cr

examples/demo_advanced.ipynb

@@ -4,11 +4,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Advanced RAG with LlamaParse\n",
+    "# Llama Parser <> LlamaIndex\n",
     "\n",
-    "<a href=\"https://colab.research.google.com/github/run-llama/llama_parse/blob/main/examples/demo_advanced.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>\n",
-    "\n",
-    "This notebook shows you how to use LlamaParse with our advanced markdown ingestion and recursive retrieval algorithms to model tables/text within a document hierarchically. This lets you ask questions over both tables and text.\n",
+    "This notebook is a complete walkthrough for using `LlamaParse` for RAG applications with `LlamaIndex`.\n",
     "\n",
     "Note for this example, we are using the `llama_index >=0.10.4` version"
    ]

examples/demo_basic.ipynb

@@ -182,8 +182,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.10"
-  }
+   "version": "3.10.12"
+  },
+  "orig_nbformat": 4
  },
  "nbformat": 4,
  "nbformat_minor": 4

llama_parse/base.py

@@ -110,53 +110,17 @@ class Language(str, Enum):
 
 SUPPORTED_FILE_TYPES = [
     ".pdf",
-    ".602",
-    ".abw",
-    ".cgm",
-    ".cwk",
+    ".xml"
     ".doc",
     ".docx",
-    ".docm",
-    ".dot",
-    ".dotm",
-    ".hwp",
-    ".key",
-    ".lwp",
-    ".mw",
-    ".mcw",
-    ".pages",
-    ".pbd",
-    ".ppt",
-    ".pptm",
     ".pptx",
-    ".pot",
-    ".potm",
-    ".potx",
     ".rtf",
-    ".sda",
-    ".sdd",
-    ".sdp",
-    ".sdw",
-    ".sgl",
-    ".sti",
-    ".sxi",
-    ".sxw",
-    ".stw",
-    ".sxg",
-    ".txt",
-    ".uof",
-    ".uop",
-    ".uot",
-    ".vor",
-    ".wpd", 
-    ".wps",
-    ".xml",
-    ".zabw",
-    ".epub",
-    ".htm",
-    ".html"
+    ".pages",
+    ".key",
+    ".epub"
 ]
 
+
 class LlamaParse(BasePydanticReader):
     """A smart-parser for files."""