Ensure image extensions, vbump (#159)

examples/demo_advanced.ipynb

@@ -19,12 +19,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index\n",
-    "!pip install llama-index-core\n",
-    "!pip install llama-index-embeddings-openai\n",
-    "!pip install llama-index-postprocessor-flag-embedding-reranker\n",
-    "!pip install git+https://github.com/FlagOpen/FlagEmbedding.git\n",
-    "!pip install llama-parse"
+    "%pip install llama-index\n",
+    "%pip install llama-index-core\n",
+    "%pip install llama-index-embeddings-openai\n",
+    "%pip install llama-index-postprocessor-flag-embedding-reranker\n",
+    "%pip install git+https://github.com/FlagOpen/FlagEmbedding.git\n",
+    "%pip install llama-parse"
    ]
   },
   {

examples/demo_advanced_astradb.ipynb

@@ -17,13 +17,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index\n",
-    "!pip install llama-index-core==0.10.6.post1\n",
-    "!pip install llama-index-embeddings-openai\n",
-    "!pip install llama-index-postprocessor-flag-embedding-reranker\n",
-    "!pip install git+https://github.com/FlagOpen/FlagEmbedding.git\n",
-    "!pip install llama-parse\n",
-    "!pip install llama-index-vector-stores-astra-db"
+    "%pip install llama-index\n",
+    "%pip install llama-index-core==0.10.6.post1\n",
+    "%pip install llama-index-embeddings-openai\n",
+    "%pip install llama-index-postprocessor-flag-embedding-reranker\n",
+    "%pip install git+https://github.com/FlagOpen/FlagEmbedding.git\n",
+    "%pip install llama-parse\n",
+    "%pip install llama-index-vector-stores-astra-db"
    ]
   },
   {

examples/demo_astradb.ipynb

@@ -28,7 +28,7 @@
    "outputs": [],
    "source": [
     "# First, install the required dependencies\n",
-    "!pip install --quiet llama-index llama-parse llama-index-vector-stores-astra-db llama-index-llms-openai"
+    "%pip install --quiet llama-index llama-parse llama-index-vector-stores-astra-db llama-index-llms-openai"
    ]
   },
   {

examples/demo_basic.ipynb

@@ -13,7 +13,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index llama-parse"
+    "%pip install llama-index llama-parse"
    ]
   },
   {

examples/demo_insurance.ipynb

@@ -24,7 +24,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index llama-parse"
+    "%pip install llama-index llama-parse"
    ]
   },
   {

examples/demo_json.ipynb

@@ -206,7 +206,7 @@
     "    for image_dict in image_dicts:\n",
     "        image_doc = ImageDocument(image_path=image_dict[\"path\"])\n",
     "        response = anthropic_mm_llm.complete(\n",
-    "            prompt=\"Describe the images as an alternative text\",\n",
+    "            prompt=\"Describe the images as alt text\",\n",
     "            image_documents=[image_doc],\n",
     "        )\n",
     "        text_node = TextNode(text=str(response), metadata={\"path\": image_dict[\"path\"]})\n",

examples/demo_json_parsing.ipynb

@@ -33,11 +33,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index\n",
-    "!pip install llama-index-core\n",
-    "!pip install llama-index-llms-anthropic llama-index-multi-modal-llms-anthropic\n",
-    "!pip install llama-index-embeddings-huggingface\n",
-    "!pip install llama-parse"
+    "%pip install llama-index\n",
+    "%pip install llama-index-core\n",
+    "%pip install llama-index-llms-anthropic llama-index-multi-modal-llms-anthropic\n",
+    "%pip install llama-index-embeddings-huggingface\n",
+    "%pip install llama-parse"
    ]
   },
   {

examples/demo_languages.ipynb

@@ -21,7 +21,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index llama-parse"
+    "%pip install llama-index llama-parse"
    ]
   },
   {

examples/demo_mongodb.ipynb

@@ -29,7 +29,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index llama-parse pip install llama-index-vector-stores-mongodb llama-index-llms-openai"
+    "%pip install llama-index llama-parse\n",
+    "%pip install llama-index-vector-stores-mongodb llama-index-llms-openai"
    ]
   },
   {

