llm_batch_helper 0.1.3__tar.gz

llm_batch_helper-0.1.3/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

llm_batch_helper-0.1.3/PKG-INFO

@@ -0,0 +1,282 @@
+Metadata-Version: 2.3
+Name: llm_batch_helper
+Version: 0.1.3
+Summary: A Python package that enables batch submission of prompts to LLM APIs, with built-in async capabilities and response caching.
+License: MIT
+Keywords: llm,openai,batch,async,ai,nlp,api
+Author: Tianyi Peng
+Author-email: tianyipeng95@gmail.com
+Requires-Python: >=3.11,<4.0
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Dist: httpx (>=0.24.0,<0.25.0)
+Requires-Dist: openai (>=1.0.0,<2.0.0)
+Requires-Dist: python-dotenv (>=1.0.0,<2.0.0)
+Requires-Dist: tenacity (>=8.0.0,<9.0.0)
+Requires-Dist: tqdm (>=4.65.0,<5.0.0)
+Project-URL: Homepage, https://github.com/TianyiPeng/LLM_batch_helper
+Project-URL: Repository, https://github.com/TianyiPeng/LLM_batch_helper
+Description-Content-Type: text/markdown
+
+# LLM Batch Helper
+
+A Python package that enables batch submission of prompts to LLM APIs, with built-in async capabilities and response caching.
+
+## Features
+
+- **Async Processing**: Submit multiple prompts concurrently for faster processing
+- **Response Caching**: Automatically cache responses to avoid redundant API calls
+- **Multiple Input Formats**: Support for both file-based and list-based prompts
+- **Provider Support**: Works with OpenAI API
+- **Retry Logic**: Built-in retry mechanism with exponential backoff
+- **Verification Callbacks**: Custom verification for response quality
+- **Progress Tracking**: Real-time progress bars for batch operations
+
+## Installation
+
+### For Users (Recommended)
+
+```bash
+# Install from PyPI
+pip install llm_batch_helper
+```
+
+### For Development
+
+```bash
+# Clone the repository
+git clone https://github.com/TianyiPeng/LLM_batch_helper.git
+cd llm_batch_helper
+
+# Install with Poetry
+poetry install
+
+# Activate the virtual environment
+poetry shell
+```
+
+## Quick Start
+
+### 1. Set up environment variables
+
+```bash
+# For OpenAI
+export OPENAI_API_KEY="your-openai-api-key"
+```
+
+### 2. Interactive Tutorial (Recommended)
+
+Check out the comprehensive Jupyter notebook [tutorial](https://github.com/TianyiPeng/LLM_batch_helper/blob/main/tutorials/llm_batch_helper_tutorial.ipynb).
+
+The tutorial covers all features with interactive examples!
+
+### 3. Basic usage
+
+```python
+import asyncio
+from llm_batch_helper import LLMConfig, process_prompts_batch
+
+async def main():
+    # Create configuration
+    config = LLMConfig(
+        model_name="gpt-4o-mini",
+        temperature=0.7,
+        max_tokens=100,
+        max_concurrent_requests=30 # number of concurrent requests with asyncIO
+    )
+    
+    # Process prompts
+    prompts = [
+        "What is the capital of France?",
+        "What is 2+2?",
+        "Who wrote 'Hamlet'?"
+    ]
+    
+    results = await process_prompts_batch(
+        config=config,
+        provider="openai",
+        prompts=prompts,
+        cache_dir="cache"
+    )
+    
+    # Print results
+    for prompt_id, response in results.items():
+        print(f"{prompt_id}: {response['response_text']}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Usage Examples
+
+### File-based Prompts
+
+```python
+import asyncio
+from llm_batch_helper import LLMConfig, process_prompts_batch
+
+async def process_files():
+    config = LLMConfig(
+        model_name="gpt-4o-mini",
+        temperature=0.7,
+        max_tokens=200
+    )
+    
+    # Process all .txt files in a directory
+    results = await process_prompts_batch(
+        config=config,
+        provider="openai",
+        input_dir="prompts",  # Directory containing .txt files
+        cache_dir="cache",
+        force=False  # Use cached responses if available
+    )
+    
+    return results
+
+asyncio.run(process_files())
+```
+
+### Custom Verification
+
+```python
+from llm_batch_helper import LLMConfig
+
+def verify_response(prompt_id, llm_response_data, original_prompt_text, **kwargs):
+    """Custom verification callback"""
+    response_text = llm_response_data.get("response_text", "")
+    
+    # Check minimum length
+    if len(response_text) < kwargs.get("min_length", 10):
+        return False
+    
+    # Check for specific keywords
+    if "error" in response_text.lower():
+        return False
+    
+    return True
+
+config = LLMConfig(
+    model_name="gpt-4o-mini",
+    temperature=0.7,
+    verification_callback=verify_response,
+    verification_callback_args={"min_length": 20}
+)
+```
+
+
+
+## API Reference
+
+### LLMConfig
+
+Configuration class for LLM requests.
+
+```python
+LLMConfig(
+    model_name: str,
+    temperature: float = 0.7,
+    max_tokens: Optional[int] = None,
+    system_instruction: Optional[str] = None,
+    max_retries: int = 10,
+    max_concurrent_requests: int = 5,
+    verification_callback: Optional[Callable] = None,
+    verification_callback_args: Optional[Dict] = None
+)
+```
+
+### process_prompts_batch
+
+Main function for batch processing of prompts.
+
+```python
+async def process_prompts_batch(
+    config: LLMConfig,
+    provider: str,  # "openai"
+    prompts: Optional[List[str]] = None,
+    input_dir: Optional[str] = None,
+    cache_dir: str = "llm_cache",
+    force: bool = False,
+    desc: str = "Processing prompts"
+) -> Dict[str, Dict[str, Any]]
+```
+
+### LLMCache
+
+Caching functionality for responses.
+
+```python
+cache = LLMCache(cache_dir="my_cache")
+
+# Check for cached response
+cached = cache.get_cached_response(prompt_id)
+
+# Save response to cache
+cache.save_response(prompt_id, prompt_text, response_data)
+
+# Clear all cached responses
+cache.clear_cache()
+```
+
+## Project Structure
+
+```
+llm_batch_helper/
+├── pyproject.toml              # Poetry configuration
+├── poetry.lock                 # Locked dependencies
+├── README.md                   # This file
+├── LICENSE                     # License file
+├── llm_batch_helper/          # Main package
+│   ├── __init__.py            # Package exports
+│   ├── cache.py               # Response caching
+│   ├── config.py              # Configuration classes
+│   ├── providers.py           # LLM provider implementations
+│   ├── input_handlers.py      # Input processing utilities
+│   └── exceptions.py          # Custom exceptions
+├── examples/                   # Usage examples
+│   ├── example.py             # Basic usage example
+│   ├── prompts/               # Sample prompt files
+│   └── llm_cache/             # Example cache directory
+└── tutorials/                 # Interactive tutorials
+    └── llm_batch_helper_tutorial.ipynb  # Comprehensive Jupyter notebook tutorial
+```
+
+## Supported Models
+
+### OpenAI
+- gpt-4o-mini
+- gpt-4o
+- gpt-4
+- gpt-3.5-turbo
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Add tests if applicable
+5. Run the test suite
+6. Submit a pull request
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Changelog
+
+### v0.1.0
+- Initial release
+- Support for OpenAI API
+- Async batch processing
+- Response caching
+- File and list-based input support
+- Custom verification callbacks
+- Poetry package management
+

