diff --git a/models/llama-index-hack/llama2_github_repos.ipynb b/models/llama-index-hack/llama2_github_repos.ipynb
new file mode 100644
index 00000000..24a936c7
--- /dev/null
+++ b/models/llama-index-hack/llama2_github_repos.ipynb
@@ -0,0 +1,840 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from llama_hub.github_repo import GithubClient, GithubRepositoryReader\n",
+    "\n",
+    "from llama_index.llms import LlamaCPP\n",
+    "from llama_index.llms.llama_utils import messages_to_prompt, completion_to_prompt\n",
+    "from llama_index import VectorStoreIndex\n",
+    "from llama_index import LLMPredictor, PromptHelper, ServiceContext\n",
+    "\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nest_asyncio\n",
+    "nest_asyncio.apply()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "gh_auth=os.getenv(\"GITHUB_AUTH\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from ../../../llama-2-7b-chat.Q4_K_M.gguf (version GGUF V2 (latest))\n",
+      "llama_model_loader: - tensor    0:                token_embd.weight q4_K     [  4096, 32000,     1,     1 ]\n",
+      "llama_model_loader: - tensor    1:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor    2:            blk.0.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor    3:            blk.0.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor    4:              blk.0.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor    5:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor    6:              blk.0.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor    7:         blk.0.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor    8:              blk.0.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor    9:              blk.0.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   10:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   11:            blk.1.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   12:            blk.1.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   13:              blk.1.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   14:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   15:              blk.1.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   16:         blk.1.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   17:              blk.1.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   18:              blk.1.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   19:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   20:           blk.10.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   21:           blk.10.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   22:             blk.10.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   23:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   24:             blk.10.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   25:        blk.10.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   26:             blk.10.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   27:             blk.10.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   28:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   29:           blk.11.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   30:           blk.11.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   31:             blk.11.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   32:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   33:             blk.11.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   34:        blk.11.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   35:             blk.11.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   36:             blk.11.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   37:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   38:           blk.12.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   39:           blk.12.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   40:             blk.12.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   41:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   42:             blk.12.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   43:        blk.12.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   44:             blk.12.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   45:             blk.12.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   46:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   47:           blk.13.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   48:           blk.13.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   49:             blk.13.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   50:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   51:             blk.13.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   52:        blk.13.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   53:             blk.13.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   54:             blk.13.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   55:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   56:           blk.14.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   57:           blk.14.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   58:             blk.14.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   59:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   60:             blk.14.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   61:        blk.14.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   62:             blk.14.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   63:             blk.14.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   64:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   65:           blk.15.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   66:           blk.15.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   67:             blk.15.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   68:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   69:             blk.15.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   70:        blk.15.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   71:             blk.15.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   72:             blk.15.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   73:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   74:           blk.16.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   75:           blk.16.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   76:             blk.16.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   77:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   78:             blk.16.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   79:        blk.16.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   80:             blk.16.