chatterer 0.1.19__py3-none-any.whl → 0.1.20__py3-none-any.whl

chatterer/examples/anything_to_markdown.py

@@ -1,36 +1,27 @@
-def resolve_import_path_and_get_logger():
-    # ruff: noqa: E402
-    import logging
-    import sys
-
-    if __name__ == "__main__" and "." not in sys.path:
-        sys.path.append(".")
-
-    logger = logging.getLogger(__name__)
-    return logger
-
-
-logger = resolve_import_path_and_get_logger()
+import logging
 from pathlib import Path
 from typing import Optional, TypedDict
 
 import openai
-from spargear import ArgumentSpec, BaseArguments
+from spargear import BaseArguments
 
 from chatterer import anything_to_markdown
 
+logger = logging.getLogger(__name__)
+
 
 class AnythingToMarkdownReturns(TypedDict):
-    in_path: str
-    out_path: Optional[str]
+    input: str
+    output: Optional[str]
     out_text: str
 
 
 class AnythingToMarkdownArguments(BaseArguments):
     """Command line arguments for converting various file types to markdown."""
 
-    in_path: ArgumentSpec[str] = ArgumentSpec(["in-path"], help="Input file to convert to markdown")
-    out_path: Optional[str] = None
+    input: str
+    """Input file to convert to markdown. Can be a file path or a URL."""
+    output: Optional[str] = None
     """Output path for the converted markdown file. If not provided, the input file's suffix is replaced with .md"""
     model: Optional[str] = None
     """OpenAI Model to use for conversion"""
@@ -50,14 +41,13 @@ class AnythingToMarkdownArguments(BaseArguments):
     """Encoding for the output file."""
 
     def run(self) -> AnythingToMarkdownReturns:
-        in_path = self.in_path.unwrap()
         if not self.prevent_save_file:
-            if not self.out_path:
-                out_path = Path(in_path).with_suffix(".md")
+            if not self.output:
+                output = Path(self.input).with_suffix(".md")
             else:
-                out_path = Path(self.out_path)
+                output = Path(self.output)
         else:
-            out_path = None
+            output = None
 
         if self.model:
             llm_client = openai.OpenAI(api_key=self.api_key, base_url=self.base_url)
@@ -67,22 +57,22 @@ class AnythingToMarkdownArguments(BaseArguments):
             llm_model = None
 
         text: str = anything_to_markdown(
-            in_path,
+            self.input,
             llm_client=llm_client,
             llm_model=llm_model,
             style_map=self.style_map,
             exiftool_path=self.exiftool_path,
             docintel_endpoint=self.docintel_endpoint,
         )
-        if out_path:
-            out_path.parent.mkdir(parents=True, exist_ok=True)
-            out_path.write_text(text, encoding=self.encoding)
-            logger.info(f"Converted `{in_path}` to markdown and saved to `{out_path}`.")
+        if output:
+            output.parent.mkdir(parents=True, exist_ok=True)
+            output.write_text(text, encoding=self.encoding)
+            logger.info(f"Converted `{self.input}` to markdown and saved to `{output}`.")
         else:
-            logger.info(f"Converted `{in_path}` to markdown.")
+            logger.info(f"Converted `{self.input}` to markdown.")
         return {
-            "in_path": in_path,
-            "out_path": str(out_path) if out_path is not None else None,
+            "input": self.input,
+            "output": str(output) if output is not None else None,
             "out_text": text,
         }
 

chatterer/examples/get_code_snippets.py

@@ -1,27 +1,19 @@
-def resolve_import_path_and_get_logger():
-    # ruff: noqa: E402
-    import logging
-    import sys
-
-    if __name__ == "__main__" and "." not in sys.path:
-        sys.path.append(".")
-
-    logger = logging.getLogger(__name__)
-    return logger
-
-
-logger = resolve_import_path_and_get_logger()
+import logging
 from pathlib import Path
 from typing import Optional
 
-from spargear import ArgumentSpec, BaseArguments
+from spargear import BaseArguments
 
 from chatterer import CodeSnippets
 
+logger = logging.getLogger(__name__)
+
 
 class GetCodeSnippetsArgs(BaseArguments):
-    path_or_pkgname: ArgumentSpec[str] = ArgumentSpec(["path_or_pkgname"], help="Path to the package or file from which to extract code snippets.")
-    out_path: Optional[str] = None
+    input: str
+    """Path to the package or file from which to extract code snippets."""
+    output: Optional[str] = None
+    """Output path for the extracted code snippets. If not provided, defaults to a file with the same name as the input."""
     ban_file_patterns: list[str] = [".venv/*", Path(__file__).relative_to(Path.cwd()).as_posix()]
     """List of file patterns to ignore."""
     glob_patterns: list[str] = ["*.py"]
@@ -32,27 +24,26 @@ class GetCodeSnippetsArgs(BaseArguments):
     """Prevent saving the extracted code snippets to a file."""
 
     def run(self) -> CodeSnippets:
-        path_or_pkgname = self.path_or_pkgname.unwrap()
         if not self.prevent_save_file:
-            if not self.out_path:
-                out_path = Path(__file__).with_suffix(".txt")
+            if not self.output:
+                output = Path(__file__).with_suffix(".txt")
             else:
-                out_path = Path(self.out_path)
+                output = Path(self.output)
         else:
-            out_path = None
+            output = None
 
         cs = CodeSnippets.from_path_or_pkgname(
-            path_or_pkgname=path_or_pkgname,
+            path_or_pkgname=self.input,
             ban_file_patterns=self.ban_file_patterns,
             glob_patterns=self.glob_patterns,
             case_sensitive=self.case_sensitive,
         )
-        if out_path is not None:
-            out_path.parent.mkdir(parents=True, exist_ok=True)
-            out_path.write_text(cs.snippets_text, encoding="utf-8")
-            logger.info(f"Extracted code snippets from `{path_or_pkgname}` and saved to `{out_path}`.")
+        if output is not None:
+            output.parent.mkdir(parents=True, exist_ok=True)
+            output.write_text(cs.snippets_text, encoding="utf-8")
+            logger.info(f"Extracted code snippets from `{self.input}` and saved to `{output}`.")
         else:
-            logger.info(f"Extracted code snippets from `{path_or_pkgname}`.")
+            logger.info(f"Extracted code snippets from `{self.input}`.")
         return cs
 
 

chatterer/examples/login_with_playwright.py

@@ -1,17 +1,5 @@
-def resolve_import_path_and_get_logger():
-    # ruff: noqa: E402
-    import logging
-    import sys
-
-    if __name__ == "__main__" and "." not in sys.path:
-        sys.path.append(".")
-
-    logger = logging.getLogger(__name__)
-    return logger
-
-
-logger = resolve_import_path_and_get_logger()
 import json
+import logging
 import sys
 from pathlib import Path
 