llm_batch_helper-0.1.3/README.md

@@ -0,0 +1,253 @@
+# LLM Batch Helper
+
+A Python package that enables batch submission of prompts to LLM APIs, with built-in async capabilities and response caching.
+
+## Features
+
+- **Async Processing**: Submit multiple prompts concurrently for faster processing
+- **Response Caching**: Automatically cache responses to avoid redundant API calls
+- **Multiple Input Formats**: Support for both file-based and list-based prompts
+- **Provider Support**: Works with OpenAI API
+- **Retry Logic**: Built-in retry mechanism with exponential backoff
+- **Verification Callbacks**: Custom verification for response quality
+- **Progress Tracking**: Real-time progress bars for batch operations
+
+## Installation
+
+### For Users (Recommended)
+
+```bash
+# Install from PyPI
+pip install llm_batch_helper
+```
+
+### For Development
+
+```bash
+# Clone the repository
+git clone https://github.com/TianyiPeng/LLM_batch_helper.git
+cd llm_batch_helper
+
+# Install with Poetry
+poetry install
+
+# Activate the virtual environment
+poetry shell
+```
+
+## Quick Start
+
+### 1. Set up environment variables
+
+```bash
+# For OpenAI
+export OPENAI_API_KEY="your-openai-api-key"
+```
+
+### 2. Interactive Tutorial (Recommended)
+
+Check out the comprehensive Jupyter notebook [tutorial](https://github.com/TianyiPeng/LLM_batch_helper/blob/main/tutorials/llm_batch_helper_tutorial.ipynb).
+
+The tutorial covers all features with interactive examples!
+
+### 3. Basic usage
+
+```python
+import asyncio
+from llm_batch_helper import LLMConfig, process_prompts_batch
+
+async def main():
+    # Create configuration
+    config = LLMConfig(
+        model_name="gpt-4o-mini",
+        temperature=0.7,
+        max_tokens=100,
+        max_concurrent_requests=30 # number of concurrent requests with asyncIO
+    )
+    
+    # Process prompts
+    prompts = [
+        "What is the capital of France?",
+        "What is 2+2?",
+        "Who wrote 'Hamlet'?"
+    ]
+    
+    results = await process_prompts_batch(
+        config=config,
+        provider="openai",
+        prompts=prompts,
+        cache_dir="cache"
+    )
+    
+    # Print results
+    for prompt_id, response in results.items():
+        print(f"{prompt_id}: {response['response_text']}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
+
+## Usage Examples
+
+### File-based Prompts
+
+```python
+import asyncio
+from llm_batch_helper import LLMConfig, process_prompts_batch
+
+async def process_files():
+    config = LLMConfig(
+        model_name="gpt-4o-mini",
+        temperature=0.7,
+        max_tokens=200
+    )
+    
+    # Process all .txt files in a directory
+    results = await process_prompts_batch(
+        config=config,
+        provider="openai",
+        input_dir="prompts",  # Directory containing .txt files
+        cache_dir="cache",
+        force=False  # Use cached responses if available
+    )
+    
+    return results
+
+asyncio.run(process_files())
+```
+
+### Custom Verification
+
+```python
+from llm_batch_helper import LLMConfig
+
+def verify_response(prompt_id, llm_response_data, original_prompt_text, **kwargs):
+    """Custom verification callback"""
+    response_text = llm_response_data.get("response_text", "")
+    
+    # Check minimum length
+    if len(response_text) < kwargs.get("min_length", 10):
+        return False
+    
+    # Check for specific keywords
+    if "error" in response_text.lower():
+        return False
+    
+    return True
+
+config = LLMConfig(
+    model_name="gpt-4o-mini",
+    temperature=0.7,
+    verification_callback=verify_response,
+    verification_callback_args={"min_length": 20}
+)
+```
+
+
+
+## API Reference
+
+### LLMConfig
+
+Configuration class for LLM requests.
+
+```python
+LLMConfig(
+    model_name: str,
+    temperature: float = 0.7,
+    max_tokens: Optional[int] = None,
+    system_instruction: Optional[str] = None,
+    max_retries: int = 10,
+    max_concurrent_requests: int = 5,
+    verification_callback: Optional[Callable] = None,
+    verification_callback_args: Optional[Dict] = None
+)
+```
+
+### process_prompts_batch
+
+Main function for batch processing of prompts.
+
+```python
+async def process_prompts_batch(
+    config: LLMConfig,
+    provider: str,  # "openai"
+    prompts: Optional[List[str]] = None,
+    input_dir: Optional[str] = None,
+    cache_dir: str = "llm_cache",
+    force: bool = False,
+    desc: str = "Processing prompts"
+) -> Dict[str, Dict[str, Any]]
+```
+
+### LLMCache
+
+Caching functionality for responses.
+
+```python
+cache = LLMCache(cache_dir="my_cache")
+
+# Check for cached response
+cached = cache.get_cached_response(prompt_id)
+
+# Save response to cache
+cache.save_response(prompt_id, prompt_text, response_data)
+
+# Clear all cached responses
+cache.clear_cache()
+```
+
+## Project Structure
+
+```
+llm_batch_helper/
+├── pyproject.toml              # Poetry configuration
+├── poetry.lock                 # Locked dependencies
+├── README.md                   # This file
+├── LICENSE                     # License file
+├── llm_batch_helper/          # Main package
+│   ├── __init__.py            # Package exports
+│   ├── cache.py               # Response caching
+│   ├── config.py              # Configuration classes
+│   ├── providers.py           # LLM provider implementations
+│   ├── input_handlers.py      # Input processing utilities
+│   └── exceptions.py          # Custom exceptions
+├── examples/                   # Usage examples
+│   ├── example.py             # Basic usage example
+│   ├── prompts/               # Sample prompt files
+│   └── llm_cache/             # Example cache directory
+└── tutorials/                 # Interactive tutorials
+    └── llm_batch_helper_tutorial.ipynb  # Comprehensive Jupyter notebook tutorial
+```
+
+## Supported Models
+
+### OpenAI
+- gpt-4o-mini
+- gpt-4o
+- gpt-4
+- gpt-3.5-turbo
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Add tests if applicable
+5. Run the test suite
+6. Submit a pull request
+
+## License
+
+This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+
+## Changelog
+
+### v0.1.0
+- Initial release
+- Support for OpenAI API
+- Async batch processing
+- Response caching
+- File and list-based input support
+- Custom verification callbacks
+- Poetry package management

