Update lab 1 and 2 to granite 3.1

Signed-off-by: BJ Hargrave <[email protected]>

.pre-commit-config.yaml

@@ -3,7 +3,7 @@
 # Run `pre-commit install` to activate pre-commit hooks
 repos:
   - repo: https://github.com/kynan/nbstripout
-    rev: 0.7.1
+    rev: 0.8.1
     hooks:
       - id: nbstripout
         args: [

docs/lab-1/README.md

@@ -8,7 +8,7 @@ logo: images/ibm-blue-background.png
 
 [Text summarization](https://www.ibm.com/topics/text-summarization) condenses one or more texts into shorter summaries for enhanced information extraction.
 
-The goal of this lab is to show how you can use [IBM Granite Code](https://www.ibm.com/granite/docs/models/code/) models in order to apply long document summarization techniques to a work of literature.
+The goal of this lab is to show how you can use [IBM Granite](https://www.ibm.com/granite/docs/models/granite/) models in order to apply long document summarization techniques to a work of literature.
 
 ## Prerequisites
 

docs/pre-work/README.md

@@ -101,8 +101,8 @@ Running Ollama locally on your computer requires the following steps:
 1. In another terminal window, pull down the Granite models you will want to use in the workshop. Larger models take more memory to run but can give better results.
 
     ```shell
-    ollama pull granite3-dense:2b
-    ollama pull granite3-dense:8b
+    ollama pull granite3.1-dense:2b
+    ollama pull granite3.1-dense:8b
     ```
 
     For [Lab 4: Generating Bash Code with Granite Code](../lab-4/README.md), you will also need at least one of the following Granite Code models.

notebooks/RAG_with_Langchain.ipynb

@@ -83,7 +83,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install \"git+https://github.com/ibm-granite-community/utils.git\" \"langchain_community<0.3.0\" \"langchain-huggingface\" \"langchain_ollama\" \"langchain-milvus\" \"replicate\" \"wget\""
+    "! pip install \"git+https://github.com/ibm-granite-community/utils.git\" langchain_community langchain_huggingface langchain_ollama langchain-milvus replicate wget"
    ]
   },
   {
@@ -133,7 +133,7 @@
    "outputs": [],
    "source": [
     "from langchain_huggingface import HuggingFaceEmbeddings\n",
-    "embeddings_model = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")"
+    "embeddings_model = HuggingFaceEmbeddings(model_name=\"ibm-granite/granite-embedding-30m-english\")"
    ]
   },
   {
@@ -193,10 +193,14 @@
     "\n",
     "try: # Look for a locally accessible Ollama server for the model\n",
     "    response = requests.get(os.getenv(\"OLLAMA_HOST\", \"http://127.0.0.1:11434\"))\n",
-    "    model = OllamaLLM(model=\"granite3-dense:8b\")\n",
+    "    model = OllamaLLM(\n",
+    "        model=\"granite3.1-dense:8b\",\n",
+    "    )\n",
     "except Exception: # Use Replicate for the model\n",
-    "    model = Replicate(model=\"ibm-granite/granite-3.0-8b-instruct\",\n",
-    "                      replicate_api_token=get_env_var(\"REPLICATE_API_TOKEN\"))\n"
+    "    model = Replicate(\n",
+    "        model=\"ibm-granite/granite-3.1-8b-instruct\",\n",
+    "        replicate_api_token=get_env_var(\"REPLICATE_API_TOKEN\")\n",
+    "    )\n"
    ]
   },
   {
@@ -328,7 +332,9 @@
    "source": [
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
     "docs = vector_db.similarity_search(query)\n",
-    "print(docs[0].page_content)"
+    "print(f\"{len(docs)} documents returned\")\n",
+    "for i, d in enumerate(docs):\n",
+    "    print(f\"Document {i+1}\\n{d.page_content}\\n\")"
    ]
   },
   {