Updating model kwargs usage in documentation (#227)

The arguments `frequency_penalty`, `presence_penalty`, and `top_p` in ChatOpenAI have been moved from direct parameters to the `model_kwargs` parameter. In this PR, I'm updating `README.md` and `docs/source/index.md` to reflect that change.
eyurtsev · Sep 23, 2023 · 77110c8 · 77110c8
1 parent 18c03b0
commit 77110c8
Show file tree

Hide file tree

Showing 2 changed files with 10 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -55,9 +55,11 @@ llm = ChatOpenAI(
     model_name="gpt-3.5-turbo",
     temperature=0,
     max_tokens=2000,
-    frequency_penalty=0,
-    presence_penalty=0,
-    top_p=1.0,
+    model_kwargs = {
+        'frequency_penalty':0,
+        'presence_penalty':0,
+        'top_p':1.0
+    }
 )
 
 schema = Object(

diff --git a/docs/source/index.md b/docs/source/index.md
@@ -25,9 +25,11 @@ llm = ChatOpenAI(
     model_name="gpt-3.5-turbo",
     temperature=0,
     max_tokens=2000,
-    frequency_penalty=0,
-    presence_penalty=0,
-    top_p=1.0,
+    model_kwargs = {
+        'frequency_penalty':0,
+        'presence_penalty':0,
+        'top_p':1.0
+    }
 )
 
 schema = Object(