examples/demo_parsing_instructions.ipynb

@@ -114,7 +114,7 @@
     }
    ],
    "source": [
-    "!pip install llama-parse"
+    "%pip install llama-parse"
    ]
   },
   {
@@ -294,7 +294,7 @@
     "### Using parsing instructions\n",
     "Let's try to parse the manga with custom instructions:\n",
     "\n",
-    "\"The provided document is a manga comic book. Most pages do NOT have title. It does not contain tables. Try to reconstruct the dialogue happening in a cohesive way.\"\n",
+    "\"The provided document is a manga comic book. Most pages do NOT have a title. It does not contain tables. Try to reconstruct the dialogue spoken in a cohesive way.\"\n",
     "\n",
     "To do so just pass the parsing instruction as a parameter to LlamaParse:"
    ]
@@ -314,9 +314,9 @@
     }
    ],
    "source": [
-    "parsingInstructionManga = \"\"\"The provided document is a manga comic book, most page do NOT have title.\n",
-    "It does not contain table.\n",
-    "Try to reconstruct the dialog happening in a cohesive way.\"\"\"\n",
+    "parsingInstructionManga = \"\"\"The provided document is a manga comic book. Most pages do NOT have a title.\n",
+    "It does not contain tables.\n",
+    "Try to reconstruct the dialogue spoken in a cohesive way.\"\"\"\n",
     "withInstructionParsing = LlamaParse(\n",
     "    result_type=\"markdown\", parsing_instruction=parsingInstructionManga\n",
     ").load_data(\"./manga.pdf\")"
@@ -404,9 +404,9 @@
     }
    ],
    "source": [
-    "parsingInstructionMangaLatex = \"\"\"The provided document is a manga comic book, most page do NOT have title.\n",
-    "It does not contain table. Do not output table.\n",
-    "Try to reconstruct the dialog happening in a cohesive way.\n",
+    "parsingInstructionMangaLatex = \"\"\"The provided document is a manga comic book. Most pages do NOT have a title.\n",
+    "It does not contain tables.\n",
+    "Try to reconstruct the dialogue spoken in a cohesive way.\n",
     "Output any math equation in LATEX markdown (between $$)\"\"\"\n",
     "withLatex = LlamaParse(\n",
     "    result_type=\"markdown\", parsing_instruction=parsingInstructionMangaLatex\n",

examples/demo_table_comparisons.ipynb

@@ -28,13 +28,13 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index\n",
-    "!pip install llama-index-core\n",
-    "!pip install llama-index-embeddings-openai\n",
-    "!pip install llama-index-question-gen-openai\n",
-    "!pip install llama-index-postprocessor-flag-embedding-reranker\n",
-    "!pip install git+https://github.com/FlagOpen/FlagEmbedding.git\n",
-    "!pip install llama-parse"
+    "%pip install llama-index\n",
+    "%pip install llama-index-core\n",
+    "%pip install llama-index-embeddings-openai\n",
+    "%pip install llama-index-question-gen-openai\n",
+    "%pip install llama-index-postprocessor-flag-embedding-reranker\n",
+    "%pip install git+https://github.com/FlagOpen/FlagEmbedding.git\n",
+    "%pip install llama-parse"
    ]
   },
   {

examples/other_files/demo_ppt_financial.ipynb

@@ -26,9 +26,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install llama-index\n",
-    "!pip install llama-parse\n",
-    "!pip install torch transformers python-pptx Pillow"
+    "%pip install llama-index\n",
+    "%pip install llama-parse\n",
+    "%pip install torch transformers python-pptx Pillow"
    ]
   },
   {

llama_parse/base.py

@@ -309,6 +309,11 @@ class LlamaParse(BasePydanticReader):
     def get_images(self, json_result: List[dict], download_path: str) -> List[dict]:
         """Download images from the parsed result."""
         headers = {"Authorization": f"Bearer {self.api_key}"}
+
+        # make the download path
+        if not os.path.exists(download_path):
+            os.makedirs(download_path)
+
         try:
             images = []
             for result in json_result:
@@ -318,9 +323,16 @@ class LlamaParse(BasePydanticReader):
                         print(f"> Image for page {page['page']}: {page['images']}")
                     for image in page["images"]:
                         image_name = image["name"]
+
+                        # get the full path
                         image_path = os.path.join(
                             download_path, f"{job_id}-{image_name}"
                         )
+
+                        # get a valid image path
+                        if not image_path.endswith(".png"):
+                            image_path += ".png"
+
                         image["path"] = image_path
                         image["job_id"] = job_id
                         image["original_pdf_path"] = result["file_path"]

llama_parse/utils.py

@@ -146,4 +146,7 @@ SUPPORTED_FILE_TYPES = [
     ".sti",
     # ebook
     ".epub",
+    # html
+    ".html",
+    ".htm",
 ]

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.4.1"
+version = "0.4.2"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"