add comment

* Update issue templates

* Update issue templates

.github/ISSUE_TEMPLATE/bug_report.md

@@ -7,8 +7,6 @@ assignees: ''
 
 ---
 
-_Note: we're aware of some missing content in the output and layout issues on tables. Please refrain from opening new issues on this topic unless if you think it's different from what has already been reported._
-
 **Describe the bug**
 Write a concise description of what the bug is.
 
@@ -19,19 +17,15 @@ If possible, please provide the PDF file causing the issue.
 If you have it, please provide the ID of the job you ran.
 You can find it here: https://cloud.llamaindex.ai/parse in the "History" tab.
 
-**Screenshots**
-Feel free to also provide screenshots if relevant.
-
 **Client:**
 Please remove untested options:
- - Frontend (cloud.llamaindex.ai)
  - Python Library
+ - API
+ - Frontend (cloud.llamaindex.ai)
  - Typescript Library
  - Notebook
- - API
-
-**Options**
-What options did you use? Multimodal, fast mode, parsing instructions, etc.
 
 **Additional context**
 Add any additional context about the problem here.
+What options did you use? Premium mode, multimodal, fast mode, parsing instructions, etc.
+Screenshots, code snippets, etc.

README.md

@@ -38,7 +38,22 @@ Lastly, install the package:
 
