diff --git a/README.md b/README.md
index faa01c2..a9ae458 100644
--- a/README.md
+++ b/README.md
@@ -7,6 +7,63 @@ workflows, aka [agile modeling](https://arxiv.org/abs/2302.12948).
 While we get this documentation ready, we recommend checking out the main
 [Perch repository](https://github.com/google-research/perch).
 
+This repository consists of four sub-libraries:
+
+* `db` - The core database functionality for storing embeddings and related
+metadata. The database also handles labels applied to embeddings and vector
+search, both exact and approximate.
+* `agile` - Tooling (and example notebooks) for agile modeling on top of the
+Hoplite db layer, combining search and active learning approaches.
+This library includes organizing labeled data and training linear
+classifiers over embeddings, as well as tooling for embedding large datasets.
+* `zoo` - A bioacoustics model zoo. A basic wrapper class is provided, and
+any model which can transform windows of audio samples into embeddings
+can then be used in the agile modeling workflow.
+* `taxonomy` - A database of taxonomic information, especially for handling
+conversions between the various bird taxonomies.
+
+Each sub-library has its own documentation.
+
+# Installation
+
+The repository can be installed with either pip or poetry. Poetry allows more
+granular management of dependencies.
+
+First, install some basic dependencies. Note that for GPU support, you may
+install `tensorflow[and-cuda]` instead of `tensorflow-cpu`.
+
+```bash
+sudo apt-get update
+sudo apt-get install libsndfile1 ffmpeg
+pip install absl-py
+pip install requests
+pip install tensorflow-cpu
+```
+
+Then to install with pip:
+```bash
+pip install git+https://github.com/google-research/hoplite.git
+```
+
+Then run the tests and check that they pass:
+```bash
+python -m unittest discover -s hoplite/db/tests -p "*test.py"
+python -m unittest discover -s hoplite/taxonomy -p "*test.py"
+python -m unittest discover -s hoplite/zoo -p "*test.py"
+python -m unittest discover -s hoplite/agile/tests -p "*test.py"
+```
+
+Or, install with poetry:
+```bash
+# Install Poetry for package management
+curl -sSL https://install.python-poetry.org | python3 -
+
+# Install all dependencies specified in the poetry configs.
+poetry install
+```
+
+## Notes on Dependencies
+
 # Disclaimer
 
 This is not an officially supported Google product. This project is not
diff --git a/hoplite/agile/1_embed_audio_v2.ipynb b/hoplite/agile/1_embed_audio_v2.ipynb
index 2c5bcfa..e0addf3 100644
--- a/hoplite/agile/1_embed_audio_v2.ipynb
+++ b/hoplite/agile/1_embed_audio_v2.ipynb
@@ -11,6 +11,8 @@
         "import os\n",
         "from IPython.display import display\n",
         "import ipywidgets as widgets\n",
+        "import numpy as np\n",
+        "from etils import epath\n",
         "\n",
         "from hoplite.agile import colab_utils\n",
         "from hoplite.agile import embed\n",
@@ -105,8 +107,11 @@
         "\n",
         "print('Initialized DB located at ', configs.db_config.db_config.db_path)\n",
         "\n",
-        "def drop_and_reload_db(_) -\u003e interface.GraphSearchDBInterface:\n",
-        "  os.unlink(configs.db_config.db_config.db_path)\n",
+        "def drop_and_reload_db(_) -\u003e interface.HopliteDBInterface:\n",
+        "  db_path = epath.Path(configs.db_config.db_config.db_path)\n",
+        "  for fp in db_path.glob('hoplite.sqlite*'):\n",
+        "    fp.unlink()\n",
+        "  (db_path / 'usearch.index').unlink()\n",
         "  print('\\n Deleted previous db at: ', configs.db_config.db_config.db_path)\n",
         "  db = configs.db_config.load_db()\n",
         "\n",
@@ -172,8 +177,17 @@
       "source": [
         "q = db.get_embedding(444)\n",
         "%time results, scores = brutalism.brute_search(worker.db, query_embedding=q, search_list_size=128, score_fn=np.dot)\n",
-        "print([r.embedding_id for r in results])"
+        "print([int(r.embedding_id) for r in results])"
       ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "vHFlcn9PnSPJ"
+      },
+      "outputs": [],
+      "source": []
     }
   ],
   "metadata": {