llm_batch_helper-0.1.3/llm_batch_helper/__init__.py

@@ -0,0 +1,15 @@
+from .cache import LLMCache
+from .config import LLMConfig
+from .input_handlers import get_prompts, read_prompt_files, read_prompt_list
+from .providers import process_prompts_batch
+
+__version__ = "0.1.1"
+
+__all__ = [
+    "LLMCache",
+    "LLMConfig",
+    "get_prompts",
+    "process_prompts_batch",
+    "read_prompt_files",
+    "read_prompt_list",
+]

llm_batch_helper-0.1.3/llm_batch_helper/cache.py

@@ -0,0 +1,34 @@
+import json
+from pathlib import Path
+from typing import Any, Dict, Optional
+
+
+class LLMCache:
+    def __init__(self, cache_dir: str = "llm_cache"):
+        self.cache_dir = Path(cache_dir)
+        self.cache_dir.mkdir(parents=True, exist_ok=True)
+
+    def _get_cache_path(self, prompt_id: str) -> Path:
+        """Generate cache file path based on prompt_id."""
+        return self.cache_dir / f"{prompt_id}.json"
+
+    def get_cached_response(self, prompt_id: str) -> Optional[Dict[str, Any]]:
+        """Retrieve cached response if it exists."""
+        cache_path = self._get_cache_path(prompt_id)
+        if cache_path.exists():
+            with open(cache_path, "r") as f:
+                return json.load(f)
+        return None
+
+    def save_response(self, prompt_id: str, prompt: str, response: Dict[str, Any]) -> None:
+        """Save response to cache."""
+        cache_path = self._get_cache_path(prompt_id)
+        cache_data = {"prompt_input": prompt, "llm_response": response}
+        with open(cache_path, "w") as f:
+            json.dump(cache_data, f, indent=2)
+
+    def clear_cache(self) -> None:
+        """Clear all cached responses."""
+        if self.cache_dir.exists():
+            for file in self.cache_dir.glob("*.json"):
+                file.unlink()

llm_batch_helper-0.1.3/llm_batch_helper/config.py

@@ -0,0 +1,32 @@
+from typing import Callable, Dict, Optional
+
+# System instruction for Gemini
+SYSTEM_INSTRUCTION = """You are a helpful AI assistant. """
+
+
+class LLMConfig:
+    def __init__(
+        self,
+        model_name: str,
+        temperature: float = 0.7,
+        max_tokens: Optional[int] = None,
+        system_instruction: Optional[str] = None,
+        max_retries: int = 10,  # Max retries for the combined LLM call + Verification
+        max_concurrent_requests: int = 5,
+        verification_callback: Optional[Callable[..., bool]] = None,
+        verification_callback_args: Optional[Dict] = None,
+        max_completion_tokens: Optional[int] = None,
+    ):
+        self.model_name = model_name
+        self.temperature = temperature
+        self.max_tokens = max_tokens
+        self.max_completion_tokens = max_completion_tokens
+        if self.max_tokens and not self.max_completion_tokens:
+            self.max_completion_tokens = self.max_tokens
+        self.system_instruction = system_instruction or SYSTEM_INSTRUCTION
+        self.max_retries = max_retries
+        self.max_concurrent_requests = max_concurrent_requests
+        self.verification_callback = verification_callback
+        self.verification_callback_args = (
+            verification_callback_args if verification_callback_args is not None else {}
+        )