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   81:             blk.16.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   82:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   83:           blk.17.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   84:           blk.17.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   85:             blk.17.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   86:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   87:             blk.17.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   88:        blk.17.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   89:             blk.17.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   90:             blk.17.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   91:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   92:           blk.18.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   93:           blk.18.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   94:             blk.18.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   95:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   96:             blk.18.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   97:        blk.18.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   98:             blk.18.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   99:             blk.18.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  100:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  101:           blk.19.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  102:           blk.19.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  103:             blk.19.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  104:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  105:             blk.19.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  106:        blk.19.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  107:             blk.19.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  108:             blk.19.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  109:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  110:            blk.2.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  111:            blk.2.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  112:              blk.2.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  113:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  114:              blk.2.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  115:         blk.2.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  116:              blk.2.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  117:              blk.2.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  118:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  119:           blk.20.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  120:           blk.20.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  121:             blk.20.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  122:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  123:             blk.20.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  124:        blk.20.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  125:             blk.20.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  126:             blk.20.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  127:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  128:           blk.21.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  129:           blk.21.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  130:             blk.21.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  131:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  132:             blk.21.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  133:        blk.21.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  134:             blk.21.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  135:             blk.21.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  136:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  137:           blk.22.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  138:           blk.22.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  139:             blk.22.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  140:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  141:             blk.22.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  142:        blk.22.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  143:             blk.22.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  144:             blk.22.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  145:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  146:           blk.23.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  147:           blk.23.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  148:             blk.23.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  149:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  150:             blk.23.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  151:        blk.23.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  152:             blk.23.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  153:             blk.23.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  154:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  155:            blk.3.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  156:            blk.3.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  157:              blk.3.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  158:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  159:              blk.3.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  160:         blk.3.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  161:              blk.3.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  162:              blk.3.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  163:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  164:            blk.4.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  165:            blk.4.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  166:              blk.4.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  167:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  168:              blk.4.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  169:         blk.4.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  170:              blk.4.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  171:              blk.4.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  172:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  173:            blk.5.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  174:            blk.5.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  175:              blk.5.