content-core 0.1.1__py3-none-any.whl → 0.2.0__py3-none-any.whl

content_core/prompter.py

@@ -10,13 +10,27 @@ 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 loguru import logger
 from pydantic import BaseModel
 
 load_dotenv()
 
-prompt_path = "/Users/luisnovo/dev/projetos/content-core/prompts"
+prompt_path_default = os.path.join(
+    os.path.dirname(os.path.abspath(__file__)), "prompts"
+)
+prompt_path_custom = os.getenv("PROMPT_PATH")
 
-env = Environment(loader=FileSystemLoader(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
@@ -57,7 +71,33 @@ class Prompter:
             ValueError: If neither prompt_template nor prompt_text is provided.
         """
         if self.prompt_template:
-            self.template = env.get_template(f"{self.prompt_template}.jinja")
+            # 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:
@@ -105,11 +145,13 @@ class Prompter:
         """
         # Convert Pydantic model to dict if necessary
         data_dict = data.model_dump() if isinstance(data, BaseModel) else data
-        data_dict["current_time"] = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        # 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:
-            data_dict["format_instructions"] = self.parser.get_format_instructions()
+            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(data_dict)
+        assert isinstance(
+            self.template, Template
+        ), "Prompter template is not a Jinja2 Template"
+        return self.template.render(render_data)

content_core/prompts/content/cleanup.jinja

@@ -0,0 +1,16 @@
+# GOAL
+
+Adjust the content below to make it clean and readable:
+Remove repeated strings that do not add value to the text.
+
+Remove any content unrelated to the text itself (e.g., metadata, artifacts, or extraction errors).
+
+Format the output as unstructured but clear text.
+
+Do not add extra text, introductions, conclusions, or commentary—only rewrite the provided content as it is.
+
+Do not interpret, analyze, or alter the meaning, intent, or narrative of the text—just reformat it for clarity and readability.
+
+Do not change the text structure, do not write conclusions about it. Your only job is to make it readable. 
+
+Keep the text in its original language, regardless of what it is.

content_core/prompts/content/summarize.jinja

@@ -0,0 +1,25 @@
+You are an AI assistant for a personal study platform.
+
+In this platform, your user collects various articles and content from the Internet for reference and study.
+
+Your role is to summarize the selected content as densely as possible, helping the reader extract maximum value from it without reading the full text.
+Focus solely on the content's value, avoiding unnecessary comments or messages.
+
+The summary should be dense, rich in characters, and designed to create a powerful vector representation.
+If the user provided additional context, follow its instructions. Otherwise, summary the whole content.
+
+Do not return any acknowledgments or greetings—only the summary.
+
+CONTENT:
+
+{{ content }}
+
+{% if context %}
+CONTEXT:
+
+User has provided the aditional context for your task:
+{{context}}
+{% endif%}
+
+
+SUMMARY:

{content_core-0.1.1.dist-info → content_core-0.2.0.dist-info}/METADATA

@@ -1,11 +1,11 @@
 Metadata-Version: 2.4
 Name: content-core
-Version: 0.1.1
+Version: 0.2.0
 Summary: Extract what matters from any media source
 Author-email: LUIS NOVO <lfnovo@gmail.com>
 License-File: LICENSE
 Requires-Python: >=3.10
-Requires-Dist: aiohttp>=3.11.16
+Requires-Dist: aiohttp>=3.11
 Requires-Dist: bs4>=0.0.2
 Requires-Dist: dicttoxml>=1.7.16
 Requires-Dist: esperanto>=1.2.0
@@ -43,7 +43,7 @@ The primary goal of Content Core is to simplify the process of ingesting content
     *   Direct text strings.
     *   Web URLs (using robust extraction methods).
     *   Local files (including automatic transcription for video/audio files and parsing for text-based formats).
-*   **Intelligent Processing:** Applies appropriate extraction techniques based on the source type.
+*   **Intelligent Processing:** Applies appropriate extraction techniques based on the source type. See the [Processors Documentation](./docs/processors.md) for detailed information on how different content types are handled.
 *   **Content Cleaning (Optional):** Likely integrates with LLMs (via `prompter.py` and Jinja templates) to refine and clean the extracted content.
 *   **Asynchronous:** Built with `asyncio` for efficient I/O operations.
 
