content-core 0.5.0__tar.gz → 0.5.1__tar.gz

{content_core-0.5.0 → content_core-0.5.1}/.gitignore

@@ -21,3 +21,4 @@ todo.md
 WIP/
 
 *.ignore
+.windsurfrules

content_core-0.5.1/Makefile

@@ -0,0 +1,16 @@
+.PHONY: tag test build-docs ruff
+
+tag:
+	@version=$$(grep '^version = ' pyproject.toml | sed 's/version = "\(.*\)"/\1/'); \
+	echo "Creating tag v$$version"; \
+	git tag "v$$version"; \
+	git push origin "v$$version"
+
+test:
+	uv run pytest -v
+    
+build-docs:
+	repomix . --include "**/*.py,**/*.yaml" --compress --style xml -o ai_docs/core.txt
+
+ruff:
+	ruff check . --fix

{content_core-0.5.0 → content_core-0.5.1}/PKG-INFO

@@ -1,10 +1,11 @@
 Metadata-Version: 2.4
 Name: content-core
-Version: 0.5.0
+Version: 0.5.1
 Summary: Extract what matters from any media source
 Author-email: LUIS NOVO <lfnovo@gmail.com>
 License-File: LICENSE
 Requires-Python: >=3.10
+Requires-Dist: ai-prompter>=0.2.3
 Requires-Dist: aiohttp>=3.11
 Requires-Dist: bs4>=0.0.2
 Requires-Dist: dicttoxml>=1.7.16

{content_core-0.5.0 → content_core-0.5.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "content-core"
-version = "0.5.0"
+version = "0.5.1"
 description = "Extract what matters from any media source"
 readme = "README.md"
 homepage = "https://github.com/lfnovo/content-core"
@@ -29,6 +29,7 @@ dependencies = [
     "langgraph>=0.3.29",
     "dicttoxml>=1.7.16",
     "validators>=0.34.0",
+    "ai-prompter>=0.2.3",
 ]
 
 [project.optional-dependencies]

{content_core-0.5.0 → content_core-0.5.1}/src/content_core/__init__.py

@@ -5,9 +5,12 @@ import os
 import sys
 from xml.etree import ElementTree as ET
 
-from dicttoxml import dicttoxml  # type: ignore
 from dotenv import load_dotenv
 
+load_dotenv()
+
+from dicttoxml import dicttoxml  # type: ignore
+
 from content_core.common import ProcessSourceInput
 from content_core.content.cleanup import cleanup_content
 from content_core.content.extraction import extract_content
@@ -18,7 +21,6 @@ from content_core.logging import configure_logging, logger
 extract = extract_content
 clean = cleanup_content
 
-load_dotenv()
 
 # Configure loguru logger using centralized configuration
 configure_logging(debug=False)
@@ -212,3 +214,5 @@ def csum():
 
 if __name__ == "__main__":
     ccore()
+if __name__ == "__main__":
+    ccore()

{content_core-0.5.0 → content_core-0.5.1}/src/content_core/notebooks/run.ipynb

@@ -305,7 +305,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -328,18 +328,18 @@
     }
    ],
    "source": [
-    "from content_core.config import set_extraction_engine, set_docling_output_format\n",
+    "# from content_core.config import set_extraction_engine, set_docling_output_format\n",
     "from content_core.content.extraction import extract_content\n",
     "\n",
-    "# 2) Turn on Docling\n",
-    "set_extraction_engine(\"docling\")\n",
+    "# # 2) Turn on Docling\n",
+    "# set_extraction_engine(\"docling\")\n",
     "\n",
-    "# 3) (Optionally) pick your format – markdown, html or json\n",
-    "set_docling_output_format(\"markdown\")\n",
+    "# # 3) (Optionally) pick your format – markdown, html or json\n",
+    "# set_docling_output_format(\"markdown\")\n",
     "\n",
     "# 4) Now extract exactly as before:\n",
     "result = await extract_content({\n",
-    "    \"file_path\": \"../../../tests/input_content/file.pdf\"\n",
+    "    \"file_path\": \"../../../tests/input_content/file.pdf\", \"engine\": \"docling\", \"output_format\": \"markdown\"\n",
     "})\n",
     "print(result.content)"
    ]