@@ -19,76 +7,8 @@ from spargear import BaseArguments, SubcommandSpec
 
 from chatterer import PlayWrightBot
 
+logger = logging.getLogger(__name__)
 
-def read_session(url: str, jsonpath: Path) -> None:
-    """
-    Loads the session state from the specified JSON file, then navigates
-    to a protected_url that normally requires login. If the stored session
-    is valid, it should open without re-entering credentials.
-
-    Correction: Loads the JSON content into a dict first to satisfy type hints.
-    """
-    logger.info(f"Loading session from {jsonpath} and navigating to {url} ...")
-
-    if not jsonpath.exists():
-        logger.error(f"Session file not found at {jsonpath}")
-        sys.exit(1)
-
-    # Load the storage state from the JSON file into a dictionary
-    logger.info(f"Reading storage state content from {jsonpath} ...")
-    try:
-        with open(jsonpath, "r", encoding="utf-8") as f:
-            # This dictionary should match the 'StorageState' type expected by Playwright/chatterer
-            storage_state_dict = json.load(f)
-    except json.JSONDecodeError:
-        logger.error(f"Failed to decode JSON from {jsonpath}")
-        sys.exit(1)
-    except Exception as e:
-        logger.error(f"Error reading file {jsonpath}: {e}")
-        sys.exit(1)
-
-    logger.info("Launching browser with loaded session state...")
-    with PlayWrightBot(
-        playwright_launch_options={"headless": False},
-        # Pass the loaded dictionary, which should match the expected 'StorageState' type
-        playwright_persistency_options={"storage_state": storage_state_dict},
-    ) as bot:
-        bot.get_page(url)
-
-        logger.info("Press Enter in the console when you're done checking the protected page.")
-        input("    >> Press Enter to exit: ")
-
-    logger.info("Done! Browser is now closed.")
-
-
-def write_session(url: str, jsonpath: Path) -> None:
-    """
-    Launches a non-headless browser and navigates to the login_url.
-    The user can manually log in, then press Enter in the console
-    to store the current session state into a JSON file.
-    """
-    logger.info(f"Launching browser and navigating to {url} ... Please log in manually.")
-
-    # Ensure jsonpath directory exists
-    jsonpath.parent.mkdir(parents=True, exist_ok=True)
-
-    with PlayWrightBot(playwright_launch_options={"headless": False}) as bot:
-        bot.get_page(url)
-
-        logger.info("After completing the login in the browser, press Enter here to save the session.")
-        input("    >> Press Enter when ready: ")
-
-        # get_sync_browser() returns the BrowserContext internally
-        context = bot.get_sync_browser()
-
-        # Save the current session (cookies, localStorage) to a JSON file
-        logger.info(f"Saving storage state to {jsonpath} ...")
-        context.storage_state(path=jsonpath)  # Pass Path object directly
-
-    logger.info("Done! Browser is now closed.")
-
-
-# --- Spargear Declarative CLI Definition ---
 
 # Define the default path location relative to this script file
 DEFAULT_JSON_PATH = Path(__file__).resolve().parent / "session_state.json"
@@ -160,7 +80,72 @@ class LoginWithPlaywrightArgs(BaseArguments):
             sys.exit(1)
 
 
-# --- Main Execution Logic ---
+def read_session(url: str, jsonpath: Path) -> None:
+    """
+    Loads the session state from the specified JSON file, then navigates
+    to a protected_url that normally requires login. If the stored session
+    is valid, it should open without re-entering credentials.
+
+    Correction: Loads the JSON content into a dict first to satisfy type hints.
+    """
+    logger.info(f"Loading session from {jsonpath} and navigating to {url} ...")
+
+    if not jsonpath.exists():
+        logger.error(f"Session file not found at {jsonpath}")
+        sys.exit(1)
+
+    # Load the storage state from the JSON file into a dictionary
+    logger.info(f"Reading storage state content from {jsonpath} ...")
+    try:
+        with open(jsonpath, "r", encoding="utf-8") as f:
+            # This dictionary should match the 'StorageState' type expected by Playwright/chatterer
+            storage_state_dict = json.load(f)
+    except json.JSONDecodeError:
+        logger.error(f"Failed to decode JSON from {jsonpath}")
+        sys.exit(1)
+    except Exception as e:
+        logger.error(f"Error reading file {jsonpath}: {e}")
+        sys.exit(1)
+
+    logger.info("Launching browser with loaded session state...")
+    with PlayWrightBot(
+        playwright_launch_options={"headless": False},
+        # Pass the loaded dictionary, which should match the expected 'StorageState' type
+        playwright_persistency_options={"storage_state": storage_state_dict},
+    ) as bot:
+        bot.get_page(url)
+
+        logger.info("Press Enter in the console when you're done checking the protected page.")
+        input("    >> Press Enter to exit: ")
+
+    logger.info("Done! Browser is now closed.")
+
+
+def write_session(url: str, jsonpath: Path) -> None:
+    """
+    Launches a non-headless browser and navigates to the login_url.
+    The user can manually log in, then press Enter in the console
+    to store the current session state into a JSON file.
+    """
+    logger.info(f"Launching browser and navigating to {url} ... Please log in manually.")
+
+    # Ensure jsonpath directory exists
+    jsonpath.parent.mkdir(parents=True, exist_ok=True)
+
+    with PlayWrightBot(playwright_launch_options={"headless": False}) as bot:
+        bot.get_page(url)
+
+        logger.info("After completing the login in the browser, press Enter here to save the session.")
+        input("    >> Press Enter when ready: ")
+
+        # get_sync_browser() returns the BrowserContext internally
+        context = bot.get_sync_browser()
+
+        # Save the current session (cookies, localStorage) to a JSON file
+        logger.info(f"Saving storage state to {jsonpath} ...")
+        context.storage_state(path=jsonpath)  # Pass Path object directly
+
+    logger.info("Done! Browser is now closed.")
 
 
 def main() -> None:

chatterer/examples/make_ppt.py

@@ -1,16 +1,3 @@
-def resolve_import_path_and_get_logger():
-    # ruff: noqa: E402
-    import logging
-    import sys
-
-    if __name__ == "__main__" and "." not in sys.path:
-        sys.path.append(".")
-
-    logger = logging.getLogger(__name__)
-    return logger
-
-
-logger = resolve_import_path_and_get_logger()
 import re
 import sys
 from pathlib import Path
@@ -192,7 +179,9 @@ class MakePptArguments(BaseArguments):
     """Prompt for organizing slides into a presentation script"""
 
     # LLM Settings
-    provider: str = "openai:gpt-4.1"  # Example: "openai:gpt-4o", "anthropic:claude-3-haiku-20240307", "google:gemini-1.5-flash"
+    provider: str = (
+        "openai:gpt-4.1"  # Example: "openai:gpt-4o", "anthropic:claude-3-haiku-20240307", "google:gemini-1.5-flash"
+    )
     """Name of the language model to use (provider:model_name)"""
 