 `pip install llama-parse`
 
-Now you can run the following to parse your first PDF file:
+Now you can parse your first PDF file using the command line interface. Use the command `llama-parse [file_paths]`. See the help text with `llama-parse --help`.
+
+```bash
+export LLAMA_CLOUD_API_KEY='llx-...'
+
+# output as text
+llama-parse my_file.pdf --result-type text --output-file output.txt
+
+# output as markdown
+llama-parse my_file.pdf --result-type markdown --output-file output.md
+
+# output as raw json
+llama-parse my_file.pdf --output-raw-json --output-file output.json
+```
+
+You can also create simple scripts:
 
 ```python
 import nest_asyncio

examples/demo_json.ipynb

@@ -342,7 +342,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "llama-parse-aNC435Vv-py3.10",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },

examples/test_tesla_impact_report/test_gpt4o.ipynb

@@ -46,7 +46,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<LLAMA_CLOUD_API_KEY>"
+    "os.environ[\"LLAMA_CLOUD_API_KEY\"] = \"<LLAMA_CLOUD_API_KEY>\""
    ]
   },
   {

llama_parse/base.py

@@ -34,9 +34,103 @@ FileInput = Union[str, bytes, BufferedIOBase]
 _DEFAULT_SEPARATOR = "\n---\n"
 
 
-class LlamaParse(BasePydanticReader):
+class LlamaParseParams(BasePydanticReader):
+    """This class contain only the parameter that are used by the LlamaParse API"""
+
+    bounding_box: Optional[str] = Field(
+        default=None,
+        description="The bounding box to use to extract text from documents describe as a string containing the bounding box margins",
+    )
+
+    continuous_mode: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will to merge together following tables",
+    )
+    do_not_cache: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the document will not be cached. This mean that you will be re-charged it you reprocess them as they will not be cached.",
+    )
+    do_not_unroll_columns: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most case.",
+    )
+    fast_mode: Optional[bool] = Field(
+        default=False,
+        description="Note: Non compatible with other modes. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction.",
+    )
+    gpt4o_api_key: Optional[str] = Field(
+        default=None,
+        description="(deprecated use vendor_multimodal_model_name='gpt-4o' instead). The API key for the GPT-4o API. Lowers the cost of parsing.",
+    )
+    gpt4o_mode: bool = Field(
+        default=False,
+        description="(deprecated use vendor_multimodal_api_key='gpt-4o' instead). Whether to use gpt-4o extract text from documents.",
+    )
+    guess_xlsx_sheet_name: Optional[str] = Field(
+        default=False,
+        description="Experimental: If set to true, when outputting to xlsx, the parser will try to guess the sheet name based on the context of the table.",
+    )
+    ignore_errors: bool = Field(
+        default=True,
+        description="Whether or not to ignore and skip errors raised during parsing.",
+    )
+    invalidate_cache: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the cache will be ignored and the document re-processes. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice.",
+    )
+    language: Language = Field(
+        default=Language.ENGLISH, description="The language of the text to parse."
+    )
+    page_prefix: Optional[str] = Field(
+        default=None,
+        description="A templated prefix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
+    )
+    page_separator: Optional[str] = Field(
+        default=None,
+        description="A templated  page separator to use to split the text.  If it contain `{page_number}`,it will be replaced by the next page number. If not set will the default separator '\\n---\\n' will be used.",
+    )
+    page_suffix: Optional[str] = Field(
+        default=None,
+        description="A templated suffix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
+    )
+    parsing_instruction: Optional[str] = Field(
+        default="", description="The parsing instruction for the parser."
+    )
+    skip_diagonal_text: Optional[bool] = Field(
+        default=False,
+        description="If set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).",
+    )
+    split_by_page: bool = Field(
+        default=True,
+        description="Whether to split by page using the page separator",
+    )
+    take_screenshot: bool = Field(
+        default=False,
+        description="Whether to take screenshot of each page of the document.",
+    )
+    target_pages: Optional[str] = Field(
+        default=None,
+        description="The target pages to extract text from documents. Describe as a comma separated list of page numbers. The first page of the document is page 0",
+    )
+    use_vendor_multimodal_model: bool = Field(
+        default=False,
+        description="Whether to use the vendor multimodal API.",
+    )
+    vendor_multimodal_api_key: Optional[str] = Field(
+        default=None,
+        description="The API key for the multimodal API.",
+    )
+
+    vendor_multimodal_model_name: Optional[str] = Field(
+        default=None,
+        description="The model name for the vendor multimodal API.",
+    )
+
+
+class LlamaParse(LlamaParseParams):
     """A smart-parser for files."""
 
+    """Package parameters"""
     api_key: str = Field(
         default="",
         description="The API key for the LlamaParse API.",
@@ -46,8 +140,12 @@ class LlamaParse(BasePydanticReader):
         default=DEFAULT_BASE_URL,
         description="The base URL of the Llama Parsing API.",
     )
-    result_type: ResultType = Field(
-        default=ResultType.TXT, description="The result type for the parser."