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  176:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  177:              blk.5.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  178:         blk.5.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  179:              blk.5.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  180:              blk.5.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  181:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  182:            blk.6.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  183:            blk.6.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  184:              blk.6.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  185:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  186:              blk.6.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  187:         blk.6.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  188:              blk.6.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  189:              blk.6.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  190:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  191:            blk.7.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  192:            blk.7.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  193:              blk.7.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  194:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  195:              blk.7.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  196:         blk.7.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  197:              blk.7.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  198:              blk.7.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  199:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  200:            blk.8.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  201:            blk.8.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  202:              blk.8.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  203:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  204:              blk.8.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  205:         blk.8.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  206:              blk.8.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  207:              blk.8.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  208:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  209:            blk.9.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  210:            blk.9.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  211:              blk.9.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  212:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  213:              blk.9.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  214:         blk.9.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  215:              blk.9.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  216:              blk.9.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  217:                    output.weight q6_K     [  4096, 32000,     1,     1 ]\n",
+      "llama_model_loader: - tensor  218:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  219:           blk.24.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  220:           blk.24.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  221:             blk.24.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  222:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  223:             blk.24.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  224:        blk.24.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  225:             blk.24.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  226:             blk.24.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  227:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  228:           blk.25.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  229:           blk.25.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  230:             blk.25.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  231:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  232:             blk.25.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  233:        blk.25.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  234:             blk.25.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  235:             blk.25.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  236:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  237:           blk.26.ffn_down.weight q4_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  238:           blk.26.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  239:             blk.26.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  240:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  241:             blk.26.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  242:        blk.26.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  243:             blk.26.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  244:             blk.26.attn_v.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  245:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  246:           blk.27.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  247:           blk.27.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  248:             blk.27.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  249:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  250:             blk.27.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  251:        blk.27.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  252:             blk.27.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  253:             blk.27.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  254:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  255:           blk.28.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  256:           blk.28.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  257:             blk.28.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  258:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  259:             blk.28.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  260:        blk.28.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  261:             blk.28.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  262:             blk.28.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  263:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  264:           blk.29.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  265:           blk.29.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  266:             blk.29.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  267:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  268:             blk.29.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  269:        blk.29.