     # Other settings

chatterer/examples/pdf_to_markdown.py

@@ -1,16 +1,4 @@
-def resolve_import_path_and_get_logger():
-    # ruff: noqa: E402
-    import logging
-    import sys
-
-    if __name__ == "__main__" and "." not in sys.path:
-        sys.path.append(".")
-
-    logger = logging.getLogger(__name__)
-    return logger
-
-
-logger = resolve_import_path_and_get_logger()
+import logging
 import sys
 from pathlib import Path
 from typing import Optional
@@ -19,46 +7,51 @@ from spargear import ArgumentSpec, BaseArguments
 
 from chatterer import Chatterer, PdfToMarkdown
 
+logger = logging.getLogger(__name__)
+
 
 class PdfToMarkdownArgs(BaseArguments):
-    in_path: ArgumentSpec[str] = ArgumentSpec(["in-path"], help="Path to the input PDF file or a directory containing PDF files.")
-    out_path: Optional[str] = None
+    input: str
+    """Input PDF file or directory containing PDF files to convert to markdown."""
+    output: Optional[str] = None
     """Output path. For a file, path to the output markdown file. For a directory, output directory for .md files."""
+    """Chatterer instance for communication."""
+    pages: Optional[str] = None
+    """Page indices to convert (e.g., '1,3,5-9')."""
+    recursive: bool = False
+    """If input is a directory, search for PDFs recursively."""
     chatterer: ArgumentSpec[Chatterer] = ArgumentSpec(
         ["--chatterer"],
-        default=None,
+        default_factory=lambda: Chatterer.from_provider("google:gemini-2.5-flash-preview-05-20"),
         help="Chatterer instance for communication.",
         type=Chatterer.from_provider,
-        required=True,
     )
-    pages: Optional[str] = None
-    """Page indices to convert (e.g., '1,3,5-9')."""
-    recursive: bool = False
-    """If input is a directory, search for PDFs recursively."""
 
     def run(self) -> list[dict[str, str]]:
-        in_path = Path(self.in_path.unwrap()).resolve()
+        input = Path(self.input).resolve()
         page_indices = parse_page_indices(self.pages) if self.pages else None
         pdf_files: list[Path] = []
         is_dir = False
-        if in_path.is_file():
-            if in_path.suffix.lower() != ".pdf":
+        if input.is_file():
+            if input.suffix.lower() != ".pdf":
                 sys.exit(1)
-            pdf_files.append(in_path)
-        elif in_path.is_dir():
+            pdf_files.append(input)
+        elif input.is_dir():
             is_dir = True
             pattern = "*.pdf"
-            pdf_files = sorted([f for f in (in_path.rglob(pattern) if self.recursive else in_path.glob(pattern)) if f.is_file()])
+            pdf_files = sorted([
+                f for f in (input.rglob(pattern) if self.recursive else input.glob(pattern)) if f.is_file()
+            ])
             if not pdf_files:
                 sys.exit(0)
         else:
             sys.exit(1)
-        if self.out_path:
-            out_base = Path(self.out_path).resolve()
+        if self.output:
+            out_base = Path(self.output).resolve()
         elif is_dir:
-            out_base = in_path
+            out_base = input
         else:
-            out_base = in_path.with_suffix(".md")
+            out_base = input.with_suffix(".md")
 
         if is_dir:
             out_base.mkdir(parents=True, exist_ok=True)
@@ -68,11 +61,11 @@ class PdfToMarkdownArgs(BaseArguments):
         converter = PdfToMarkdown(chatterer=self.chatterer.unwrap())
         results: list[dict[str, str]] = []
         for pdf in pdf_files:
-            out_path = (out_base / (pdf.stem + ".md")) if is_dir else out_base
+            output = (out_base / (pdf.stem + ".md")) if is_dir else out_base
             md = converter.convert(str(pdf), page_indices)
-            out_path.parent.mkdir(parents=True, exist_ok=True)
-            out_path.write_text(md, encoding="utf-8")
-            results.append({"input": pdf.as_posix(), "output": out_path.as_posix(), "result": md})
+            output.parent.mkdir(parents=True, exist_ok=True)
+            output.write_text(md, encoding="utf-8")
+            results.append({"input": pdf.as_posix(), "output": output.as_posix(), "result": md})
         logger.info(f"Converted {len(pdf_files)} PDF(s) to markdown and saved to `{out_base}`.")
         return results
 

chatterer/examples/pdf_to_text.py

@@ -1,36 +1,30 @@
-def resolve_import_path_and_get_logger():
-    # ruff: noqa: E402
-    import logging
-    import sys
-
-    if __name__ == "__main__" and "." not in sys.path:
-        sys.path.append(".")
-
-    logger = logging.getLogger(__name__)
-    return logger
-
-
-logger = resolve_import_path_and_get_logger()
+import logging
 import sys
 from pathlib import Path
+from typing import Optional
 
-from spargear import ArgumentSpec, BaseArguments
+from spargear import BaseArguments
 
 from chatterer.tools.convert_to_text import pdf_to_text
 
+logger = logging.getLogger(__name__)
+
 
 class PdfToTextArgs(BaseArguments):
-    in_path: ArgumentSpec[Path] = ArgumentSpec(["in-path"], help="Path to the PDF file.")
-    out_path: ArgumentSpec[Path] = ArgumentSpec(["--out-path"], default=None, help="Output file path.")
-    pages: ArgumentSpec[str] = ArgumentSpec(["--pages"], default=None, help="Page indices to extract, e.g. '1,3,5-9'.")
+    input: Path
+    """Path to the PDF file to convert to text."""
+    output: Optional[Path]
+    """Path to the output text file. If not provided, defaults to the input file with a .txt suffix."""
+    pages: Optional[str] = None
+    """Comma-separated list of page indices to extract from the PDF. Supports ranges, e.g., '1,3,5-9'."""
 
     def run(self) -> None:
-        input = self.in_path.unwrap().resolve()
-        out = self.out_path.value or input.with_suffix(".txt")
+        input = self.input.resolve()
+        out = self.output or input.with_suffix(".txt")
         if not input.is_file():
             sys.exit(1)
         out.write_text(
-            pdf_to_text(input, parse_page_indices(pages_arg) if (pages_arg := self.pages.value) else None),
+            pdf_to_text(path_or_file=input, page_indices=self.pages),
             encoding="utf-8",
         )
         logger.info(f"Extracted text from `{input}` to `{out}`")

chatterer/examples/transcription_api.py

@@ -2,51 +2,36 @@
 
 from io import BytesIO
 from pathlib import Path
-from typing import cast
+from typing import Optional, cast
 
 from openai import OpenAI
 from pydub import AudioSegment
-from spargear import ArgumentSpec, BaseArguments
+from spargear import BaseArguments
 
