 (ollama), http://localhost:9600 (lollms), https://api.openai.com/v1 (openai) |
 | --embedding-model | bge-m3:latest | Embedding model name |

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,
         )
 

lightrag/llm.py

@@ -350,10 +350,11 @@ async def ollama_model_if_cache(
     timeout = kwargs.pop("timeout", None)
     kwargs.pop("hashing_kv", None)
     api_key = kwargs.pop("api_key", None)
-    headers = {
+    headers = (
-                "Content-Type": "application/json",
+        {"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"}
-                "Authorization": f"Bearer {api_key}"
+        if api_key
-                } if api_key else {"Content-Type": "application/json"}
+        else {"Content-Type": "application/json"}
+    )
     ollama_client = ollama.AsyncClient(host=host, timeout=timeout, headers=headers)
     messages = []
     if system_prompt:
@@ -386,10 +387,11 @@ async def lollms_model_if_cache(
 
     stream = True if kwargs.get("stream") else False
     api_key = kwargs.pop("api_key", None)
-    headers = {
+    headers = (
-                "Content-Type": "application/json",
+        {"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"}
-                "Authorization": f"Bearer {api_key}"
+        if api_key
-                } if api_key else {"Content-Type": "application/json"}
+        else {"Content-Type": "application/json"}
+    )
 
     # Extract lollms specific parameters
     request_data = {