@@ -220,6 +220,20 @@ OPENAI_API_KEY=your-key-here
 GOOGLE_API_KEY=your-key-here
 ```
 
+### Custom Prompt Templates
+
+Content Core allows you to define custom prompt templates for content processing. By default, the library uses built-in prompts located in the `prompts` directory. However, you can create your own prompt templates and store them in a dedicated directory. To specify the location of your custom prompts, set the `PROMPT_PATH` environment variable in your `.env` file or system environment.
+
+Example `.env` with custom prompt path:
+
+```plaintext
+OPENAI_API_KEY=your-key-here
+GOOGLE_API_KEY=your-key-here
+PROMPT_PATH=/path/to/your/custom/prompts
+```
+
+When a prompt template is requested, Content Core will first look in the custom directory specified by `PROMPT_PATH` (if set and exists). If the template is not found there, it will fall back to the default built-in prompts. This allows you to override specific prompts while still using the default ones for others.
+
 ## Development
 
 To set up a development environment:

{content_core-0.1.1.dist-info → content_core-0.2.0.dist-info}/RECORD

@@ -1,6 +1,6 @@
 content_core/__init__.py,sha256=CAPVVm3mDl8dH3j7Pn7t7UJqdwwpNjy77SzF7acssFw,6352
 content_core/config.py,sha256=5nFWb-g7DG__OuxSvwK4yCFEC1YCKdE6-rX5Z7c6JSo,794
-content_core/prompter.py,sha256=aUm_Bz_pkQuXIMKB1Xe6OEE-y4AUNoNsfFy82fAU-Ss,4049
+content_core/prompter.py,sha256=oXDBww_V-_NR1rQvpEpZwf6NNBlsAMk-hj6yMdkKXRk,5729
 content_core/py.typed,sha256=pLuU3XTTeVpXo4UomOjcvAIQqOrzIotlWlJ3KFo2lxQ,154
 content_core/templated_message.py,sha256=NSttaX1jL5LYIDlJnabx7baDuySIFIPjFjAX5NZt9pM,1704
 content_core/common/__init__.py,sha256=SjDp-0QRjX9PMubyTjv77_GrUqm6eC4gBuXr593JVK4,525
@@ -14,7 +14,7 @@ content_core/content/extraction/__init__.py,sha256=TaYw6CAcG62GZfsJxeZ6VJDLP85BU
 content_core/content/extraction/graph.py,sha256=qrTEl9YDUJJJg7TbBqPjueSvV9oo4_WwAJ-VpWKOYec,4621
 content_core/content/summary/__init__.py,sha256=ReKCZWKfDtqlInKeh87Y1DEfiNzVWabGybEz3hS2FrI,114
 content_core/content/summary/core.py,sha256=BTzTYhB-5sQmvvDaxnnWwBYcVinMHcnG-fBApcf2cyg,517
-content_core/notebooks/run.ipynb,sha256=MmZGVl62b8S7FpsFPAUKbB7ndEtyFXY-JeihaeT5CII,375888
+content_core/notebooks/run.ipynb,sha256=s4mIIiYdMfTlutaVlsYjFGwwvVnoVF83UbGT9rgizCA,340220
 content_core/processors/audio.py,sha256=ox-ScigfbBrN9B4MCvdgbYn2d3GBYqf6His0HPrzXDs,3459
 content_core/processors/office.py,sha256=13qNAfqqLwXUT6HNmF8OnxjbfvkhnTRCPoVUctw4w1k,12139
 content_core/processors/pdf.py,sha256=yndt8EGvV5_IxcFbFp4lb4g9T84w6cJ4LPdiTduO7aM,5296
@@ -22,12 +22,14 @@ content_core/processors/text.py,sha256=MiXNILDKcLO5sWTzp-LNJ8yC764_gmUEvDB7GUd7W
 content_core/processors/url.py,sha256=LcDB_FcmJMcwqM75DX2ERXcOry98e63WEjwd6l8u3ho,6268
 content_core/processors/video.py,sha256=aEe3M_POENPwI1tK4mUNxSeGewsmjex7lvMmELdcQeo,5183
 content_core/processors/youtube.py,sha256=3DioyLZT-wHmLcJ-vnONjMdZ1qWpeuHhQtsZw2nIE5M,5784
+content_core/prompts/content/cleanup.jinja,sha256=elyjbm9O_AeOcxkG-kui5wjBIRiOQCicjm92I4NmoVA,693
+content_core/prompts/content/summarize.jinja,sha256=zLPbomfjA-tQZr-c_rOqvKhd55R8NN3Q2gLyLR1sKso,817
 content_core/tools/__init__.py,sha256=DuJmd7fE-NpDvLP8IW1XY5MUkAQcdks52rn2jk4N8jQ,231
 content_core/tools/cleanup.py,sha256=5IdKedsFyRQMdYzgFSKtsfyxJldbroXQXHesHICNENI,523
 content_core/tools/extract.py,sha256=-r2_jsuMMXyXxGVqWhh1ilNPo_UMYAbw3Pkp1FzPy5g,577
 content_core/tools/summarize.py,sha256=DPfeglLWB08q8SvHrsKpOKZ35XjduUDs2J02ISwjdj0,596
-content_core-0.1.1.dist-info/METADATA,sha256=U6Z7hfiSC83FCrX6zl7M_36L6As9CPKXXJ0T5QLQLFw,7372
-content_core-0.1.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-content_core-0.1.1.dist-info/entry_points.txt,sha256=9fGQUk6bxBVXj9PRwfWVPn54ClSEJV7J-KBLXtjOhQw,99
-content_core-0.1.1.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
-content_core-0.1.1.dist-info/RECORD,,
+content_core-0.2.0.dist-info/METADATA,sha256=fXtKo9M6oBAxKPDavDDtMRPyptAqgcK8Qi_PKR1xMTo,8390
+content_core-0.2.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+content_core-0.2.0.dist-info/entry_points.txt,sha256=9fGQUk6bxBVXj9PRwfWVPn54ClSEJV7J-KBLXtjOhQw,99
+content_core-0.2.0.dist-info/licenses/LICENSE,sha256=myj0z2T4qIkenCgLsRfx7Wk6UqCQNj5c7O14Qx4zpGg,1066
+content_core-0.2.0.dist-info/RECORD,,