github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-06-23 15:19:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: Update Multi_modal_RAG_google.ipynb to remove the unsupported Gemini models (#31526)

Browse Source 
- **Description:** Remove the outdated Gemini models and replace those
with the latest models.
- **Issue:** Earlier the code was not running, now the code runs.
- **Dependencies:** No
- **Twitter handle:** [soumendrak_](https://x.com/soumendrak_)
This commit is contained in:
Soumendra kumar sahoo 2025-06-10 06:56:01 +05:30 committed by GitHub
parent b21526fe38
commit e455fab5d3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
cookbook/Multi_modal_RAG_google.ipynb
View File

@ -185,7 +185,7 @@
" )\n", " )\n",
" # Text summary chain\n", " # Text summary chain\n",
" model = VertexAI(\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", " ).with_fallbacks([empty_response])\n",
" summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n", " summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
"\n", "\n",
@ -254,7 +254,7 @@
"\n", "\n",
"def image_summarize(img_base64, prompt):\n", "def image_summarize(img_base64, prompt):\n",
" \"\"\"Make image summary\"\"\"\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", "\n",
" msg = model.invoke(\n", " msg = model.invoke(\n",
" [\n", " [\n",
@ -394,7 +394,7 @@
"# The vectorstore to use to index the summaries\n", "# The vectorstore to use to index the summaries\n",
"vectorstore = Chroma(\n", "vectorstore = Chroma(\n",
" collection_name=\"mm_rag_cj_blog\",\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",
"\n", "\n",
"# Create retriever\n", "# Create retriever\n",
@ -553,7 +553,7 @@
" \"\"\"\n", " \"\"\"\n",
"\n", "\n",
" # Multi-modal LLM\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", "\n",
" # RAG pipeline\n", " # RAG pipeline\n",
" chain = (\n", " chain = (\n",