llm-extractinator 0.1.0__tar.gz

llm_extractinator-0.1.0/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_extractinator-0.1.0/MANIFEST.in

@@ -0,0 +1,14 @@
+# Include essential metadata files
+include README.md
+include LICENSE
+include setup.cfg
+include pyproject.toml
+
+# Include package data
+recursive-include llm_extractinator *.txt *.json *.md
+
+# Exclude unnecessary files
+exclude *.pyc
+exclude *.pyo
+exclude __pycache__/
+exclude .DS_Store

llm_extractinator-0.1.0/PKG-INFO

@@ -0,0 +1,150 @@
+Metadata-Version: 2.1
+Name: llm_extractinator
+Version: 0.1.0
+Summary: A tool for extracting data efficiently
+Author: Luc Builtjes
+Author-email: Luc.Builtjes@radboudumc.nl
+License: Apache License 2.0
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas
+Requires-Dist: tqdm
+Requires-Dist: pydantic
+Requires-Dist: langchain-core
+Requires-Dist: langchain-huggingface
+Requires-Dist: langchain-chroma
+Requires-Dist: langchain-community
+Requires-Dist: langchain-ollama
+Requires-Dist: ollama
+
+
+# LLM Extractinator
+
+![Overview of the LLM Data Extractor](images/doofenshmirtz.jpg)
+
+> [!Important]
+> This tool is a prototype which is in active development and is still undergoing major changes. Please always check the results!
+
+
+---
+
+## Overview
+
+This project enables the efficient extraction of structured data from unstructured text using large language models (LLMs). It provides a flexible configuration system and supports a variety of tasks.
+
+### Tool Workflow
+
+![Overview of the LLM Data Extractor](images/overview.png)
+
+---
+
+## Setup Environment
+
+To set up the environment, run the following commands:
+
+```bash
+conda create --name=llm_extractinator python=3.12
+conda activate llm_extractinator
+
+pip install -e .
+```
+
+---
+
+## Setting Up Task Configuration
+
+Create a JSON file in the `tasks` folder for each task, following the naming convention:
+
+```bash
+TaskXXX_taskname.json
+```
+
+Where `XXX` is a 3-digit number, and `taskname` is a brief descriptor of the task.
+
+The JSON file should always include the following fields:
+
+- **Task**: The name of the task.
+- **Type**: The type of task.
+- **Description**: A detailed description of the task.
+- **Data_Path**: The filename of the data file in the data folder.
+- **Input_Field**: The column name containing the text data.
+- **Parser_Format**: The JSON format you want the output to be in. See `Task999_example.json` for an example.
+
+The following fields are only mandatory if you want to have the model automatically generate examples:
+
+- **Example_Path**: The path to data used for creating examples (only required if `num_examples > 0` when running the model).
+- **Label_Field**: The column name containing the ground truth labels (only required if `num_examples > 0`).
+
+---
+
+## Input Flags for `extractinate`
+
+The following input flags can be used to configure the behavior of the `extractinate` script:
+
+| Flag                      | Type          | Default Value        | Description                                                                 |
+|---------------------------|---------------|----------------------|-----------------------------------------------------------------------------|
+| `--task_id`               | `int`         | **Required**         | Task ID to generate examples for.                                           |
+| `--model_name`            | `str`         | `"mistral-nemo"`     | Name of the model to use for prediction tasks. See [https://ollama.com/search](https://ollama.com/search) for the options.                              |
+| `--num_examples`          | `int`         | `0`                  | Number of examples to generate for each task.                               |
+| `--n_runs`                | `int`         | `5`                  | Number of runs to perform.                                                  |
+| `--temperature`           | `float`       | `0.3`                | Temperature for text generation.                                            |
+| `--max_context_len`       | `int`         | `8192`               | Maximum context length for input text.                                      |
+| `--num_predict`           | `int`         | `1024`               | Maximum number of tokens to predict.                                        |
+| `--run_name`              | `Path`        | `"run"`              | Name of the run for logging purposes.                                       |
+| `--output_dir`            | `Path`        | `<project_root>/output` | Path to the directory for output files.                                      |
+| `--task_dir`              | `Path`        | `<project_root>/tasks` | Path to the directory containing task configuration files.                   |
+| `--log_dir`               | `Path`        | `<project_root>/output` | Path to the directory for log files.                                        |
+| `--data_dir`              | `Path`        | `<project_root>/data` | Path to the directory containing input data.                                 |
+| `--chunk_size`            | `int`         | `None`               | Number of examples to generate in a single chunk. When None, use dataset size as chunksize.|
+| `--translate`             | `bool`        | `False`              | Translate the generated examples to English.                                |
+
+---
+
+## Example `Task.json`
+
+Below is an example configuration file for a task:
+
+```json
+{
+    "Task": "Text Summarization",
+    "Type": "Summarization",
+    "Description": "Generate summaries for long-form text documents.",
+    "Data_Path": "data/documents.csv",
+    "Example_Path": "data/summaries_examples.csv",
+    "Input_Field": "text",
+    "Label_Field": "summary",
+    "Parser_Format": {
+        "summary": "string"
+    }
+}
+```
+
+---
+
+## Running the Extractor
+
+To run the data extraction process, use the following command:
+
+```bash
+extractinate --task_id 001 --model_name "mistral-nemo" --num_examples 0 --max_context_len 8192 --num_predict 8192 --translate
+```
+
+Customize the flags based on your task requirements.
+
+---
+
+## Output
+
+The output will be saved in the specified `--output_dir`. Ensure that the directory structure and paths specified in the `Task.json` file match your project's organization.
+
+For further details, check the logs in the directory specified by `--log_dir`.
+
+---
+
+## Enhancements and Contributions
+
+Feel free to enhance this project by improving configurations, adding more task types, or extending model compatibility. Open a pull request or file an issue for discussions!