+    check_interval: int = Field(
+        default=1,
+        description="The interval in seconds to check if the parsing is done.",
+    )
+    custom_client: Optional[httpx.AsyncClient] = Field(
+        default=None, description="A custom HTTPX client to use for sending requests."
     )
     num_workers: int = Field(
         default=4,
@@ -55,104 +153,18 @@ class LlamaParse(BasePydanticReader):
         lt=10,
         description="The number of workers to use sending API requests for parsing.",
     )
-    check_interval: int = Field(
-        default=1,
-        description="The interval in seconds to check if the parsing is done.",
-    )
     max_timeout: int = Field(
         default=2000,
         description="The maximum timeout in seconds to wait for the parsing to finish.",
     )
-    verbose: bool = Field(
-        default=True, description="Whether to print the progress of the parsing."
+    result_type: ResultType = Field(
+        default=ResultType.TXT, description="The result type for the parser."
     )
     show_progress: bool = Field(
         default=True, description="Show progress when parsing multiple files."
     )
-    language: Language = Field(
-        default=Language.ENGLISH, description="The language of the text to parse."
-    )
-    parsing_instruction: Optional[str] = Field(
-        default="", description="The parsing instruction for the parser."
-    )
-    skip_diagonal_text: Optional[bool] = Field(
-        default=False,
-        description="If set to true, the parser will ignore diagonal text (when the text rotation in degrees modulo 90 is not 0).",
-    )
-    invalidate_cache: Optional[bool] = Field(
-        default=False,
-        description="If set to true, the cache will be ignored and the document re-processes. All document are kept in cache for 48hours after the job was completed to avoid processing the same document twice.",
-    )
-    do_not_cache: Optional[bool] = Field(
-        default=False,
-        description="If set to true, the document will not be cached. This mean that you will be re-charged it you reprocess them as they will not be cached.",
-    )
-    fast_mode: Optional[bool] = Field(
-        default=False,
-        description="Note: Non compatible with gpt-4o. If set to true, the parser will use a faster mode to extract text from documents. This mode will skip OCR of images, and table/heading reconstruction.",
-    )
-    premium_mode: bool = Field(
-        default=False,
-        description="Use our best parser mode if set to True.",
-    )
-    do_not_unroll_columns: Optional[bool] = Field(
-        default=False,
-        description="If set to true, the parser will keep column in the text according to document layout. Reduce reconstruction accuracy, and LLM's/embedings performances in most case.",
-    )
-    page_separator: Optional[str] = Field(
-        default=None,
-        description="A templated  page separator to use to split the text.  If it contain `{page_number}`,it will be replaced by the next page number. If not set will the default separator '\\n---\\n' will be used.",
-    )
-    page_prefix: Optional[str] = Field(
-        default=None,
-        description="A templated prefix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
-    )
-    page_suffix: Optional[str] = Field(
-        default=None,
-        description="A templated suffix to add to the beginning of each page. If it contain `{page_number}`, it will be replaced by the page number.",
-    )
-    gpt4o_mode: bool = Field(
-        default=False,
-        description="Whether to use gpt-4o extract text from documents.",
-    )
-    gpt4o_api_key: Optional[str] = Field(
-        default=None,
-        description="The API key for the GPT-4o API. Lowers the cost of parsing.",
-    )
-    bounding_box: Optional[str] = Field(
-        default=None,
-        description="The bounding box to use to extract text from documents describe as a string containing the bounding box margins",
-    )
-    target_pages: Optional[str] = Field(
-        default=None,
-        description="The target pages to extract text from documents. Describe as a comma separated list of page numbers. The first page of the document is page 0",
-    )
-    ignore_errors: bool = Field(
-        default=True,
-        description="Whether or not to ignore and skip errors raised during parsing.",
-    )
-    split_by_page: bool = Field(
-        default=True,
-        description="Whether to split by page using the page separator",
-    )
-    vendor_multimodal_api_key: Optional[str] = Field(
-        default=None,
-        description="The API key for the multimodal API.",
-    )
-    use_vendor_multimodal_model: bool = Field(
-        default=False,
-        description="Whether to use the vendor multimodal API.",
-    )
-    vendor_multimodal_model_name: Optional[str] = Field(
-        default=None,
-        description="The model name for the vendor multimodal API.",
-    )
-    take_screenshot: bool = Field(
-        default=False,
-        description="Whether to take screenshot of each page of the document.",
-    )
-    custom_client: Optional[httpx.AsyncClient] = Field(
-        default=None, description="A custom HTTPX client to use for sending requests."
+    verbose: bool = Field(
+        default=True, description="Whether to print the progress of the parsing."
     )
 
     @field_validator("api_key", mode="before", check_fields=True)
@@ -224,39 +236,18 @@ class LlamaParse(BasePydanticReader):
                 "file_input must be either a file path string, file bytes, or buffer object"
             )
 
-        data = {
-            "language": self.language.value,