 # Maximum chunk length in seconds
 MAX_CHUNK_DURATION = 600
 
 
 class TranscriptionApiArguments(BaseArguments):
-    in_path = ArgumentSpec(
-        ["in-path"],
-        type=Path,
-        help="The audio file to transcribe.",
-    )
-    out_path = ArgumentSpec(
-        ["--out-path"],
-        type=Path,
-        default=None,
-        help="Path to save the transcription output.",
-    )
-    model: ArgumentSpec[str] = ArgumentSpec(
-        ["--model"],
-        default="gpt-4o-transcribe",
-        help="The model to use for transcription.",
-    )
-    api_key: ArgumentSpec[str] = ArgumentSpec(
-        ["--api-key"],
-        default=None,
-        help="The API key for authentication.",
-    )
-    base_url: ArgumentSpec[str] = ArgumentSpec(
-        ["--base-url"],
-        default="https://api.openai.com/v1",
-        help="The base URL for the API.",
-    )
+    input: Path
+    """The audio file to transcribe."""
+    output: Optional[Path] = None
+    """Path to save the transcription output."""
+    model: str = "gpt-4o-transcribe"
+    """The model to use for transcription."""
+    api_key: Optional[str] = None
+    """The API key for authentication."""
+    base_url: str = "https://api.openai.com/v1"
+    """The base URL for the API."""
+    prompt: str = "Transcribe whole text from audio."
+    """The prompt to use for transcription."""
 
     def run(self) -> None:
-        audio_path = self.in_path.unwrap()
-        model = self.model.unwrap()
+        model = self.model
 
-        client = OpenAI(api_key=self.api_key.value, base_url=self.base_url.value)
+        client = OpenAI(api_key=self.api_key, base_url=self.base_url)
 
-        audio = load_audio_segment(audio_path)
+        audio = load_audio_segment(self.input)
 
         segments = split_audio(audio, MAX_CHUNK_DURATION)
         print(f"[i] Audio duration: {len(audio) / 1000:.1f}s; splitting into {len(segments)} segment(s)")
@@ -54,10 +39,10 @@ class TranscriptionApiArguments(BaseArguments):
         transcripts: list[str] = []
         for idx, seg in enumerate(segments, start=1):
             print(f"[i] Transcribing segment {idx}/{len(segments)}...")
-            transcripts.append(transcribe_segment(seg, client, model))
+            transcripts.append(transcribe_segment(seg, client, model, self.prompt))
 
         full_transcript = "\n\n".join(transcripts)
-        output_path: Path = self.out_path.value or audio_path.with_suffix(".txt")
+        output_path: Path = self.output or self.input.with_suffix(".txt")
         output_path.write_text(full_transcript, encoding="utf-8")
         print(f"[✓] Transcription saved to: {output_path}")
 
@@ -94,7 +79,7 @@ def split_audio(audio: AudioSegment, max_duration_s: int) -> list[AudioSegment]:
     return segments
 
 
-def transcribe_segment(segment: AudioSegment, client: OpenAI, model: str) -> str:
+def transcribe_segment(segment: AudioSegment, client: OpenAI, model: str, prompt: str) -> str:
     """
     Transcribe a single AudioSegment chunk and return its text.
     """
@@ -104,7 +89,7 @@ def transcribe_segment(segment: AudioSegment, client: OpenAI, model: str) -> str
     mp3_bytes = buffer.read()
     response = client.audio.transcriptions.create(
         model=model,
-        prompt="Transcribe whole text from audio.",
+        prompt=prompt,
         file=("audio.mp3", mp3_bytes),
         response_format="text",
         stream=True,

chatterer/examples/upstage_parser.py

@@ -1,17 +1,6 @@
-def resolve_import_path_and_get_logger():
-    # ruff: noqa: E402
-    import logging
-    import sys
-
-    if __name__ == "__main__" and "." not in sys.path:
-        sys.path.append(".")
-
-    logger = logging.getLogger(__name__)
-    return logger
-
-
-logger = resolve_import_path_and_get_logger()
+import logging
 from pathlib import Path
+from typing import Optional
 
 from langchain_core.documents.base import Blob
 from spargear import ArgumentSpec, BaseArguments
@@ -27,28 +16,34 @@ from chatterer.tools.upstage_document_parser import (
     SplitType,
 )
 
+logger = logging.getLogger(__name__)
+
 
 class UpstageParserArguments(BaseArguments):
-    in_path: ArgumentSpec[Path] = ArgumentSpec(["in-path"], help="Path to the input file.")
-    out_path: ArgumentSpec[Path] = ArgumentSpec(["--out-path"], default=None, help="Output file path.")
-    api_key: ArgumentSpec[str] = ArgumentSpec(["--api-key"], default=None, help="API key for the Upstage API.")
-    base_url: ArgumentSpec[str] = ArgumentSpec(["--base-url"], default=DOCUMENT_PARSE_BASE_URL, help="Base URL for the Upstage API.")
-    model: ArgumentSpec[str] = ArgumentSpec(["--model"], default=DOCUMENT_PARSE_DEFAULT_MODEL, help="Model to use for parsing.")
-    split: ArgumentSpec[SplitType] = ArgumentSpec(["--split"], default="none", help="Split type for parsing.")
-    ocr: ArgumentSpec[OCR] = ArgumentSpec(["--ocr"], default="auto", help="OCR type for parsing.")
-    output_format: ArgumentSpec[OutputFormat] = ArgumentSpec(["--output-format"], default="markdown", help="Output format.")
-    coordinates: ArgumentSpec[bool] = ArgumentSpec(["--coordinates"], action="store_true", help="Include coordinates.")
-    base64_encoding: ArgumentSpec[list[Category]] = ArgumentSpec(["--base64-encoding"], default=["figure"], help="Base64 encoding for specific categories.")
-    image_description_instruction: ArgumentSpec[str] = ArgumentSpec(
-        ["--image-description-instruction"],
-        default="Describe the image in detail.",
-        help="Instruction for image description.",
-    )
-    image_dir: ArgumentSpec[str] = ArgumentSpec(
-        ["--image-dir"],
-        default=DEFAULT_IMAGE_DIR,
-        help="Directory for image paths.",
-    )
+    input: Path
+    """Input file to parse. Can be a PDF, image, or other supported formats."""
+    output: Optional[Path] = None
+    """Output file path for the parsed content. Defaults to input file with .md suffix if not provided."""
+    api_key: Optional[str] = None
+    """API key for the Upstage API."""
+    base_url: str = DOCUMENT_PARSE_BASE_URL
+    """Base URL for the Upstage API."""
+    model: str = DOCUMENT_PARSE_DEFAULT_MODEL
+    """Model to use for parsing."""
+    split: SplitType = "none"
+    """Split type for the parsed content."""
+    ocr: OCR = "auto"
+    """OCR type for parsing."""
+    output_format: OutputFormat = "markdown"
+    """Output format for the parsed content."""
+    coordinates: bool = False
+    """Whether to include coordinates in the output."""
+    base64_encoding: list[Category] = ["figure"]
+    """Base64 encoding for specific categories in the parsed content."""
+    image_description_instruction: str = "Describe the image in detail."
+    """Instruction for generating image descriptions."""
+    image_dir: str = DEFAULT_IMAGE_DIR
+    """Directory to save images extracted from the document."""
     chatterer: ArgumentSpec[Chatterer] = ArgumentSpec(
         ["--chatterer"],
         default=None,
@@ -57,26 +52,25 @@ class UpstageParserArguments(BaseArguments):
     )
 
