From e131156805962fd8fa2a984f0f7d996475d0c089 Mon Sep 17 00:00:00 2001
From: AeroXi <31943024+AeroXi@users.noreply.github.com>
Date: Fri, 7 Apr 2023 13:32:24 +0800
Subject: [PATCH] set default embedding max token size (#2330)

#991 has already implemented this convenient feature to prevent
exceeding max token limit in embedding model.

> By default, this function is deactivated so as not to change the
previous behavior. If you specify something like 8191 here, it will work
as desired.
According to the author, this is not set by default.
Until now, the default model in OpenAIEmbeddings's max token size is
8191 tokens, no other openai model has a larger token limit.
So I believe it will be better to set this as default value, other wise
users may encounter this error and hard to solve it.
---
 langchain/embeddings/openai.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/langchain/embeddings/openai.py b/langchain/embeddings/openai.py
index fd57d281..6c206ebc 100644
--- a/langchain/embeddings/openai.py
+++ b/langchain/embeddings/openai.py
@@ -96,7 +96,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
     #  https://github.com/openai/openai-python/issues/132
     document_model_name: str = "text-embedding-ada-002"
     query_model_name: str = "text-embedding-ada-002"
-    embedding_ctx_length: int = -1
+    embedding_ctx_length: int = 8191
     openai_api_key: Optional[str] = None
     chunk_size: int = 1000
     """Maximum number of texts to embed in each batch"""