prompt-caller 0.0.1__py3-none-any.whl → 0.0.2__py3-none-any.whl

prompt_caller-0.0.2.dist-info/METADATA

@@ -0,0 +1,122 @@
+Metadata-Version: 2.1
+Name: prompt_caller
+Version: 0.0.2
+Summary: This package is responsible for calling prompts in a specific format. It uses LangChain and OpenAI API
+Author: Thiago Nepomuceno
+Author-email: thiago@neps.academy
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Description-Content-Type: text/markdown
+Requires-Dist: pyyaml>=6.0.2
+Requires-Dist: python-dotenv>=1.0.1
+Requires-Dist: Jinja2>=3.1.4
+Requires-Dist: langchain-openai>=0.1.23
+
+# PromptCaller
+
+**PromptCaller** is a Python package for calling prompts in a specific format, using LangChain and the OpenAI API. It enables users to load prompts from a template, render them with contextual data, and make structured requests to the OpenAI API.
+
+## Features
+
+- **Load prompts** from a `.prompt` file containing a YAML configuration and a message template.
+- **Render templates** using context and Jinja2.
+- **Parse prompt messages** written in a JSX-like format (`<system>`, `<user>`, `<assistant>`).
+- **Invoke prompts** using LangChain and OpenAI API, with support for structured output.
+- **Dynamically create Pydantic models** based on the expected structured output.
+
+## Installation
+
+To install the package, simply run:
+
+```bash
+pip install prompt-caller
+```
+
+You will also need an `.env` file that contains your OpenAI API key:
+
+```
+OPENAI_API_KEY=your_openai_api_key_here
+```
+
+## Usage
+
+1. **Define a prompt file:**
+
+Create a `.prompt` file in the `prompts` directory, e.g., `prompts/sample.prompt`:
+
+```yaml
+---
+model: gpt-4o-mini
+temperature: 0.7
+max_tokens: 512
+output:
+  result: "Final result of the expression"
+  explanation: "Explanation of the calculation"
+---
+<system>
+You are a helpful assistant.
+</system>
+
+<user>
+How much is {{expression}}?
+</user>
+```
+
+This `.prompt` file contains:
+
+- A YAML header for configuring the model and parameters.
+- A template body using Jinja2 to inject the context (like `{{ expression }}`).
+- Messages structured in a JSX-like format (`<system>`, `<user>`).
+
+2. **Load and call a prompt:**
+
+```python
+from prompt_caller import PromptCaller
+
+ai = PromptCaller()
+
+response = ai.call("sample", {"expression": "3+8/9"})
+
+print(response)
+```
+
+In this example:
+
+- The `expression` value `3+8/9` is injected into the user message.
+- The model will respond with both the result of the expression and an explanation, as specified in the `output` section of the prompt.
+
+## How It Works
+
+1. **\_loadPrompt:** Loads the prompt file, splits the YAML header from the body, and parses them.
+2. **\_renderTemplate:** Uses the Jinja2 template engine to render the body with the provided context.
+3. **\_parseJSXBody:** Parses the message body written in JSX-like tags to extract system and user messages.
+4. **call:** Invokes the OpenAI API with the parsed configuration and messages, and handles structured output via dynamic Pydantic models.
+
+## Build and Upload
+
+To build the distribution and upload it to a package repository like PyPI, follow these steps:
+
+1. **Build the distribution:**
+
+   Run the following command to create both source (`sdist`) and wheel (`bdist_wheel`) distributions:
+
+   ```bash
+   python setup.py sdist bdist_wheel
+   ```
+
+   This will generate the distribution files in the `dist/` directory.
+
+2. **Upload to PyPI using Twine:**
+
+   Use `twine` to securely upload the distribution to PyPI:
+
+   ```bash
+   twine upload dist/*
+   ```
+
+   Ensure you have configured your PyPI credentials before running this command. You can find more information on configuring credentials in the [Twine documentation](https://twine.readthedocs.io/).
+
+## License
+
+This project is licensed under the **Apache License 2.0**. You may use, modify, and distribute this software as long as you provide proper attribution and include the full text of the license in any distributed copies or derivative works.

{prompt_caller-0.0.1.dist-info → prompt_caller-0.0.2.dist-info}/RECORD

@@ -1,7 +1,7 @@
 prompt_caller/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 prompt_caller/__main__.py,sha256=dJ0dYtVmnhZuoV79R6YiAIta1ZkUKb-TEX4VEuYbgk0,139
 prompt_caller/prompt_caller.py,sha256=VmmMLiOWsTC-545ejXcfOP0neA3k4aDA2SLCYNGD2nI,2824
-prompt_caller-0.0.1.dist-info/METADATA,sha256=B8L0iifaUnM3idkMsLV_AE455LVTE51WMFwKKnuhdCI,625
-prompt_caller-0.0.1.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
-prompt_caller-0.0.1.dist-info/top_level.txt,sha256=iihiDRq-0VrKB8IKjxf7Lrtv-fLMq4tvgM4fH3x0I94,14
-prompt_caller-0.0.1.dist-info/RECORD,,
+prompt_caller-0.0.2.dist-info/METADATA,sha256=6uxqVskKCCs2ic4STEFERNGEjjzWPuBPHVBv1-AF5Qs,4040
+prompt_caller-0.0.2.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
+prompt_caller-0.0.2.dist-info/top_level.txt,sha256=iihiDRq-0VrKB8IKjxf7Lrtv-fLMq4tvgM4fH3x0I94,14
+prompt_caller-0.0.2.dist-info/RECORD,,

prompt_caller-0.0.1.dist-info/METADATA

@@ -1,21 +0,0 @@
-Metadata-Version: 2.1
-Name: prompt_caller
-Version: 0.0.1
-Summary: This package is responsible for calling prompts in a specific format. It uses LangChain and OpenAI API
-Author: Thiago Nepomuceno
-Author-email: thiago@neps.academy
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Description-Content-Type: text/markdown
-Requires-Dist: toml
-
-# Neps Academy AI
-
-This package is responsible for all Neps Academy features related to AI
-
-# Build and Upload
-
-python setup.py sdist bdist_wheel
-
-twine upload dist/\*