-            "parsing_instruction": self.parsing_instruction,
-            "invalidate_cache": self.invalidate_cache,
-            "skip_diagonal_text": self.skip_diagonal_text,
-            "do_not_cache": self.do_not_cache,
-            "fast_mode": self.fast_mode,
-            "premium_mode": self.premium_mode,
-            "do_not_unroll_columns": self.do_not_unroll_columns,
-            "gpt4o_mode": self.gpt4o_mode,
-            "gpt4o_api_key": self.gpt4o_api_key,
-            "vendor_multimodal_api_key": self.vendor_multimodal_api_key,
-            "use_vendor_multimodal_model": self.use_vendor_multimodal_model,
-            "vendor_multimodal_model_name": self.vendor_multimodal_model_name,
-            "take_screenshot": self.take_screenshot,
-        }
+        data = {}
 
-        # only send page separator to server if it is not None
-        # as if a null, "" string is sent the server will then ignore the page separator instead of using the default
-        if self.page_separator is not None:
-            data["page_separator"] = self.page_separator
+        # for each key of LlamaParseParams
+        # if the value is not None, add it to the data
+        llama_keys = LlamaParseParams.__annotations__.keys()
 
-        if self.page_prefix is not None:
-            data["page_prefix"] = self.page_prefix
+        for key in llama_keys:
+            if getattr(self, key) is not None:
+                data[key] = getattr(self, key)
 
-        if self.page_suffix is not None:
-            data["page_suffix"] = self.page_suffix
-
-        if self.bounding_box is not None:
-            data["bounding_box"] = self.bounding_box
-
-        if self.target_pages is not None:
-            data["target_pages"] = self.target_pages
+        # To track that the job was created from the Python client and better handle bugs
+        data["from_python_client"] = True
 
         try:
             async with self.client_context() as client:

llama_parse/cli/main.py

@@ -0,0 +1,92 @@
+import click
+import json
+from enum import Enum
+from pathlib import Path
+from pydantic.fields import FieldInfo
+from typing import Any, Callable, List
+
+from llama_parse.base import LlamaParse
+
+
+def pydantic_field_to_click_option(name: str, field: FieldInfo) -> click.Option:
+    """Convert a Pydantic field to a Click option."""
+    kwargs = {
+        "default": field.default if field.default else None,
+        "help": field.description,
+    }
+
+    if isinstance(kwargs["default"], Enum):
+        kwargs["default"] = kwargs["default"].value
+
+    if field.annotation is bool:
+        kwargs["is_flag"] = True
+        if field.default and field.default is True:
+            name = f"no-{name}"
+    return click.option(f'--{name.replace("_", "-")}', **kwargs)
+
+
+def add_options(options: List[click.Option]) -> Callable:
+    def _add_options(func: Callable) -> Callable:
+        for option in reversed(options):
+            func = option(func)
+        return func
+
+    return _add_options
+
+
+@click.command()
+@click.argument("file_paths", nargs=-1, type=click.Path(exists=True, path_type=Path))
+@click.option(
+    "--output-file", type=click.Path(path_type=Path), help="Path to save the output"
+)
+@click.option("--output-raw-json", is_flag=True, help="Output the raw JSON result")
+@add_options(
+    [
+        pydantic_field_to_click_option(name, field)
+        for name, field in LlamaParse.model_fields.items()
+        if name not in ["custom_client"]
+    ]
+)
+def parse(**kwargs: Any) -> None:
+    """Parse files using LlamaParse and output the results."""
+    file_paths = kwargs.pop("file_paths")
+    output_file = kwargs.pop("output_file")
+    output_raw_json = kwargs.pop("output_raw_json")
+
+    # Remove None values to use LlamaParse defaults
+    kwargs = {k: v for k, v in kwargs.items() if v is not None}
+
+    # Remove no- prefix for boolean flags
+    kwargs = {k.replace("no_", ""): v for k, v in kwargs.items()}
+
+    parser = LlamaParse(**kwargs)
+    if output_raw_json:
+        results = parser.get_json_result(list(file_paths))
+
+        if output_file:
+            with output_file.open("w") as f:
+                json.dump(results, f)
+            click.echo(f"Results saved to {output_file}")
+        else:
+            click.echo(results)
+    else:
+        results = parser.load_data(list(file_paths))
+
+        if output_file:
+            with output_file.open("w") as f:
+                for i, doc in enumerate(results):
+                    f.write(f"File: {doc.metadata.get('file_path', 'Unknown')}\n")  # type: ignore
+                    f.write(doc.text)  # type: ignore
+                    if i < len(results) - 1:
+                        f.write("\n\n---\n\n")
+            click.echo(f"Results saved to {output_file}")
+        else:
+            for i, doc in enumerate(results):
+                click.echo(f"File: {doc.metadata.get('file_path', 'Unknown')}")  # type: ignore
+                click.echo(doc.text)  # type: ignore
+                if i < len(results) - 1:
+                    click.echo("\n---\n")
+
+
+if __name__ == "__main__":
+    parse()

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "llama-parse"
-version = "0.5.6"
+version = "0.5.12"
 description = "Parse files into RAG-Optimized formats."
 authors = ["Logan Markewich <logan@llamaindex.ai>"]
 license = "MIT"
@@ -14,7 +14,11 @@ packages = [{include = "llama_parse"}]
 [tool.poetry.dependencies]
 python = ">=3.8.1,<4.0"
 llama-index-core = ">=0.11.0"
+click = "^8.1.7"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^8.0.0"
 ipykernel = "^6.29.0"
+
+[tool.poetry.scripts]
+llama-parse = "llama_parse.cli.main:parse"