     def run(self) -> None:
-        input = UpstageParserArguments.in_path.unwrap().resolve()
-        out = UpstageParserArguments.out_path.value or input.with_suffix(".md")
+        input = UpstageParserArguments.input.resolve()
+        out = UpstageParserArguments.output or input.with_suffix(".md")
 
         parser = UpstageDocumentParseParser(
-            api_key=UpstageParserArguments.api_key.value,
-            base_url=UpstageParserArguments.base_url.unwrap(),
-            model=UpstageParserArguments.model.unwrap(),
-            split=UpstageParserArguments.split.unwrap(),
-            ocr=UpstageParserArguments.ocr.unwrap(),
-            output_format=UpstageParserArguments.output_format.unwrap(),
-            coordinates=UpstageParserArguments.coordinates.unwrap(),
-            base64_encoding=UpstageParserArguments.base64_encoding.unwrap(),
-            image_description_instruction=UpstageParserArguments.image_description_instruction.unwrap(),
-            image_dir=UpstageParserArguments.image_dir.value,
+            api_key=UpstageParserArguments.api_key,
+            base_url=UpstageParserArguments.base_url,
+            model=UpstageParserArguments.model,
+            split=UpstageParserArguments.split,
+            ocr=UpstageParserArguments.ocr,
+            output_format=UpstageParserArguments.output_format,
+            coordinates=UpstageParserArguments.coordinates,
+            base64_encoding=UpstageParserArguments.base64_encoding,
+            image_description_instruction=UpstageParserArguments.image_description_instruction,
+            image_dir=UpstageParserArguments.image_dir,
             chatterer=UpstageParserArguments.chatterer.value,
         )
-
         docs = parser.parse(Blob.from_path(input))  # pyright: ignore[reportUnknownMemberType]
 
-        if UpstageParserArguments.image_dir.value:
+        if UpstageParserArguments.image_dir:
             for path, image in parser.image_data.items():
                 (path := Path(path)).parent.mkdir(parents=True, exist_ok=True)
                 path.write_bytes(image)

chatterer/examples/webpage_to_markdown.py

@@ -1,16 +1,3 @@
-def resolve_import_path_and_get_logger():
-    # ruff: noqa: E402
-    import logging
-    import sys
-
-    if __name__ == "__main__" and "." not in sys.path:
-        sys.path.append(".")
-
-    logger = logging.getLogger(__name__)
-    return logger
-
-
-logger = resolve_import_path_and_get_logger()
 from pathlib import Path
 from typing import Literal
 
@@ -20,49 +7,53 @@ from chatterer import Chatterer, MarkdownLink, PlayWrightBot
 
 
 class WebpageToMarkdownArgs(BaseArguments):
-    url: ArgumentSpec[str] = ArgumentSpec(["url"], help="The URL to crawl.")
-    out_path: str = Path(__file__).with_suffix(".md").as_posix()
+    url: str
+    """The URL to crawl."""
+    output: str = Path(__file__).with_suffix(".md").as_posix()
     """The output file path for the markdown file."""
     chatterer: ArgumentSpec[Chatterer] = ArgumentSpec(
-        ["--llm"],
-        default=None,
-        type=Chatterer.from_provider,
+        ["--chatterer"],
         help="The Chatterer backend and model to use for filtering the markdown.",
+        type=Chatterer.from_provider,
     )
     engine: Literal["firefox", "chromium", "webkit"] = "firefox"
     """The browser engine to use."""
 
     def run(self) -> None:
         chatterer = self.chatterer.value
-        url: str = self.url.unwrap().strip()
-        out_path: Path = Path(self.out_path).resolve()
+        url: str = self.url.strip()
+        output: Path = Path(self.output).resolve()
         with PlayWrightBot(chatterer=chatterer, engine=self.engine) as bot:
             md = bot.url_to_md(url)
-            out_path.write_text(md, encoding="utf-8")
+            output.write_text(md, encoding="utf-8")
             if chatterer is not None:
                 md_llm = bot.url_to_md_with_llm(url.strip())
-                out_path.write_text(md_llm, encoding="utf-8")
+                output.write_text(md_llm, encoding="utf-8")
             links = MarkdownLink.from_markdown(md, referer_url=url)
             for link in links:
                 if link.type == "link":
-                    print(f"- [{truncate_string(link.url)}] {truncate_string(link.inline_text)} ({truncate_string(link.inline_title)})")
+                    print(
+                        f"- [{truncate_string(link.url)}] {truncate_string(link.inline_text)} ({truncate_string(link.inline_title)})"
+                    )
                 elif link.type == "image":
                     print(f"- ![{truncate_string(link.url)}] ({truncate_string(link.inline_text)})")
 
     async def arun(self) -> None:
         chatterer = self.chatterer.value
-        url: str = self.url.unwrap().strip()
-        out_path: Path = Path(self.out_path).resolve()
+        url: str = self.url.strip()
+        output: Path = Path(self.output).resolve()
         async with PlayWrightBot(chatterer=chatterer, engine=self.engine) as bot:
             md = await bot.aurl_to_md(url)
-            out_path.write_text(md, encoding="utf-8")
+            output.write_text(md, encoding="utf-8")
             if chatterer is not None:
                 md_llm = await bot.aurl_to_md_with_llm(url.strip())
-                out_path.write_text(md_llm, encoding="utf-8")
+                output.write_text(md_llm, encoding="utf-8")
             links = MarkdownLink.from_markdown(md, referer_url=url)
             for link in links:
                 if link.type == "link":
-                    print(f"- [{truncate_string(link.url)}] {truncate_string(link.inline_text)} ({truncate_string(link.inline_title)})")
+                    print(
+                        f"- [{truncate_string(link.url)}] {truncate_string(link.inline_text)} ({truncate_string(link.inline_title)})"
+                    )
                 elif link.type == "image":
                     print(f"- ![{truncate_string(link.url)}] ({truncate_string(link.inline_text)})")
 

chatterer/strategies/atom_of_thoughts.py

@@ -379,7 +379,7 @@ class AoTPipeline:
     chatterer: Chatterer
     max_depth: int = 2
     max_retries: int = 2
-    steps_history: list[StepRecord] = field(default_factory=list)
+    steps_history: list[StepRecord] = field(default_factory=list[StepRecord])
     prompter: AoTPrompter = field(default_factory=AoTPrompter)
 
