Document how to use remote server with Ollama (#276)

Author: stellasia

docs/source/user_guide_rag.rst

@@ -223,7 +223,10 @@ it can be queried using the following:
 .. code:: python
 
     from neo4j_graphrag.llm import OllamaLLM
-    llm = OllamaLLM(model_name="orca-mini")
+    llm = OllamaLLM(
+        model_name="orca-mini",
+        # host="...",  # when using a remote server
+    )
     llm.invoke("say something")
 
 

examples/customize/embeddings/ollama_embeddings.py

@@ -6,6 +6,7 @@
 
 embeder = OllamaEmbeddings(
     model="<model_name>",
+    # host="...",  # if using a remote server
 )
 res = embeder.embed_query("my question")
 print(res[:10])

examples/customize/llms/ollama_llm.py

@@ -6,6 +6,7 @@
 
 llm = OllamaLLM(
     model_name="<model_name>",
+    # host="...",  # if using a remote server
 )
 res: LLMResponse = llm.invoke("What is the additive color model?")
 print(res.content)