From c9f93f5f7416f719dea663192727ce43151118fe Mon Sep 17 00:00:00 2001
From: tmyjoe <tmyjoe@users.noreply.github.com>
Date: Fri, 7 Apr 2023 23:27:03 +0900
Subject: [PATCH] fix: token counting for chat openai. (#2543)

I noticed that the value of get_num_tokens_from_messages in `ChatOpenAI`
is always one less than the response from OpenAI's API. Upon checking
the official documentation, I found that it had been updated, so I made
the necessary corrections.
Then now I got the same value from OpenAI's API.


https://github.com/openai/openai-cookbook/commit/d972e7482ed71d36e12f5b058380a61d516bc6d0#diff-2d4485035b3a3469802dbad11d7b4f834df0ea0e2790f418976b303bc82c1874L474
---
 langchain/chat_models/openai.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/langchain/chat_models/openai.py b/langchain/chat_models/openai.py
index 667934d8..6d510d4b 100644
--- a/langchain/chat_models/openai.py
+++ b/langchain/chat_models/openai.py
@@ -400,5 +400,5 @@ class ChatOpenAI(BaseChatModel):
                 if key == "name":
                     num_tokens += tokens_per_name
         # every reply is primed with <im_start>assistant
-        num_tokens += 2
+        num_tokens += 3
         return num_tokens