Housekeeping

week5/day4.ipynb

@@ -168,13 +168,13 @@
     "# Put the chunks of data into a Vector Store that associates a Vector Embedding with each chunk\n",
     "# Chroma is a popular open source Vector Database based on SQLLite\n",
     "\n",
-    "embeddings = OpenAIEmbeddings()\n",
+    "# embeddings = OpenAIEmbeddings()\n",
     "\n",
     "# If you would rather use the free Vector Embeddings from HuggingFace sentence-transformers\n",
     "# Then replace embeddings = OpenAIEmbeddings()\n",
     "# with:\n",
-    "# from langchain.embeddings import HuggingFaceEmbeddings\n",
-    "# embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-MiniLM-L6-v2\")\n",
+    "from langchain.embeddings import HuggingFaceEmbeddings\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=\"sentence-transformers/all-MiniLM-L6-v2\")\n",
     "\n",
     "# Delete if already exists\n",
     "\n",
@@ -329,6 +329,23 @@
     "</table>"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3dd0a478-bde4-41f8-8fe8-a35d3246e1b6",
+   "metadata": {},
+   "source": [
+    "## Alternative: to use a free open-source model instead of OpenAI in the next cell\n",
+    "\n",
+    "First run this in a cell: `!pip install langchain-ollama`\n",
+    "\n",
+    "Then replace `llm = ChatOpenAI(temperature=0.7, model_name=MODEL)` with:\n",
+    "\n",
+    "```python\n",
+    "from langchain_ollama import ChatOllama\n",
+    "llm = ChatOllama(temperature=0.7, model=\"llama3.2\")\n",
+    "```"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,