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  270:             blk.29.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  271:             blk.29.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  272:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  273:           blk.30.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  274:           blk.30.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  275:             blk.30.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  276:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  277:             blk.30.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  278:        blk.30.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  279:             blk.30.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  280:             blk.30.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  281:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  282:           blk.31.ffn_down.weight q6_K     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  283:           blk.31.ffn_gate.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  284:             blk.31.ffn_up.weight q4_K     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  285:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  286:             blk.31.attn_k.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  287:        blk.31.attn_output.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  288:             blk.31.attn_q.weight q4_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  289:             blk.31.attn_v.weight q6_K     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  290:               output_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - kv   0:                       general.architecture str     \n",
+      "llama_model_loader: - kv   1:                               general.name str     \n",
+      "llama_model_loader: - kv   2:                       llama.context_length u32     \n",
+      "llama_model_loader: - kv   3:                     llama.embedding_length u32     \n",
+      "llama_model_loader: - kv   4:                          llama.block_count u32     \n",
+      "llama_model_loader: - kv   5:                  llama.feed_forward_length u32     \n",
+      "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32     \n",
+      "llama_model_loader: - kv   7:                 llama.attention.head_count u32     \n",
+      "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32     \n",
+      "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32     \n",
+      "llama_model_loader: - kv  10:                          general.file_type u32     \n",
+      "llama_model_loader: - kv  11:                       tokenizer.ggml.model str     \n",
+      "llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr     \n",
+      "llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr     \n",
+      "llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr     \n",
+      "llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32     \n",
+      "llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32     \n",
+      "llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32     \n",
+      "llama_model_loader: - kv  18:               general.quantization_version u32     \n",
+      "llama_model_loader: - type  f32:   65 tensors\n",
+      "llama_model_loader: - type q4_K:  193 tensors\n",
+      "llama_model_loader: - type q6_K:   33 tensors\n",
+      "llm_load_print_meta: format         = GGUF V2 (latest)\n",
+      "llm_load_print_meta: arch           = llama\n",
+      "llm_load_print_meta: vocab type     = SPM\n",
+      "llm_load_print_meta: n_vocab        = 32000\n",
+      "llm_load_print_meta: n_merges       = 0\n",
+      "llm_load_print_meta: n_ctx_train    = 4096\n",
+      "llm_load_print_meta: n_ctx          = 3900\n",
+      "llm_load_print_meta: n_embd         = 4096\n",
+      "llm_load_print_meta: n_head         = 32\n",
+      "llm_load_print_meta: n_head_kv      = 32\n",
+      "llm_load_print_meta: n_layer        = 32\n",
+      "llm_load_print_meta: n_rot          = 128\n",
+      "llm_load_print_meta: n_gqa          = 1\n",
+      "llm_load_print_meta: f_norm_eps     = 1.0e-05\n",
+      "llm_load_print_meta: f_norm_rms_eps = 1.0e-06\n",
+      "llm_load_print_meta: n_ff           = 11008\n",
+      "llm_load_print_meta: freq_base      = 10000.0\n",
+      "llm_load_print_meta: freq_scale     = 1\n",
+      "llm_load_print_meta: model type     = 7B\n",
+      "llm_load_print_meta: model ftype    = mostly Q4_K - Medium\n",
+      "llm_load_print_meta: model size     = 6.74 B\n",
+      "llm_load_print_meta: general.name   = LLaMA v2\n",
+      "llm_load_print_meta: BOS token = 1 '<s>'\n",
+      "llm_load_print_meta: EOS token = 2 '</s>'\n",
+      "llm_load_print_meta: UNK token = 0 '<unk>'\n",
+      "llm_load_print_meta: LF token  = 13 '<0x0A>'\n",
+      "llm_load_tensors: ggml ctx size =    0.09 MB\n",
+      "llm_load_tensors: mem required  = 3891.34 MB (+ 1950.00 MB per state)\n",
+      "..................................................................................................\n",
+      "llama_new_context_with_model: kv self size  = 1950.00 MB\n",
+      "llama_new_context_with_model: compute buffer total size =  269.22 MB\n",
+      "AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | \n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = LlamaCPP(\n",
+    "    model_path=\"../../../llama-2-7b-chat.Q4_K_M.gguf\",\n",
+    "    temperature=0.1,\n",
+    "    max_new_tokens=256,\n",
+    "    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room\n",
+    "    context_window=3900,\n",
+    "    # kwargs to pass to __call__()\n",
+    "    generate_kwargs={},\n",
+    "    # kwargs to pass to __init__()\n",
+    "    # set to at least 1 to use GPU\n",
+    "    model_kwargs={\"n_gpu_layers\": 1},\n",
+    "    # transform inputs into Llama2 format\n",
+    "    messages_to_prompt=messages_to_prompt,\n",
+    "    completion_to_prompt=completion_to_prompt,\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_Hut23():\n",
+    "    loader = GithubRepositoryReader(\n",
+    "        GithubClient(gh_auth),\n",
+    "        owner=\"alan-turing-institute\",\n",
+    "        repo=\"Hut23\",\n",
+    "        verbose=False,\n",
+    "        filter_file_extensions=([\".md\",\".ipynb\"], GithubRepositoryReader.FilterType.INCLUDE),\n",
+    "        filter_directories=([\"JDs\",\"development\",\"newsletters\",\"objectives\",\"rfc\"], GithubRepositoryReader.FilterType.INCLUDE),\n",
+    "        )\n",
+    "    documents = loader.load_data(branch=\"master\")\n",
+    "    return documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_REG_handbook():\n",
+    "    loader = GithubRepositoryReader(\n",
+    "        GithubClient(gh_auth),\n",
+    "        owner=\"alan-turing-institute\",\n",
+    "        repo=\"REG-handbook\",\n",
+    "        verbose=False,\n",
