From 74c7b799ef16a9987c5d13200b16f176b9d16ae1 Mon Sep 17 00:00:00 2001
From: Max Weng <zhiyong.weng@gmail.com>
Date: Tue, 5 Dec 2023 12:27:54 +0800
Subject: [PATCH] migrate openai audio api (#13557)

for issue https://github.com/langchain-ai/langchain/issues/13162
migrate openai audio api, as [openai v1.0.0 Migration
Guide](https://github.com/openai/openai-python/discussions/742)

<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change,
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->

---------

Co-authored-by: Double Max <max@ground-map.com>
---
 .../document_loaders/parsers/audio.py          | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/libs/langchain/langchain/document_loaders/parsers/audio.py b/libs/langchain/langchain/document_loaders/parsers/audio.py
index 073eb82ea08..737cfd147a3 100644
--- a/libs/langchain/langchain/document_loaders/parsers/audio.py
+++ b/libs/langchain/langchain/document_loaders/parsers/audio.py
@@ -6,6 +6,7 @@ from langchain_core.documents import Document
 
 from langchain.document_loaders.base import BaseBlobParser
 from langchain.document_loaders.blob_loaders import Blob
+from langchain.utils.openai import is_openai_v1
 
 logger = logging.getLogger(__name__)
 
@@ -36,9 +37,13 @@ class OpenAIWhisperParser(BaseBlobParser):
                 "pydub package not found, please install it with " "`pip install pydub`"
             )
 
-        # Set the API key if provided
-        if self.api_key:
-            openai.api_key = self.api_key
+        if is_openai_v1():
+            # api_key optional, defaults to `os.environ['OPENAI_API_KEY']`
+            client = openai.OpenAI(api_key=self.api_key)
+        else:
+            # Set the API key if provided
+            if self.api_key:
+                openai.api_key = self.api_key
 
         # Audio file from disk
         audio = AudioSegment.from_file(blob.path)
@@ -63,7 +68,12 @@ class OpenAIWhisperParser(BaseBlobParser):
             attempts = 0
             while attempts < 3:
                 try:
-                    transcript = openai.Audio.transcribe("whisper-1", file_obj)
+                    if is_openai_v1():
+                        transcript = client.audio.transcriptions.create(
+                            model="whisper-1", file=file_obj
+                        )
+                    else:
+                        transcript = openai.Audio.transcribe("whisper-1", file_obj)
                     break
                 except Exception as e:
                     attempts += 1