content_core-0.5.1/src/content_core/templated_message.py

@@ -0,0 +1,49 @@
+from typing import Dict, Optional, Union
+
+from ai_prompter import Prompter
+from esperanto import LanguageModel
+from esperanto.common_types import Message
+from pydantic import BaseModel, Field
+
+from content_core.models import ModelFactory
+
+
+class TemplatedMessageInput(BaseModel):
+    system_prompt_template: Optional[str] = None
+    system_prompt_text: Optional[str] = None
+    user_prompt_template: Optional[str] = None
+    user_prompt_text: Optional[str] = None
+    data: Optional[Union[Dict, BaseModel]] = Field(default_factory=lambda: {})
+    config: Dict = Field(
+        description="The config for the LLM",
+        default={
+            "temperature": 0,
+            "top_p": 1,
+            "max_tokens": 600,
+        },
+    )
+
+
+async def templated_message(
+    input: TemplatedMessageInput, model: Optional[LanguageModel] = None
+) -> str:
+    if not model:
+        model = ModelFactory.get_model("default_model")
+
+    msgs = []
+    if input.system_prompt_template or input.system_prompt_text:
+        system_prompt = Prompter(
+            prompt_template=input.system_prompt_template,
+            template_text=input.system_prompt_text,
+        ).render(data=input.data)
+        msgs.append(Message(role="system", content=system_prompt))
+
+    if input.user_prompt_template or input.user_prompt_text:
+        user_prompt = Prompter(
+            prompt_template=input.user_prompt_template,
+            template_text=input.user_prompt_text,
+        ).render(data=input.data)
+        msgs.append(Message(role="user", content=user_prompt))
+
+    result = await model.achat_complete(msgs)
+    return result.content

{content_core-0.5.0 → content_core-0.5.1}/uv.lock

@@ -23,6 +23,20 @@ resolution-markers = [
     "(python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_machine != 'x86_64' and platform_system == 'Linux') or (python_full_version >= '3.12.4' and platform_machine != 'x86_64' and platform_system != 'Darwin' and platform_system != 'Linux') or (python_full_version >= '3.12.4' and platform_machine != 'aarch64' and platform_system == 'Linux' and sys_platform != 'darwin') or (python_full_version >= '3.12.4' and platform_system != 'Darwin' and platform_system != 'Linux' and sys_platform != 'darwin')",
 ]
 
+[[package]]
+name = "ai-prompter"
+version = "0.2.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "jinja2" },
+    { name = "pip" },
+    { name = "pydantic" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/39/ff/cf13c31b88c06e11a1ffeed505601c167293b23d3e2e4e02adac93cc9300/ai_prompter-0.2.3.tar.gz", hash = "sha256:40f55c18f87df250a13f84d0cf7a4e8b31815a01f27666039386d6592849694b", size = 72955 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5f/11/9e3712b8393dbef152258c68617baec343040c3d08b372d77b57e51d8e5d/ai_prompter-0.2.3-py3-none-any.whl", hash = "sha256:e8c0becbb3c8bdff399e372830e2c0a3cc3292e02d67921e2b255871329ee477", size = 7345 },
+]
+
 [[package]]
 name = "aiohappyeyeballs"
 version = "2.6.1"
@@ -391,9 +405,10 @@ wheels = [
 
 [[package]]
 name = "content-core"
-version = "0.5.0"
+version = "0.5.1"
 source = { editable = "." }
 dependencies = [
+    { name = "ai-prompter" },
     { name = "aiohttp" },
     { name = "bs4" },
     { name = "dicttoxml" },
@@ -435,6 +450,7 @@ dev = [
 
 [package.metadata]
 requires-dist = [
+    { name = "ai-prompter", specifier = ">=0.2.3" },
     { name = "aiohttp", specifier = ">=3.11" },
     { name = "asciidoc", marker = "extra == 'docling'" },
     { name = "bs4", specifier = ">=0.0.2" },
@@ -2239,6 +2255,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/21/2c/5e05f58658cf49b6667762cca03d6e7d85cededde2caf2ab37b81f80e574/pillow-11.2.1-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:208653868d5c9ecc2b327f9b9ef34e0e42a4cdd172c2988fd81d62d2bc9bc044", size = 2674751 },
 ]
 