llm_extractinator-0.1.0/README.md

@@ -0,0 +1,127 @@
+
+# LLM Extractinator
+
+![Overview of the LLM Data Extractor](images/doofenshmirtz.jpg)
+
+> [!Important]
+> This tool is a prototype which is in active development and is still undergoing major changes. Please always check the results!
+
+
+---
+
+## Overview
+
+This project enables the efficient extraction of structured data from unstructured text using large language models (LLMs). It provides a flexible configuration system and supports a variety of tasks.
+
+### Tool Workflow
+
+![Overview of the LLM Data Extractor](images/overview.png)
+
+---
+
+## Setup Environment
+
+To set up the environment, run the following commands:
+
+```bash
+conda create --name=llm_extractinator python=3.12
+conda activate llm_extractinator
+
+pip install -e .
+```
+
+---
+
+## Setting Up Task Configuration
+
+Create a JSON file in the `tasks` folder for each task, following the naming convention:
+
+```bash
+TaskXXX_taskname.json
+```
+
+Where `XXX` is a 3-digit number, and `taskname` is a brief descriptor of the task.
+
+The JSON file should always include the following fields:
+
+- **Task**: The name of the task.
+- **Type**: The type of task.
+- **Description**: A detailed description of the task.
+- **Data_Path**: The filename of the data file in the data folder.
+- **Input_Field**: The column name containing the text data.
+- **Parser_Format**: The JSON format you want the output to be in. See `Task999_example.json` for an example.
+
+The following fields are only mandatory if you want to have the model automatically generate examples:
+
+- **Example_Path**: The path to data used for creating examples (only required if `num_examples > 0` when running the model).
+- **Label_Field**: The column name containing the ground truth labels (only required if `num_examples > 0`).
+
+---
+
+## Input Flags for `extractinate`
+
+The following input flags can be used to configure the behavior of the `extractinate` script:
+
+| Flag                      | Type          | Default Value        | Description                                                                 |
+|---------------------------|---------------|----------------------|-----------------------------------------------------------------------------|
+| `--task_id`               | `int`         | **Required**         | Task ID to generate examples for.                                           |
+| `--model_name`            | `str`         | `"mistral-nemo"`     | Name of the model to use for prediction tasks. See [https://ollama.com/search](https://ollama.com/search) for the options.                              |
+| `--num_examples`          | `int`         | `0`                  | Number of examples to generate for each task.                               |
+| `--n_runs`                | `int`         | `5`                  | Number of runs to perform.                                                  |
+| `--temperature`           | `float`       | `0.3`                | Temperature for text generation.                                            |
+| `--max_context_len`       | `int`         | `8192`               | Maximum context length for input text.                                      |
+| `--num_predict`           | `int`         | `1024`               | Maximum number of tokens to predict.                                        |
+| `--run_name`              | `Path`        | `"run"`              | Name of the run for logging purposes.                                       |
+| `--output_dir`            | `Path`        | `<project_root>/output` | Path to the directory for output files.                                      |
+| `--task_dir`              | `Path`        | `<project_root>/tasks` | Path to the directory containing task configuration files.                   |
+| `--log_dir`               | `Path`        | `<project_root>/output` | Path to the directory for log files.                                        |
+| `--data_dir`              | `Path`        | `<project_root>/data` | Path to the directory containing input data.                                 |
+| `--chunk_size`            | `int`         | `None`               | Number of examples to generate in a single chunk. When None, use dataset size as chunksize.|
+| `--translate`             | `bool`        | `False`              | Translate the generated examples to English.                                |
+
+---
+
+## Example `Task.json`
+
+Below is an example configuration file for a task:
+
+```json
+{
+    "Task": "Text Summarization",
+    "Type": "Summarization",
+    "Description": "Generate summaries for long-form text documents.",
+    "Data_Path": "data/documents.csv",
+    "Example_Path": "data/summaries_examples.csv",
+    "Input_Field": "text",
+    "Label_Field": "summary",
+    "Parser_Format": {
+        "summary": "string"
+    }
+}
+```
+
+---
+
+## Running the Extractor
+
+To run the data extraction process, use the following command:
+
+```bash
+extractinate --task_id 001 --model_name "mistral-nemo" --num_examples 0 --max_context_len 8192 --num_predict 8192 --translate
+```
+
+Customize the flags based on your task requirements.
+
+---
+
+## Output
+
+The output will be saved in the specified `--output_dir`. Ensure that the directory structure and paths specified in the `Task.json` file match your project's organization.
+
+For further details, check the logs in the directory specified by `--log_dir`.
+
+---
+
+## Enhancements and Contributions
+
+Feel free to enhance this project by improving configurations, adding more task types, or extending model compatibility. Open a pull request or file an issue for discussions!