     # 4.1) Utility for calling the LLM with Pydantic parsing

chatterer/tools/convert_pdf_to_markdown.py

@@ -4,7 +4,8 @@ import logging
 import re
 from contextlib import contextmanager
 from dataclasses import dataclass
-from typing import TYPE_CHECKING, Callable, Iterable, List, Literal, Optional, Union
+from types import EllipsisType
+from typing import TYPE_CHECKING, Callable, Iterable, List, Literal, Optional
 
 from ..language_model import Chatterer, HumanMessage
 from ..utils.base64_image import Base64Image
@@ -17,6 +18,7 @@ if TYPE_CHECKING:
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
 MARKDOWN_PATTERN: re.Pattern[str] = re.compile(r"```(?:markdown\s*\n)?(.*?)```", re.DOTALL)
+PageIndexType = Iterable[int | tuple[int | EllipsisType, int | EllipsisType]] | int | str
 
 
 @dataclass
@@ -107,8 +109,8 @@ class PdfToMarkdown:
 
     def convert(
         self,
-        pdf_input: Union[str, "Document"],
-        page_indices: Optional[Union[Iterable[int], int]] = None,
+        pdf_input: "Document | PathOrReadable",
+        page_indices: Optional[PageIndexType] = None,
         progress_callback: Optional[Callable[[int, int], None]] = None,
     ) -> str:
         """
@@ -123,7 +125,9 @@ class PdfToMarkdown:
             A single string containing the concatenated Markdown output for the processed pages.
         """
         with open_pdf(pdf_input) as doc:
-            target_page_indices = list(_get_page_indices(page_indices, len(doc)))
+            target_page_indices = list(
+                _get_page_indices(page_indices=page_indices, max_doc_pages=len(doc), is_input_zero_based=True)
+            )
             total_pages_to_process = len(target_page_indices)
             if total_pages_to_process == 0:
                 logger.warning("No pages selected for processing.")
@@ -232,7 +236,7 @@ def render_pdf_as_image(
 
     images_bytes: dict[int, bytes] = {}
     matrix = Matrix(zoom, zoom)  # Control output resolution
-    for page_idx in _get_page_indices(page_indices, len(doc)):
+    for page_idx in _get_page_indices(page_indices=page_indices, max_doc_pages=len(doc), is_input_zero_based=True):
         img_bytes = bytes(
             get_pixmap(
                 page=doc[page_idx],
@@ -243,10 +247,7 @@ def render_pdf_as_image(
     return images_bytes
 
 
-def extract_text_from_pdf(
-    doc: "Document",
-    page_indices: Iterable[int] | int | None = None,
-) -> dict[int, str]:
+def extract_text_from_pdf(doc: "Document", page_indices: Optional[PageIndexType] = None) -> dict[int, str]:
     """Convert a PDF file to plain text.
 
     Extracts text from each page of a PDF file and formats it with page markers.
@@ -261,7 +262,11 @@ def extract_text_from_pdf(
     """
     return {
         page_idx: doc[page_idx].get_textpage().extractText().strip()  # pyright: ignore[reportUnknownMemberType]
-        for page_idx in _get_page_indices(page_indices, len(doc))
+        for page_idx in _get_page_indices(
+            page_indices=page_indices,
+            max_doc_pages=len(doc),
+            is_input_zero_based=True,
+        )
     }
 
 
@@ -292,11 +297,97 @@ def open_pdf(pdf_input: PathOrReadable | Document):
         doc.close()
 
 
-def _get_page_indices(page_indices: Iterable[int] | int | None, max_doc_pages: int) -> Iterable[int]:
+def _get_page_indices(
+    page_indices: Optional[PageIndexType], max_doc_pages: int, is_input_zero_based: bool
+) -> list[int]:
     """Helper function to handle page indices for PDF conversion."""
+
+    def _to_zero_based_int(idx: int) -> int:
+        """Convert a 1-based index to a 0-based index if necessary."""
+        if is_input_zero_based:
+            return idx
+        else:
+            if idx < 1 or idx > max_doc_pages:
+                raise ValueError(f"Index {idx} is out of bounds for document with {max_doc_pages} pages (1-based).")
+            return idx - 1
+
     if page_indices is None:
-        return range(max_doc_pages)
+        return list(range(max_doc_pages))  # Convert all pages
     elif isinstance(page_indices, int):
-        return [page_indices]
+        # Handle single integer input for page index
+        return [_to_zero_based_int(page_indices)]
+    elif isinstance(page_indices, str):
+        # Handle string input for page indices
+        return _interpret_index_string(
+            index_str=page_indices, max_doc_pages=max_doc_pages, is_input_zero_based=is_input_zero_based
+        )
     else:
-        return [i for i in page_indices if 0 <= i < max_doc_pages]
+        # Handle iterable input for page indices
+        indices: set[int] = set()
+        for idx in page_indices:
+            if isinstance(idx, int):
+                indices.add(_to_zero_based_int(idx))
+            else:
+                start, end = idx
+                if isinstance(start, EllipsisType):
+                    start = 0
+                else:
+                    start = _to_zero_based_int(start)
+
+                if isinstance(end, EllipsisType):
+                    end = max_doc_pages - 1
+                else:
+                    end = _to_zero_based_int(end)
+
+                if start > end:
+                    raise ValueError(
+                        f"Invalid range: {start} - {end}. Start index must be less than or equal to end index."
+                    )
+                indices.update(range(start, end + 1))
+
+        return sorted(indices)  # Return sorted list of indices
+
+
+def _interpret_index_string(index_str: str, max_doc_pages: int, is_input_zero_based: bool) -> list[int]:
+    """Interpret a string of comma-separated indices and ranges."""
+
+    def _to_zero_based_int(idx_str: str) -> int:
+        i = int(idx_str)
+        if is_input_zero_based:
+            if i < 0 or i >= max_doc_pages:
+                raise ValueError(f"Index {i} is out of bounds for document with {max_doc_pages} pages.")
+            return i
+        else:
+            if i < 1 or i > max_doc_pages:
+                raise ValueError(f"Index {i} is out of bounds for document with {max_doc_pages} pages (1-based).")
+            return i - 1  # Convert to zero-based index
+
+    indices: set[int] = set()
+    for part in index_str.split(","):
+        part: str = part.strip()
+        count_dash: int = part.count("-")
+        if count_dash == 0:
+            indices.add(_to_zero_based_int(part))
+        elif count_dash == 1:
+            idx_dash: int = part.index("-")
+            start = part[:idx_dash].strip()
+            end = part[idx_dash + 1 :].strip()
+            if not start:
+                start = _to_zero_based_int("0")  # Default to 0 if no start index is provided
+            else:
+                start = _to_zero_based_int(start)
+
+            if not end:
+                end = _to_zero_based_int(str(max_doc_pages - 1))  # Default to last page if no end index is provided
+            else:
+                end = _to_zero_based_int(end)
+
+            if start > end:
+                raise ValueError(
+                    f"Invalid range: {start} - {end}. Start index must be less than or equal to end index."
+                )
+            indices.update(range(start, end + 1))
+        else:
+            raise ValueError(f"Invalid page index format: '{part}'. Expected format is '1,2,3' or '1-3'.")
+
+    return sorted(indices)  # Return sorted list of indices, ensuring no duplicates