llm_batch_helper-0.1.3/llm_batch_helper/exceptions.py

@@ -0,0 +1,7 @@
+class VerificationFailedError(Exception):
+    """Custom exception for when verification callback fails."""
+
+    def __init__(self, message, prompt_id, llm_response_data=None):
+        super().__init__(message)
+        self.prompt_id = prompt_id
+        self.llm_response_data = llm_response_data

llm_batch_helper-0.1.3/llm_batch_helper/input_handlers.py

@@ -0,0 +1,84 @@
+import hashlib
+from pathlib import Path
+from typing import Any, Dict, List, Tuple, Union
+
+
+def read_prompt_files(input_dir: str) -> List[Tuple[str, str]]:
+    """Read all text files from input directory and return as (filename, content) pairs.
+
+    Args:
+        input_dir: Path to directory containing prompt files
+
+    Returns:
+        List of (prompt_id, prompt_text) tuples where prompt_id is the filename without extension
+    """
+    input_path = Path(input_dir)
+    if not input_path.exists():
+        raise ValueError(f"Input directory {input_dir} does not exist")
+
+    prompts = []
+    for file_path in input_path.glob("*.txt"):
+        with open(file_path, "r") as f:
+            content = f.read().strip()
+            # Use filename without extension as prompt_id
+            prompt_id = file_path.stem
+            prompts.append((prompt_id, content))
+
+    if not prompts:
+        raise ValueError(f"No .txt files found in {input_dir}")
+
+    return prompts
+
+
+def read_prompt_list(
+    input_source: List[Union[str, Tuple[str, str], Dict[str, Any]]],
+) -> List[Tuple[str, str]]:
+    """Read prompts from a list of various formats.
+
+    Args:
+        input_source: List of prompts in any of these formats:
+            - str: The prompt text (will use hash as ID)
+            - tuple: (prompt_id, prompt_text)
+            - dict: {"id": prompt_id, "text": prompt_text}
+
+    Returns:
+        List of (prompt_id, prompt_text) tuples
+    """
+    prompts = []
+    for item in input_source:
+        if isinstance(item, str):
+            # String format: use hash as ID
+            prompt_id = hashlib.sha256(item.encode()).hexdigest()[:32]
+            prompt_text = item
+        elif isinstance(item, tuple) and len(item) == 2:
+            # Tuple format: (prompt_id, prompt_text)
+            prompt_id, prompt_text = item
+        elif isinstance(item, dict) and "id" in item and "text" in item:
+            # Dict format: {"id": prompt_id, "text": prompt_text}
+            prompt_id = item["id"]
+            prompt_text = item["text"]
+        else:
+            raise ValueError(f"Invalid prompt format: {item}")
+        prompts.append((prompt_id, prompt_text))
+    return prompts
+
+
+def get_prompts(
+    input_source: Union[str, List[Union[str, Tuple[str, str], Dict[str, Any]]]],
+) -> List[Tuple[str, str]]:
+    """Get prompts from either a directory or a list.
+
+    Args:
+        input_source: Either:
+            - str: Path to directory containing prompt files
+            - List: List of prompts in various formats (string, tuple, or dict)
+
+    Returns:
+        List of (prompt_id, prompt_text) tuples
+    """
+    if isinstance(input_source, str):
+        return read_prompt_files(input_source)
+    elif isinstance(input_source, list):
+        return read_prompt_list(input_source)
+    else:
+        raise ValueError(f"Invalid input source type: {type(input_source)}")