+[[package]]
+name = "pip"
+version = "25.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/70/53/b309b4a497b09655cb7e07088966881a57d082f48ac3cb54ea729fd2c6cf/pip-25.0.1.tar.gz", hash = "sha256:88f96547ea48b940a3a385494e181e29fb8637898f88d88737c5049780f196ea", size = 1950850 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c9/bc/b7db44f5f39f9d0494071bddae6880eb645970366d0a200022a1a93d57f5/pip-25.0.1-py3-none-any.whl", hash = "sha256:c46efd13b6aa8279f33f2864459c8ce587ea6a1a59ee20de055868d8f7688f7f", size = 1841526 },
+]
+
 [[package]]
 name = "platformdirs"
 version = "4.3.7"

content_core-0.5.0/.windsurfrules

@@ -1,13 +0,0 @@
-Also use uv as the package manager: uv run, uv sync, uv add.
-
-All documentation (code or readmes) must be in english.
-Whenever I ask you to tag and release, make sure to run `make test` as part of the process. 
-
-The full release process is: 
-- Run `make test` to make sure everything is working (if we changed any code or import)
-- Update version on pyproject.toml
-- Run `uv sync` to update the lock file
-- Commit all that's needed
-- Merge to main (if in a branch)
-- Tag the release
-- Push to GitHub

content_core-0.5.0/Makefile

@@ -1,8 +0,0 @@
-test:
-	uv run pytest -v
-    
-build-docs:
-	repomix . --include "**/*.py,**/*.yaml" --compress --style xml -o ai_docs/core.txt
-
-ruff:
-	ruff check . --fix

content_core-0.5.0/src/content_core/prompter.py

@@ -1,159 +0,0 @@
-"""
-A prompt management module using Jinja to generate complex prompts with simple templates.
-"""
-
-import os
-from dataclasses import dataclass
-from datetime import datetime
-from typing import Any, Dict, Optional, Union
-
-from dotenv import load_dotenv
-from jinja2 import Environment, FileSystemLoader, Template
-from langchain_core.prompts import ChatPromptTemplate
-from pydantic import BaseModel
-
-from content_core.logging import logger
-
-load_dotenv()
-
-prompt_path_default = os.path.join(
-    os.path.dirname(os.path.abspath(__file__)), "prompts"
-)
-prompt_path_custom = os.getenv("PROMPT_PATH")
-
-logger.debug(
-    f"Pasta de prompts personalizada: {prompt_path_custom if prompt_path_custom else 'Não definida'}"
-)
-logger.debug(f"Pasta de prompts padrão: {prompt_path_default}")
-
-env_custom = (
-    Environment(loader=FileSystemLoader(prompt_path_custom))
-    if prompt_path_custom and os.path.exists(prompt_path_custom)
-    else None
-)
-env_default = Environment(loader=FileSystemLoader(prompt_path_default))
-
-
-@dataclass
-class Prompter:
-    """
-    A class for managing and rendering prompt templates.
-
-    Attributes:
-        prompt_template (str, optional): The name of the prompt template file.
-        prompt_variation (str, optional): The variation of the prompt template.
-        prompt_text (str, optional): The raw prompt text.
-        template (Union[str, Template], optional): The Jinja2 template object.
-    """
-
-    prompt_template: Optional[str] = None
-    prompt_variation: Optional[str] = "default"
-    prompt_text: Optional[str] = None
-    template: Optional[Union[str, Template]] = None
-    parser: Optional[Any] = None
-
-    def __init__(self, prompt_template=None, prompt_text=None, parser=None):
-        """
-        Initialize the Prompter with either a template file or raw text.
-
-        Args:
-            prompt_template (str, optional): The name of the prompt template file.
-            prompt_text (str, optional): The raw prompt text.
-        """
-        self.prompt_template = prompt_template
-        self.prompt_text = prompt_text
-        self.parser = parser
-        self.setup()
-
-    def setup(self):
-        """
-        Set up the Jinja2 template based on the provided template file or text.
-        Raises:
-            ValueError: If neither prompt_template nor prompt_text is provided.
-        """
-        if self.prompt_template:
-            # Primeiro tenta carregar da pasta personalizada, se disponível
-            if env_custom:
-                try:
-                    self.template = env_custom.get_template(
-                        f"{self.prompt_template}.jinja"
-                    )
-                    logger.debug(
-                        f"Template {self.prompt_template} carregado da pasta personalizada"
-                    )
-                    return
-                except Exception as e:
-                    logger.debug(
-                        f"Template {self.prompt_template} não encontrado na pasta personalizada: {e}"
-                    )
-
-            # Se não encontrou na personalizada ou não há pasta personalizada, tenta a padrão
-            try:
-                self.template = env_default.get_template(
-                    f"{self.prompt_template}.jinja"
-                )
-                logger.debug(
-                    f"Template {self.prompt_template} carregado da pasta padrão"
-                )
-            except Exception as e:
-                raise ValueError(
-                    f"Template {self.prompt_template} não encontrado na pasta padrão: {e}"
-                )
-        elif self.prompt_text:
-            self.template = Template(self.prompt_text)
-        else:
-            raise ValueError("Prompter must have a prompt_template or prompt_text")
-
-        assert self.prompt_template or self.prompt_text, "Prompt is required"
-
-    def to_langchain(self):
-        if isinstance(self.template, str):
-            template_text = self.template
-        else:
-            # For file-based templates, read the raw content
-            template_path = os.path.join("prompts", f"{self.prompt_template}.jinja")
-            with open(template_path, "r") as f:
-                template_text = f.read()
-        return ChatPromptTemplate.from_template(template_text, template_format="jinja2")
-
-    @classmethod
-    def from_text(cls, text: str):
-        """
-        Create a Prompter instance from raw text, which can contain Jinja code.
-
-        Args:
-            text (str): The raw prompt text.
-
-        Returns:
-            Prompter: A new Prompter instance.
-        """
-
-        return cls(prompt_text=text)
-
-    def render(self, data: Optional[Union[Dict, BaseModel]] = {}) -> str:
-        """
-        Render the prompt template with the given data.
-
-        Args:
-            data (Union[Dict, BaseModel]): The data to be used in rendering the template.
-                Can be either a dictionary or a Pydantic BaseModel.
-
-        Returns:
-            str: The rendered prompt text.
-
-        Raises:
-            AssertionError: If the template is not defined or not a Jinja2 Template.
-        """
-        # Convert Pydantic model to dict if necessary
-        data_dict = data.model_dump() if isinstance(data, BaseModel) else data
-        # Create a new mutable dictionary with the original data
-        render_data = dict(data_dict)
-        render_data["current_time"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-        if self.parser:
-            render_data["format_instructions"] = self.parser.get_format_instructions()
-        assert self.template, "Prompter template is not defined"
-        assert isinstance(
-            self.template, Template
-        ), "Prompter template is not a Jinja2 Template"
-        return self.template.render(render_data)
-        return self.template.render(render_data)