chatterer/tools/convert_to_text.py

@@ -8,7 +8,6 @@ from pathlib import Path
 from typing import (
     TYPE_CHECKING,
     Callable,
-    Iterable,
     NamedTuple,
     NotRequired,
     Optional,
@@ -20,7 +19,7 @@ from typing import (
 
 from ..common_types.io import PathOrReadable
 from ..utils.bytesio import read_bytes_stream
-from .convert_pdf_to_markdown import extract_text_from_pdf
+from .convert_pdf_to_markdown import PageIndexType, extract_text_from_pdf
 
 if TYPE_CHECKING:
     from bs4 import Tag
@@ -222,7 +221,7 @@ def html_to_markdown(html: str, options: Optional[HtmlToMarkdownOptions]) -> str
     return str(markdownify(html, **(options or {})))  # pyright: ignore[reportUnknownArgumentType]
 
 
-def pdf_to_text(path_or_file: PathOrReadable, page_indices: Iterable[int] | int | None = None) -> str:
+def pdf_to_text(path_or_file: PathOrReadable, page_indices: Optional[PageIndexType] = None) -> str:
     """
     Convert a PDF file to plain text.
 
@@ -248,7 +247,7 @@ def pdf_to_text(path_or_file: PathOrReadable, page_indices: Iterable[int] | int
         with Document(stream=stream.read()) as doc:
             return "\n".join(
                 f"<!-- Page {page_no} -->\n{text}\n"
-                for page_no, text in extract_text_from_pdf(doc, page_indices).items()
+                for page_no, text in extract_text_from_pdf(doc=doc, page_indices=page_indices).items()
             )
 
 

chatterer/tools/upstage_document_parser.py

@@ -67,7 +67,7 @@ class Coordinate(BaseModel):
 class Element(BaseModel):
     category: Category
     content: Content
-    coordinates: list[Coordinate] = Field(default_factory=list)
+    coordinates: list[Coordinate] = Field(default_factory=list[Coordinate])
     base64_encoding: str = ""
     id: int
     page: int
@@ -701,5 +701,5 @@ def _get_metadata_from_document(doc: Document) -> dict[object, object]:
     Helper function to extract metadata from a Document object.
     This is a placeholder and should be adjusted based on actual metadata structure.
     """
-    metadata: dict[object, object] = doc.metadata  # pyright: ignore[reportUnknownMemberType]
+    metadata: dict[object, object] = doc.metadata  # pyright: ignore[reportUnknownMemberType, reportUnknownVariableType]
     return metadata

chatterer/utils/code_agent.py

@@ -185,7 +185,7 @@ def insert_callables_into_global(
         repl_tool.globals = {}  # Or handle appropriately
 
     # Safely update globals
-    current_globals: dict[object, object] = repl_tool.globals  # pyright: ignore[reportUnknownMemberType]
+    current_globals: dict[object, object] = repl_tool.globals  # pyright: ignore[reportUnknownMemberType, reportUnknownVariableType]
     for fsig in function_signatures:
         current_globals[fsig.name] = fsig.callable
     # No need to reassign if globals is mutable (dict)

{chatterer-0.1.19.dist-info → chatterer-0.1.20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chatterer
-Version: 0.1.19
+Version: 0.1.20
 Summary: The highest-level interface for various LLM APIs.
 Requires-Python: >=3.12
 Description-Content-Type: text/markdown
@@ -11,7 +11,7 @@ Requires-Dist: pillow>=11.1.0
 Requires-Dist: regex>=2024.11.6
 Requires-Dist: rich>=13.9.4
 Requires-Dist: colorama>=0.4.6
-Requires-Dist: spargear>=0.1.6
+Requires-Dist: spargear>=0.2.0
 Provides-Extra: dev
 Requires-Dist: neo4j-extension>=0.1.14; extra == "dev"
 Requires-Dist: ipykernel>=6.29.5; extra == "dev"