llm_batch_helper-0.1.3/llm_batch_helper/providers.py

@@ -0,0 +1,232 @@
+import asyncio
+import os
+from typing import Any, Dict, List, Optional, Tuple, Union
+
+import httpx
+import openai
+from dotenv import load_dotenv
+from tenacity import retry, retry_if_exception_type, stop_after_attempt, wait_exponential
+from tqdm.asyncio import tqdm_asyncio
+
+from .cache import LLMCache
+from .config import LLMConfig
+from .input_handlers import get_prompts
+
+load_dotenv()
+
+
+@retry(
+    stop=stop_after_attempt(5),
+    wait=wait_exponential(multiplier=1, min=4, max=60),
+    retry=retry_if_exception_type(
+        (
+            ConnectionError,
+            TimeoutError,
+            openai.APITimeoutError,
+            openai.APIConnectionError,
+            openai.RateLimitError,
+            openai.APIError,
+        )
+    ),
+    reraise=True,
+)
+async def _get_openai_response_direct(
+    prompt: str, config: LLMConfig
+) -> Dict[str, Union[str, Dict]]:
+    api_key = os.environ.get("OPENAI_API_KEY")
+    if not api_key:
+        raise ValueError("OPENAI_API_KEY environment variable not set")
+
+    async with httpx.AsyncClient(timeout=1000.0) as client:
+        aclient = openai.AsyncOpenAI(api_key=api_key, http_client=client)
+        messages = [
+            {"role": "system", "content": config.system_instruction},
+            {"role": "user", "content": prompt},
+        ]
+
+        response = await aclient.chat.completions.create(
+            model=config.model_name,
+            messages=messages,
+            temperature=config.temperature,
+            max_completion_tokens=config.max_completion_tokens,
+        )
+        usage_details = {
+            "prompt_token_count": response.usage.prompt_tokens,
+            "completion_token_count": response.usage.completion_tokens,
+            "total_token_count": response.usage.total_tokens,
+        }
+        return {
+            "response_text": response.choices[0].message.content,
+            "usage_details": usage_details,
+        }
+
+async def get_llm_response_with_internal_retry(
+    prompt_id: str,
+    prompt: str,
+    config: LLMConfig,
+    provider: str,
+    cache: Optional[LLMCache] = None,
+    force: bool = False,
+) -> Dict[str, Union[str, Dict]]:
+    # Check cache first if available and not forcing regeneration
+    if cache and not force:
+        cached_response = cache.get_cached_response(prompt_id)
+        if cached_response:
+            return cached_response["llm_response"]
+
+    try:
+        if provider.lower() == "openai":
+            response = await _get_openai_response_direct(prompt, config)
+        else:
+            raise ValueError(f"Unsupported provider: {provider}")
+
+        # Cache the response if cache is available
+        if cache and "error" not in response:
+            cache.save_response(prompt_id, prompt, response)
+
+        return response
+    except Exception as e:
+        return {
+            "error": f"LLM API call failed after internal retries: {e!s}",
+            "provider": provider,
+        }
+
+
+async def process_prompts_batch(
+    prompts: Optional[List[Union[str, Tuple[str, str], Dict[str, Any]]]] = None,
+    input_dir: Optional[str] = None,
+    config: LLMConfig = None,
+    provider: str = "openai",
+    desc: str = "Processing prompts",
+    cache_dir: Optional[str] = None,
+    force: bool = False,
+) -> Dict[str, Dict[str, Union[str, Dict]]]:
+    """Process a batch of prompts through the LLM.
+
+    Args:
+        prompts: Optional list of prompts in any supported format (string, tuple, or dict)
+        input_dir: Optional path to directory containing prompt files
+        config: LLM configuration
+        provider: LLM provider to use ("openai" or "gemini")
+        desc: Description for progress bar
+        cache_dir: Optional directory for caching responses
+        force: If True, force regeneration even if cached response exists
+
+    Returns:
+        Dict mapping prompt IDs to their responses
+
+    Note:
+        Either prompts or input_dir must be provided, but not both.
+    """
+    if prompts is None and input_dir is None:
+        raise ValueError("Either prompts or input_dir must be provided")
+    if prompts is not None and input_dir is not None:
