Merge pull request #1258 from rbrisita/fix_doc

Fix Documentation

Author: KillianLucas

docs/language-models/custom-models.mdx

@@ -9,21 +9,20 @@ As long as your system can accept an input and stream an output (and can be inte
 Simply replace the OpenAI-compatible `completions` function in your language model with one of your own:
 
 ```python
-def custom_language_model(openai_message):
+def custom_language_model(messages, model, stream, max_tokens):
     """
     OpenAI-compatible completions function (this one just echoes what the user said back).
+    To make it OpenAI-compatible and parsable, `choices` has to be the root property.
+    The property `delta` is used to signify streaming.
     """
-    users_content = openai_message[-1].get("content") # Get last message's content
-
-    # To make it OpenAI-compatible, we yield this first:
-    yield {"delta": {"role": "assistant"}}
+    users_content = messages[-1].get("content") # Get last message's content
 
     for character in users_content:
-        yield {"delta": {"content": character}}
+        yield {"choices": [{"delta": {"content": character}}]}
 
 # Tell Open Interpreter to power the language model with this function
 
-interpreter.llm.completion = custom_language_model
+interpreter.llm.completions = custom_language_model
 ```
 
 Then, set the following settings:
@@ -39,4 +38,4 @@ And start using it:
 
 ```
 interpreter.chat("Hi!") # Returns/displays "Hi!" character by character
-```
+```