+    "        filter_file_extensions=([\".md\"], GithubRepositoryReader.FilterType.INCLUDE),\n",
+    "        filter_directories=([\"content\"], GithubRepositoryReader.FilterType.INCLUDE),\n",
+    "        )\n",
+    "    documents = loader.load_data(branch=\"main\")\n",
+    "    return documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_rse_course():\n",
+    "    loader = GithubRepositoryReader(\n",
+    "        GithubClient(gh_auth),\n",
+    "        owner=\"alan-turing-institute\",\n",
+    "        repo=\"rse-course\",\n",
+    "        verbose=False,\n",
+    "        filter_file_extensions=([\".md\",\".ipynb\"], GithubRepositoryReader.FilterType.INCLUDE),\n",
+    "        )\n",
+    "    documents = loader.load_data(branch=\"main\")\n",
+    "    return documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_rds_course():\n",
+    "    loader = GithubRepositoryReader(\n",
+    "        GithubClient(gh_auth),\n",
+    "        owner=\"alan-turing-institute\",\n",
+    "        repo=\"rds-course\",\n",
+    "        verbose=False,\n",
+    "        filter_file_extensions=([\".md\",\".ipynb\"], GithubRepositoryReader.FilterType.INCLUDE),\n",
+    "        )\n",
+    "    documents = loader.load_data(branch=\"develop\")\n",
+    "    return documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_rds_course():\n",
+    "    loader = GithubRepositoryReader(\n",
+    "        GithubClient(gh_auth),\n",
+    "        owner=\"alan-turing-institute\",\n",
+    "        repo=\"rds-course\",\n",
+    "        verbose=False,\n",
+    "        filter_file_extensions=([\".md\",\".ipynb\"], GithubRepositoryReader.FilterType.INCLUDE),\n",
+    "        )\n",
+    "    documents = loader.load_data(branch=\"develop\")\n",
+    "    return documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# could also add:\n",
+    "# - https://github.com/alan-turing-institute/TuringDataStories\n",
+    "# - https://github.com/alan-turing-institute/DataScienceSkills/tree/master"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def load_turing_way():\n",
+    "    loader = GithubRepositoryReader(\n",
+    "        GithubClient(gh_auth),\n",
+    "        owner=\"the-turing-way\",\n",
+    "        repo=\"the-turing-way\",\n",
+    "        verbose=False,\n",
+    "        filter_file_extensions=([\".md\"], GithubRepositoryReader.FilterType.INCLUDE),\n",
+    "        )\n",
+    "    documents = loader.load_data(branch=\"main\")\n",
+    "    return documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "documents = []\n",
+    "documents.extend(load_Hut23())\n",
+    "documents.extend(load_REG_handbook())\n",
+    "documents.extend(load_rse_course())\n",
+    "documents.extend(load_rds_course())\n",
+    "documents.extend(load_turing_way())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "877"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(documents)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_docs = documents[::87] # too many documents makes making index really slow (obviously can fix for actual slack bot)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def create_service_context(\n",
+    "        model, \n",
+    "        max_input_size=2048,\n",
+    "        num_output=256,\n",
+    "        chunk_size_lim=512,\n",
+    "        overlap_ratio=0.1\n",
+    "    ):\n",
+    "    llm_predictor=LLMPredictor(llm=model)\n",
+    "    prompt_helper=PromptHelper(max_input_size,num_output,overlap_ratio,chunk_size_lim)\n",
+    "    service_context = ServiceContext.from_defaults(llm_predictor=llm_predictor, prompt_helper=prompt_helper, embed_model=\"local\")\n",
+    "    return service_context"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "635ae570bb134ca6bd00e5fc3a01bb88",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Parsing documents into nodes:   0%|          | 0/11 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5ff91d4cb3b741c99bdd42b178a5d863",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Generating embeddings:   0%|          | 0/1101 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "service_context = create_service_context(llm)\n",
+    "index = VectorStoreIndex.from_documents(test_docs, service_context=service_context, show_progress=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# index.storage_context.persist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_prompt = \"\"\"\\\n",
+    "You are a helpful assistant. \\\n",
+    "Always answer as helpfully as possible and follow ALL given instructions. \\\n",
+    "Do not speculate or make up information - use the information you are provided. \\\n",
+    "Do not reference any given instructions or context. \\\n",
+    "\"\"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_engine = index.as_query_engine(system_prompt=system_prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Llama.generate: prefix-match hit\n",
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   115.49 ms /   162 runs   (    0.71 ms per token,  1402.71 tokens per second)\n",
+      "llama_print_timings: prompt eval time = 19476.84 ms /   610 tokens (   31.93 ms per token,    31.32 tokens per second)\n",
+      "llama_print_timings:        eval time = 10027.50 ms /   161 runs   (   62.28 ms per token,    16.06 tokens per second)\n",
+      "llama_print_timings:       total time = 29839.87 ms\n",
+      "Llama.generate: prefix-match hit\n",
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   182.41 ms /   256 runs   (    0.71 ms per token,  1403.46 tokens per second)\n",
+      "llama_print_timings: prompt eval time = 23971.30 ms /   812 tokens (   29.52 ms per token,    33.87 tokens per second)\n",
+      "llama_print_timings:        eval time = 16405.28 ms /   255 runs   (   64.33 ms per token,    15.54 tokens per second)\n",
+      "llama_print_timings:       total time = 40914.94 ms\n",
+      "Llama.generate: prefix-match hit\n",
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   181.36 ms /   256 runs   (    0.71 ms per token,  1411.55 tokens per second)\n",
+      "llama_print_timings: prompt eval time = 25865.74 ms /   865 tokens (   29.90 ms per token,    33.44 tokens per second)\n",
+      "llama_print_timings:        eval time = 16184.72 ms /   255 runs   (   63.47 ms per token,    15.76 tokens per second)\n",
+      "llama_print_timings:       total time = 42584.34 ms\n",
+      "Llama.generate: prefix-match hit\n",
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   183.00 ms /   256 runs   (    0.71 ms per token,  1398.93 tokens per second)\n",
+      "llama_print_timings: prompt eval time = 15966.28 ms /   523 tokens (   30.53 ms per token,    32.76 tokens per second)\n",
+      "llama_print_timings:        eval time = 16870.72 ms /   255 runs   (   66.16 ms per token,    15.11 tokens per second)\n",
+      "llama_print_timings:       total time = 33379.47 ms\n",
