Merge pull request #97 from aymeric-roucher/main

Fix a link with updated notebook name

notebooks/en/agents.ipynb

@@ -31,19 +31,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.3.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "!pip install datasets huggingface_hub langchain sentence-transformers faiss-cpu serpapi google-search-results -q"
    ]
@@ -316,16 +306,6 @@
     "### Run the agent!"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%reload_ext autoreload\n",
-    "%autoreload 2"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 38,
@@ -375,6 +355,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "What happened here? First, the agent launched the retriever with specific sources in mind (`['transformers', 'blog']`).\n",
+    "\n",
+    "But this retrieval did not yield enough results ⇒ no problem! The agent could iterate on previous results, so it just re-ran its retrieval with less restrictive search parameters.\n",
+    "Thus the research was successful!\n",
+    "\n",
+    "Note that **using an LLM agent** that calls a retriever as a tool and can dynamically modify the query and other retrieval parameters **is a more general formulation of RAG**, which also covers many RAG improvement techniques like iterative query refinement.\n",
+    "\n",
     "## 3. 💻 Debugging Python code\n",
     "Since the ReactCodeAgent has an built int Python code interpreter, we can use it to debug our faulty Python script!"
    ]

notebooks/en/llm_judge.ipynb

@@ -684,9 +684,9 @@
     "\"\"\"\n",
     "```\n",
     "\n",
-    "**Implement with constrained generation:**\n",
+    "**Implement with structured generation:**\n",
     "\n",
-    "With constrained generation, you can configure the LLM judge to directly provide its output as a JSON with fields `Evaluation` and `Total rating`, which makes parsing easier : see our [constrained generation](constrained_generation) cookbook to learn more!\n",
+    "Using **structured generation**, you can configure the LLM judge to directly provide its output as a JSON with fields `Evaluation` and `Total rating`, which makes parsing easier : see our [structured generation](structured_generation) cookbook to learn more!\n",
     "\n",
     "## Conclusion\n",
     "\n",

notebooks/en/structured_generation.ipynb

@@ -78,7 +78,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Pprompting the model\n",
+    "## Prompting the model\n",
     "\n",
     "To get structured outputs from your model, you can simply prompt a powerful enough models with appropriate guidelines, and it should work directly... most of the time.\n",
     "\n",