llm_extractinator-0.1.0/data_extractor/data_loader.py

@@ -0,0 +1,57 @@
+import json
+import os
+import re
+from pathlib import Path
+from typing import Tuple
+
+import pandas as pd
+
+
+class DataLoader:
+    def __init__(self, train_path, test_path) -> None:
+        if train_path is not None:
+            self.train_path = Path(train_path)
+        else:
+            self.train_path = None
+        self.test_path = Path(test_path)
+
+    def load_data(self) -> Tuple[pd.DataFrame, pd.DataFrame]:
+        if self.train_path is not None:
+            train = pd.read_json(self.train_path)
+        else:
+            train = None
+        test = pd.read_json(self.test_path)
+        return train, test
+
+
+class TaskLoader:
+    def __init__(self, folder_path, task_id):
+        self.folder_path = folder_path
+        self.task_id = task_id
+
+    def find_and_load_task(self):
+        # Regex pattern to match files like TaskXXX_name.json
+        pattern = re.compile(rf".*{self.task_id}.*\.json")
+
+        # List all files in the folder that match the pattern
+        matching_files = [f for f in os.listdir(self.folder_path) if pattern.match(f)]
+
+        # Check for exactly one match
+        if len(matching_files) == 0:
+            raise FileNotFoundError(
+                f"No file found matching Task{self.task_id:03}*.json"
+            )
+        elif len(matching_files) > 1:
+            raise RuntimeError(
+                f"Multiple files found matching Task{self.task_id:03}*.json"
+            )
+
+        # Load the JSON file
+        self.file_path = os.path.join(self.folder_path, matching_files[0])
+        with open(self.file_path, "r") as file:
+            data = json.load(file)
+
+        return data
+
+    def get_task_name(self):
+        return os.path.splitext(os.path.basename(self.file_path))[0]