The agent engineering platform.
Python agentsaiai-agentsanthropicchatgptdeepagentsenterpriseframeworkgeminigenerative-ailangchainlanggraphllmmultiagentopen-sourceopenaipydanticpythonragtypescript
docs: Update Multi_modal_RAG_google.ipynb to remove the unsupported Gemini models (#31526)
Soumendra kumar sahooe455fab5d3ca
diff --git a/cookbook/Multi_modal_RAG_google.ipynb b/cookbook/Multi_modal_RAG_google.ipynbindex 35bdfff764..579f8c7dfe 100644--- a/cookbook/Multi_modal_RAG_google.ipynb+++ b/cookbook/Multi_modal_RAG_google.ipynb@@ -185,7 +185,7 @@" )\n"," # Text summary chain\n"," model = VertexAI(\n",- " temperature=0, model_name=\"gemini-pro\", max_tokens=1024\n",+ " temperature=0, model_name=\"gemini-2.0-flash-lite-001\", max_tokens=1024\n"," ).with_fallbacks([empty_response])\n"," summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n","\n",@@ -254,7 +254,7 @@"\n","def image_summarize(img_base64, prompt):\n"," \"\"\"Make image summary\"\"\"\n",- " model = ChatVertexAI(model=\"gemini-pro-vision\", max_tokens=1024)\n",+ " model = ChatVertexAI(model=\"gemini-2.0-flash\", max_tokens=1024)\n","\n"," msg = model.invoke(\n"," [\n",@@ -394,7 +394,7 @@"# The vectorstore to use to index the summaries\n","vectorstore = Chroma(\n"," collection_name=\"mm_rag_cj_blog\",\n",- " embedding_function=VertexAIEmbeddings(model_name=\"textembedding-gecko@latest\"),\n",+ " embedding_function=VertexAIEmbeddings(model_name=\"text-embedding-005\"),\n",")\n","\n","# Create retriever\n",@@ -553,7 +553,7 @@" \"\"\"\n","\n"," # Multi-modal LLM\n",- " model = ChatVertexAI(temperature=0, model_name=\"gemini-pro-vision\", max_tokens=1024)\n",+ " model = ChatVertexAI(temperature=0, model_name=\"gemini-2.0-flash\", max_tokens=1024)\n","\n"," # RAG pipeline\n"," chain = (\n",