+        raise ValueError("Cannot specify both prompts and input_dir")
+
+    # Get prompts from either source
+    if input_dir is not None:
+        prompts = get_prompts(input_dir)
+    else:
+        prompts = get_prompts(prompts)
+
+    # Create semaphore for concurrent requests
+    semaphore = asyncio.Semaphore(config.max_concurrent_requests)
+
+    # Process prompts
+    results = {}
+    tasks = [
+        _process_single_prompt_attempt_with_verification(
+            prompt_id, prompt_text, config, provider, semaphore, cache_dir, force
+        )
+        for prompt_id, prompt_text in prompts
+    ]
+
+    for future in tqdm_asyncio(asyncio.as_completed(tasks), total=len(tasks), desc=desc):
+        prompt_id, response_data = await future
+        results[prompt_id] = response_data
+
+    return results
+
+
+async def _process_single_prompt_attempt_with_verification(
+    prompt_id: str,
+    prompt_text: str,
+    config: LLMConfig,
+    provider: str,
+    semaphore: asyncio.Semaphore,
+    cache_dir: Optional[str] = None,
+    force: bool = False,
+):
+    """Process a single prompt with verification and caching."""
+    async with semaphore:
+        # Check cache first if cache_dir is provided
+        if cache_dir and not force:
+            cache = LLMCache(cache_dir)
+            cached_response = cache.get_cached_response(prompt_id)
+            if cached_response is not None:
+                # Verify response if callback provided
+                cached_response_data = cached_response["llm_response"]
+                if config.verification_callback:
+                    verified = await asyncio.to_thread(
+                        config.verification_callback,
+                        prompt_id,
+                        cached_response_data,
+                        prompt_text,
+                        **config.verification_callback_args,
+                    )
+                    if verified:
+                        return prompt_id, {**cached_response_data, "from_cache": True}
+
+        # Process the prompt
+        last_exception_details = None
+        for attempt in range(config.max_retries):
+            try:
+                # Get LLM response
+                llm_response_data = await get_llm_response_with_internal_retry(
+                    prompt_id, prompt_text, config, provider
+                )
+
+                if "error" in llm_response_data:
+                    last_exception_details = llm_response_data
+                    continue
+
+                # Verify response if callback provided
+                if config.verification_callback:
+                    verified = await asyncio.to_thread(
+                        config.verification_callback,
+                        prompt_id,
+                        llm_response_data,
+                        prompt_text,
+                        **config.verification_callback_args,
+                    )
+                    if not verified:
+                        last_exception_details = {
+                            "error": f"Verification failed on attempt {attempt + 1}",
+                            "prompt_id": prompt_id,
+                            "llm_response_data": llm_response_data,
+                        }
+                        if attempt == config.max_retries - 1:
+                            return prompt_id, last_exception_details
+                        await asyncio.sleep(min(2 * 2**attempt, 30))
+                        continue
+
+                # Save to cache if cache_dir provided
+                if cache_dir:
+                    cache = LLMCache(cache_dir)
+                    cache.save_response(prompt_id, prompt_text, llm_response_data)
+
+                return prompt_id, llm_response_data
+
+            except Exception as e:
+                last_exception_details = {
+                    "error": f"Unexpected error: {e!s}",
+                    "prompt_id": prompt_id,
+                }
+                if attempt == config.max_retries - 1:
+                    return prompt_id, last_exception_details
+                await asyncio.sleep(min(2 * 2**attempt, 30))
+                continue
+
+        return prompt_id, last_exception_details or {
+            "error": f"Exhausted all {config.max_retries} retries for {prompt_id}"
+        }