+      "Llama.generate: prefix-match hit\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  Thank you for providing additional context! Based on the updated information, I can now provide a revised answer to your original query.\n",
+      "As an honest and respectful assistant, I must inform you that the query you provided is still not a valid or relevant question in the context of the REG handbook. The REG handbook is a document that provides information and guidelines for researchers at the Alan Turing Institute, and it does not contain any sections or areas where contributions are solicited or accepted.\n",
+      "However, I understand that you may be interested in contributing to the REG community in some way. In that case, there are several ways you can get involved:\n",
+      "1. Participate in Tech Talks: The REG handbook mentions \"Tech Talks\" (Tuesdays 12:30pm) as a way for researchers to share their knowledge and expertise with others. You can sign up to give a talk or simply attend and learn from others.\n",
+      "2. Join the Society of Research Software Engineering: The REG handbook recommends joining the Society of Research Software Engineering (RSE), including its Slack workspace. This is a great way to connect with other researchers\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   182.57 ms /   256 runs   (    0.71 ms per token,  1402.17 tokens per second)\n",
+      "llama_print_timings: prompt eval time =  4969.07 ms /    72 tokens (   69.01 ms per token,    14.49 tokens per second)\n",
+      "llama_print_timings:        eval time = 14999.77 ms /   255 runs   (   58.82 ms per token,    17.00 tokens per second)\n",
+      "llama_print_timings:       total time = 20514.78 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"How can I contribute to the REG handbook?\")\n",
+    "print(response.response)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Llama.generate: prefix-match hit\n",
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =    77.61 ms /   109 runs   (    0.71 ms per token,  1404.42 tokens per second)\n",
+      "llama_print_timings: prompt eval time = 18501.31 ms /   563 tokens (   32.86 ms per token,    30.43 tokens per second)\n",
+      "llama_print_timings:        eval time =  6730.49 ms /   108 runs   (   62.32 ms per token,    16.05 tokens per second)\n",
+      "llama_print_timings:       total time = 25459.36 ms\n",
+      "Llama.generate: prefix-match hit\n",
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   181.92 ms /   256 runs   (    0.71 ms per token,  1407.22 tokens per second)\n",
+      "llama_print_timings: prompt eval time = 20821.02 ms /   679 tokens (   30.66 ms per token,    32.61 tokens per second)\n",
+      "llama_print_timings:        eval time = 16030.69 ms /   255 runs   (   62.87 ms per token,    15.91 tokens per second)\n",
+      "llama_print_timings:       total time = 37397.61 ms\n",
+      "Llama.generate: prefix-match hit\n",
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   181.33 ms /   256 runs   (    0.71 ms per token,  1411.78 tokens per second)\n",
+      "llama_print_timings: prompt eval time = 22551.23 ms /   766 tokens (   29.44 ms per token,    33.97 tokens per second)\n",
+      "llama_print_timings:        eval time = 16028.97 ms /   255 runs   (   62.86 ms per token,    15.91 tokens per second)\n",
+      "llama_print_timings:       total time = 39119.85 ms\n",
+      "Llama.generate: prefix-match hit\n",
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   180.98 ms /   256 runs   (    0.71 ms per token,  1414.50 tokens per second)\n",
+      "llama_print_timings: prompt eval time = 12869.07 ms /   467 tokens (   27.56 ms per token,    36.29 tokens per second)\n",
+      "llama_print_timings:        eval time = 15807.03 ms /   255 runs   (   61.99 ms per token,    16.13 tokens per second)\n",
+      "llama_print_timings:       total time = 29213.77 ms\n",
+      "Llama.generate: prefix-match hit\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  Thank you for providing additional context! Based on the information provided, a lay summary is a brief explanation of a complex topic or document, written in simple language that can be easily understood by a non-expert audience. It is often used to summarize scientific research papers, technical reports, or other documents that contain specialized knowledge or jargon that may be difficult for non-experts to understand. The purpose of a lay summary is to provide a clear and concise overview of the main points and key findings of the original document, making it accessible to a wider audience.\n",
+      "In light of the new context provided, here are some additional details that could be included in a lay summary:\n",
+      "* A brief description of the purpose of the document, such as why it was created and what it covers\n",
+      "* An overview of the main points and key findings of the document, including any notable trends or insights\n",
+      "* Any relevant examples or case studies that help to illustrate the points being made in the document\n",
+      "* A summary of any recommendations or actions that the reader should take as a result of reading the document\n",
+      "* Any additional information that could be helpful for non-experts to know, such as definitions of key terms\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time = 19297.75 ms\n",
+      "llama_print_timings:      sample time =   181.83 ms /   256 runs   (    0.71 ms per token,  1407.89 tokens per second)\n",
+      "llama_print_timings: prompt eval time =  5578.25 ms /   122 tokens (   45.72 ms per token,    21.87 tokens per second)\n",
+      "llama_print_timings:        eval time = 14821.13 ms /   255 runs   (   58.12 ms per token,    17.21 tokens per second)\n",
+      "llama_print_timings:       total time = 20941.35 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "response = query_engine.query(\"What is a lay summary?\")\n",
+    "print(response.response)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "reginald-slack-ZVq5BSHv-py3.11",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/poetry.lock b/poetry.lock
index bee4578e..fb28e53f 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -2030,13 +2030,13 @@ retrying = "*"
 
 [[package]]
 name = "llama-index"
-version = "0.8.24.post1"
+version = "0.8.24"
 description = "Interface between LLMs and your data"
 optional = false
 python-versions = "*"
 files = [
-    {file = "llama_index-0.8.24.post1-py3-none-any.whl", hash = "sha256:4b7645a445d394640bad8c66a67483df29f7f0af25c53360cb382075be0c6c34"},
-    {file = "llama_index-0.8.24.post1.tar.gz", hash = "sha256:7cd47cf6ba64d24dbc6db712bcd4834767e0d35890559feee139bd4fa90ad916"},
+    {file = "llama_index-0.8.24-py3-none-any.whl", hash = "sha256:c7bcf11ced7cd7a1a30d2f7d75b96c6b36dd815892e12e1a0642d7d20b76846e"},
+    {file = "llama_index-0.8.24.tar.gz", hash = "sha256:6a70dd010377be8170389721b0c5521e767f41fd676cf35d16214d80e532ec00"},
 ]
 
 [package.dependencies]