content_core-0.5.0/src/content_core/templated_message.py

@@ -1,57 +0,0 @@
-from typing import Dict, Optional, Union
-
-from esperanto import LanguageModel
-from esperanto.common_types import Message
-from pydantic import BaseModel, Field
-
-from content_core.models import ModelFactory
-from content_core.prompter import Prompter
-
-
-class TemplatedMessageInput(BaseModel):
-    system_prompt_template: Optional[str] = ""
-    system_prompt_text: Optional[str] = ""
-    user_prompt_template: Optional[str] = ""
-    user_prompt_text: Optional[str] = ""
-    data: Optional[Union[Dict, BaseModel]] = Field(default_factory=lambda: {})
-    config: Dict = Field(
-        description="The config for the LLM",
-        default={
-            "temperature": 0,
-            "top_p": 1,
-            "max_tokens": 600,
-        },
-    )
-
-
-async def templated_message(
-    input: TemplatedMessageInput, model: Optional[LanguageModel] = None
-) -> str:
-    if not model:
-        model = ModelFactory.get_model('default_model')
-
-    msgs = []
-    if input.system_prompt_template or input.system_prompt_text:
-        msgs.append(
-            Message(
-                role="system",
-                content=Prompter(
-                    prompt_template=input.system_prompt_template,
-                    prompt_text=input.system_prompt_text,
-                ).render(data=input.data),
-            )
-        )
-
-    if input.user_prompt_template or input.user_prompt_text:
-        msgs.append(
-            Message(
-                role="user",
-                content=Prompter(
-                    prompt_template=input.user_prompt_template,
-                    prompt_text=input.user_prompt_text,
-                ).render(data=input.data),
-            )
-        )
-
-    result = await model.achat_complete(msgs)
-    return result.content