llm_batch_helper-0.1.3/pyproject.toml

@@ -0,0 +1,59 @@
+[tool.poetry]
+name = "llm_batch_helper"
+version = "0.1.3"
+description = "A Python package that enables batch submission of prompts to LLM APIs, with built-in async capabilities and response caching."
+authors = ["Tianyi Peng <tianyipeng95@gmail.com>"]
+readme = "README.md"
+license = "MIT"
+homepage = "https://github.com/TianyiPeng/LLM_batch_helper"
+repository = "https://github.com/TianyiPeng/LLM_batch_helper"
+keywords = ["llm", "openai", "batch", "async", "ai", "nlp", "api"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+packages = [{include = "llm_batch_helper"}]
+
+[tool.poetry.dependencies]
+python = "^3.11"
+httpx = "^0.24.0"
+openai = "^1.0.0"
+python-dotenv = "^1.0.0"
+tenacity = "^8.0.0"
+tqdm = "^4.65.0"
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^7.0.0"
+black = "^23.0.0"
+isort = "^5.12.0"
+flake8 = "^6.0.0"
+mypy = "^1.0.0"
+jupyter = "^1.0.0"
+twine = "^6.1.0"
+ipython = "^9.4.0"
+ipykernel = "^6.29.5"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.black]
+line-length = 88
+target-version = ['py38']
+
+[tool.isort]
+profile = "black"
+line_length = 88
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = true