From 03d6b94c2959388a54b78769b399e46e6af00ea0 Mon Sep 17 00:00:00 2001 From: ggeutzzang Date: Mon, 4 Dec 2023 03:13:57 +0900 Subject: [PATCH] Fix: (issue #14066) DOC: Summarization output broken (#14078) - **Description:** : As described in the issue below, https://python.langchain.com/docs/use_cases/summarization I've modified the Python code in the above notebook to perform well. I also modified the OpenAI LLM model to the latest version as shown below. `gpt-3.5-turbo-16k --> gpt-3.5-turbo-1106` This is because it seems to be a bit more responsive. - **Issue:** : #14066 --- docs/docs/use_cases/summarization.ipynb | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/docs/use_cases/summarization.ipynb b/docs/docs/use_cases/summarization.ipynb index 82a5b16c66..72583aaf6b 100644 --- a/docs/docs/use_cases/summarization.ipynb +++ b/docs/docs/use_cases/summarization.ipynb @@ -181,7 +181,7 @@ "source": [ "We can use `chain_type=\"stuff\"`, especially if using larger context window models such as:\n", "\n", - "* 16k token OpenAI `gpt-3.5-turbo-16k` \n", + "* 16k token OpenAI `gpt-3.5-turbo-1106` \n", "* 100k token Anthropic [Claude-2](https://www.anthropic.com/index/claude-2)\n", "\n", "We can also supply `chain_type=\"map_reduce\"` or `chain_type=\"refine\"` (read more [here](/docs/modules/chains/document/refine))." @@ -212,7 +212,7 @@ "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n", "docs = loader.load()\n", "\n", - "llm = ChatOpenAI(temperature=0, model_name=\"gpt-3.5-turbo-16k\")\n", + "llm = ChatOpenAI(temperature=0, model_name=\"gpt-3.5-turbo-1106\")\n", "chain = load_summarize_chain(llm, chain_type=\"stuff\")\n", "\n", "chain.run(docs)" @@ -672,7 +672,7 @@ "summarize_document_chain = AnalyzeDocumentChain(\n", " combine_docs_chain=chain, text_splitter=text_splitter\n", ")\n", - "summarize_document_chain.run(docs[0])" + "summarize_document_chain.run(docs[0].page_content)" ] }, {