{chatterer-0.1.19.dist-info → chatterer-0.1.20.dist-info}/RECORD

@@ -6,23 +6,23 @@ chatterer/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 chatterer/common_types/__init__.py,sha256=jfS6m5UANSvGjzQ_nzYDpryn5uZqNb06-4xCsQ2C_lw,376
 chatterer/common_types/io.py,sha256=fetiyi1suZ3NF2mj5k5KDLJLGKS1n4J-5UmH7JN36g8,817
 chatterer/examples/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-chatterer/examples/anything_to_markdown.py,sha256=fyqUfzQWlUMyPEAmRyvvoSnNGVOjhPS6AGWru0wIpuo,3066
-chatterer/examples/get_code_snippets.py,sha256=L6hilONtNItWlX4lHhWJNEJpA9yviDSeJlWwvGCfMmk,2198
-chatterer/examples/login_with_playwright.py,sha256=d_EJQYGhNdAEYSmRiv_RlyqpV-sCc_6_VGd5br7prTg,6322
-chatterer/examples/make_ppt.py,sha256=62I0DTyOuxirgHnO5WojFK7KQjoYKYYICgGTxgszL98,23565
-chatterer/examples/pdf_to_markdown.py,sha256=cCO2mXLXLfXLPtiVbQl1g4VI5Qklti8Udz8eNtL_srE,3670
-chatterer/examples/pdf_to_text.py,sha256=K8CmZ-E7SbUtdjutBMk80qWZXo21CcFrqvTf6pUTN5c,1847
-chatterer/examples/transcription_api.py,sha256=mj8kQKYL23ayYWzaO_THQtPtMLsU0pqGEVOiZb1nckQ,4255
-chatterer/examples/upstage_parser.py,sha256=UtGKt9UNqXqIoJlKpg6q1h7DI7LDujFqyKXnH0FsZVw,4236
-chatterer/examples/webpage_to_markdown.py,sha256=ZBmZ0AjPnETBpXn_RScUSLF6PGYJpdcaZzXbp8Zfack,3143
+chatterer/examples/anything_to_markdown.py,sha256=4O9ze7AIHcwEzvVmm5JMMKo_rVSFwhPL8MVHtfMLJ5Y,2734
+chatterer/examples/get_code_snippets.py,sha256=pz05JjhKaWAknVKlk1ftEEzpSG4-sqD9oa_gyIQoCAs,1911
+chatterer/examples/login_with_playwright.py,sha256=EhvJLaH5TD7bmDi12uP8YLd0fRhdjR-oyIkBHLi1Jjs,5988
+chatterer/examples/make_ppt.py,sha256=vsT_iL_jS2ami5VYrReLMQcD576FfZUH7913F7_As0A,23278
+chatterer/examples/pdf_to_markdown.py,sha256=Y83GfpmMApSvwbgNCw8CgFLeunYvZP0RCrgkvcXatGU,3479
+chatterer/examples/pdf_to_text.py,sha256=JhM_meogmvDmQZ31NqAgYd5Wx_WWKnt20V79g-uVEdo,1581
+chatterer/examples/transcription_api.py,sha256=WUs12qHH4616eLMQDHOiyVGxaXstTpgeE47djYyli6c,3897
+chatterer/examples/upstage_parser.py,sha256=TrfeSIiF0xklhFCknop22TIOVibI4CJ_UKj5-lD8c8E,3487
+chatterer/examples/webpage_to_markdown.py,sha256=DnZfQ-trXBiOiszA2tMlgadgKH-ObTi6l4gGloT-cQw,2846
 chatterer/strategies/__init__.py,sha256=SdOggbmHpw4f7Njwy-T8q64e91OLOUp1k0a0ozZd4qI,221
-chatterer/strategies/atom_of_thoughts.py,sha256=CygOCLu5vLk-fzY9O-iE3qLShfjD7iY40ks9jH4ULBM,40872
+chatterer/strategies/atom_of_thoughts.py,sha256=pUhqt47YlzBIVNRh0UebeBwuJ0J94Ge6yZgXxrsiDPE,40884
 chatterer/strategies/base.py,sha256=b2gMPqodp97OP1dkHfj0UqixjdjVhmTw_V5qJ7i2S6g,427
 chatterer/tools/__init__.py,sha256=m3PRK9H5vOhk-2gG9W2eg8CYBlEn-K9-eaulOu91bgo,1474
 chatterer/tools/caption_markdown_images.py,sha256=r4QajHYuL4mdyYQXP1vQcNmqKN8lxBf5y0VKELXILOI,15392
-chatterer/tools/convert_pdf_to_markdown.py,sha256=8VEnZiaZSDq5k5BGaJEaSaJpJrAxSeL-gc7s38Vf9Fg,14990
-chatterer/tools/convert_to_text.py,sha256=IWtSHBh8-bvEZekk9Vli8yK4Ufa_VezN9mpfKCUWvys,15443
-chatterer/tools/upstage_document_parser.py,sha256=Bn6dGwgCsCOvhA5GfTWcfJ9unKqyuXNMMwoqZLwYLYU,33103
+chatterer/tools/convert_pdf_to_markdown.py,sha256=Q5ln-_av2eor0A2LkQG7-IgyQKJ79wwrSOvv5Jncfso,18901
+chatterer/tools/convert_to_text.py,sha256=WHQ0Xj4Ri_jYbFjzTx3mjmvJ9U8bAv4wGaKEVC88Nlk,15457
+chatterer/tools/upstage_document_parser.py,sha256=CXslVYAHDK8EV8jtUAUWzf8rxU4qilSnW8_dhAxHOE8,33142
 chatterer/tools/webpage_to_markdown.py,sha256=ADH4sqM6iquJR7HU6umMQ5qO7EvcbNutuchXDpAcxAo,31961
 chatterer/tools/youtube.py,sha256=Hl2MMXJwwZ-i6_YAq0zh0rN4LHpYOb1Rt88P1gMjlLE,6081
 chatterer/tools/citation_chunking/__init__.py,sha256=gG7Fnkkp28UpcWMbfMY_4gqzZSZ8QzlhalHBoeoq7K0,82
@@ -35,10 +35,10 @@ chatterer/tools/citation_chunking/utils.py,sha256=M4pH2-UIE1VLzQLXDqjEe4L3Xcy0e0
 chatterer/utils/__init__.py,sha256=2v-lB2dqHgBlGcyaKKHc_hcyeH_AVoOddpr0STF7YAw,341
 chatterer/utils/base64_image.py,sha256=m_qAT3ERBiq8D-H4H9Z7rLfL31_BiPmV_m4uQ5XRLs0,11124
 chatterer/utils/bytesio.py,sha256=3MC2atOOFKo5YxuReo_y_t8Wem9p2Y1ahC5M2lGclwI,2618
-chatterer/utils/code_agent.py,sha256=A0IIgUAvW3lWMdJa8OZNKqmwdd5uuSvco-TxAN5-cek,10468
+chatterer/utils/code_agent.py,sha256=7ka_WRI4TQmZ5H46mjY3hI6RO_pxw6pg3LAxjgW4AbM,10495
 chatterer/utils/imghdr.py,sha256=6JhJMXD4MZ0dQolT2VM87YrRYm3hPf3RTEWnP4lYRVc,3842
-chatterer-0.1.19.dist-info/METADATA,sha256=F_g5KhtlpDxZqeMlDi2Wewt_fBPSJgC_gKPMlIJeC50,11826
-chatterer-0.1.19.dist-info/WHEEL,sha256=Nw36Djuh_5VDukK0H78QzOX-_FQEo6V37m3nkm96gtU,91
-chatterer-0.1.19.dist-info/entry_points.txt,sha256=KhxL2dctnZalnDSmPoB5dZBBa9hZpJETW3C5xkoRaW4,554
-chatterer-0.1.19.dist-info/top_level.txt,sha256=7nSQKP0bHxPRc7HyzdbKsJdkvPgYD0214o6slRizv9s,10
-chatterer-0.1.19.dist-info/RECORD,,
+chatterer-0.1.20.dist-info/METADATA,sha256=9EIDlz3bfnlo0YfskNaooTj0UgCTyq3UHwBjcul1ijs,11826
+chatterer-0.1.20.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
+chatterer-0.1.20.dist-info/entry_points.txt,sha256=KhxL2dctnZalnDSmPoB5dZBBa9hZpJETW3C5xkoRaW4,554
+chatterer-0.1.20.dist-info/top_level.txt,sha256=7nSQKP0bHxPRc7HyzdbKsJdkvPgYD0214o6slRizv9s,10
+chatterer-0.1.20.dist-info/RECORD,,

{chatterer-0.1.19.dist-info → chatterer-0.1.20.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.7.1)
+Generator: setuptools (80.8.0)
 Root-Is-Purelib: true
 Tag: py3-none-any