@ -181,7 +181,7 @@
"source": [
"source": [
"We can use `chain_type=\"stuff\"`, especially if using larger context window models such as:\n",
"We can use `chain_type=\"stuff\"`, especially if using larger context window models such as:\n",
"\n",
"\n",
"* 16k token OpenAI `gpt-3.5-turbo-16k ` \n",
"* 16k token OpenAI `gpt-3.5-turbo-110 6` \n",
"* 100k token Anthropic [Claude-2](https://www.anthropic.com/index/claude-2)\n",
"* 100k token Anthropic [Claude-2](https://www.anthropic.com/index/claude-2)\n",
"\n",
"\n",
"We can also supply `chain_type=\"map_reduce\"` or `chain_type=\"refine\"` (read more [here](/docs/modules/chains/document/refine))."
"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",
"loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
"docs = loader.load()\n",
"docs = loader.load()\n",
"\n",
"\n",
"llm = ChatOpenAI(temperature=0, model_name=\"gpt-3.5-turbo-16k \")\n",
"llm = ChatOpenAI(temperature=0, model_name=\"gpt-3.5-turbo-110 6\")\n",
"chain = load_summarize_chain(llm, chain_type=\"stuff\")\n",
"chain = load_summarize_chain(llm, chain_type=\"stuff\")\n",
"\n",
"\n",
"chain.run(docs)"
"chain.run(docs)"
@ -672,7 +672,7 @@
"summarize_document_chain = AnalyzeDocumentChain(\n",
"summarize_document_chain = AnalyzeDocumentChain(\n",
" combine_docs_chain=chain, text_splitter=text_splitter\n",
" combine_docs_chain=chain, text_splitter=text_splitter\n",
")\n",
")\n",
"summarize_document_chain.run(docs[0])"
"summarize_document_chain.run(docs[0].page_content )"
]
]
},
},
{
{