minor cleanup

Author: jph00

00_xml.ipynb

@@ -21,7 +21,9 @@
   {
    "cell_type": "markdown",
    "id": "ff6f6471-8061-4fdd-85a1-25fdc27c5cf3",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Setup"
    ]
@@ -30,7 +32,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "033c76fd",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| export\n",
@@ -50,7 +54,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "2795f9fc",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| exports\n",
@@ -73,7 +79,9 @@
   {
    "cell_type": "markdown",
    "id": "140a35a2",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "JSON doesn't map as nicely to XML as the data structure used in `fastcore.xml`, but for simple XML trees it can be convenient -- for example:"
    ]
@@ -82,7 +90,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "005a5be4",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -119,15 +129,19 @@
   {
    "cell_type": "markdown",
    "id": "7788c48c",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "## Including documents"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "479be4c9",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "According [to Anthropic](https://docs.anthropic.com/claude/docs/long-context-window-tips), \"*it's essential to structure your prompts in a way that clearly separates the input data from the instructions*\". They recommend using the following format:\n",
     "\n",
@@ -153,7 +167,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "a01dc320",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| exports\n",
@@ -163,7 +179,9 @@
   {
    "cell_type": "markdown",
    "id": "6620a123",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "We'll use `doctype` to store our pairs."
    ]
@@ -172,7 +190,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "ce853491",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| exports\n",
@@ -186,7 +206,9 @@
   {
    "cell_type": "markdown",
    "id": "026d3b06",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "Since Anthropic's example shows newlines before and after each tag, we'll do the same."
    ]
@@ -195,7 +217,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "932e8858",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| exports\n",
@@ -210,7 +234,9 @@
   {
    "cell_type": "markdown",
    "id": "8800921b",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "This is a convenience wrapper to ensure that a `doctype` has the needed information in the right format."
    ]
@@ -219,7 +245,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "14f9e185",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -241,7 +269,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "d8913bd3",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "from fastcore.xml import xt"
@@ -251,7 +281,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "3b8e6f87",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| exports\n",
@@ -270,7 +302,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "15e454db",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| exports\n",
@@ -288,7 +322,9 @@
   {
    "cell_type": "markdown",
    "id": "a8b6ac26",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "We can now generate XML for one document in the suggested format:"
    ]
@@ -297,7 +333,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "5782369d",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "dt = mk_doctype(doc)"
@@ -307,7 +345,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "e7ed5a9a",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -333,7 +373,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "ba5ebfab",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| exports\n",
@@ -351,7 +393,9 @@
   {
    "cell_type": "markdown",
    "id": "85004124",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "Putting it all together, we have our final XML format:"
    ]
@@ -360,7 +404,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "1dac60f6",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -415,15 +461,19 @@
   {
    "cell_type": "markdown",
    "id": "65317fc6",
-   "metadata": {},
+   "metadata": {
+    "heading_collapsed": true
+   },
    "source": [
     "### File list to context"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "3778e8ed",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "source": [
     "For generating XML context from files, we'll just read them as text and use the file names as `source`."
    ]
@@ -432,7 +482,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "0a168636",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [],
    "source": [
     "#| exports\n",
@@ -449,7 +501,9 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "1bf73d36",
-   "metadata": {},
+   "metadata": {
+    "hidden": true
+   },
    "outputs": [
     {
      "data": {
@@ -565,10 +619,9 @@
     "@delegates(folder2ctx)\n",
     "def folder2ctx_cli(\n",
     "    folder:str, # Folder name containing files to add to context\n",
-    "    prefix:bool=True, # Include Anthropic's suggested prose intro?\n",
     "    **kwargs # Passed to `folder2ctx`\n",
     ")->str: # XML for Claude context\n",
-    "    return folder2ctx(folder, prefix, **kwargs)"
+    "    return folder2ctx(folder, **kwargs)"
    ]
   },
   {
@@ -596,7 +649,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 28,
    "id": "1e9ee5c1",
    "metadata": {},
    "outputs": [],
@@ -618,9 +671,21 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "python3",
+   "display_name": "Python 3 (ipykernel)",
    "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": "3.11.8"
   }
  },
  "nbformat": 4,

toolslm/xml.py

@@ -106,7 +106,6 @@ def folder2ctx(
 @delegates(folder2ctx)
 def folder2ctx_cli(
     folder:str, # Folder name containing files to add to context
-    prefix:bool=True, # Include Anthropic's suggested prose intro?
     **kwargs # Passed to `folder2ctx`
 )->str: # XML for Claude context
-    return folder2ctx(folder, prefix, **kwargs)
+    return folder2ctx(folder, **kwargs)