AutoRAG 0.3.0__tar.gz → 0.3.2__tar.gz

autorag-0.3.2/.dockerignore

@@ -0,0 +1,164 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+pytest.ini
+.DS_Store
+projects/tutorial_1
+!projects/tutorial_1/config.yaml

{autorag-0.3.0 → autorag-0.3.2}/.gitignore

@@ -159,3 +159,6 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 .idea/
 pytest.ini
+.DS_Store
+projects/tutorial_1
+!projects/tutorial_1/config.yaml

{autorag-0.3.0 → autorag-0.3.2}/AutoRAG.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: AutoRAG
-Version: 0.3.0
+Version: 0.3.2
 Summary: Automatically Evaluate RAG pipelines with your own data. Find optimal structure for new RAG product.
 Author-email: Marker-Inc <vkehfdl1@gmail.com>
 License:                                  Apache License
@@ -261,7 +261,7 @@ Requires-Dist: llama-index-retrievers-bm25
 Requires-Dist: streamlit
 Requires-Dist: gradio
 Requires-Dist: langchain-core>=0.3.0
-Requires-Dist: langchain_unstructured
+Requires-Dist: langchain-unstructured>=0.1.5
 Requires-Dist: langchain-upstage
 Requires-Dist: panel
 Requires-Dist: seaborn
@@ -290,7 +290,7 @@ Requires-Dist: AutoRAG[parse]; extra == "all"
 
 # AutoRAG
 
-RAG AutoML tool for automatically finds an optimal RAG pipeline for your data.
+RAG AutoML tool for automatically finding an optimal RAG pipeline for your data.
 
 ![Thumbnail](https://github.com/user-attachments/assets/6bab243d-a4b3-431a-8ac0-fe17336ab4de)
 
@@ -299,8 +299,8 @@ but you don’t know what pipeline is great for “your own data” and "your ow
 Making and evaluating all RAG modules is very time-consuming and hard to do.
 But without it, you will never know which RAG pipeline is the best for your own use-case.
 
-AutoRAG is a tool for finding optimal RAG pipeline for “your data.”
-You can evaluate various RAG modules automatically with your own evaluation data,
+AutoRAG is a tool for finding the optimal RAG pipeline for “your data.”
+You can evaluate various RAG modules automatically with your own evaluation data
 and find the best RAG pipeline for your own use-case.
 
 AutoRAG supports a simple way to evaluate many RAG module combinations.
@@ -329,6 +329,7 @@ You can see on [YouTube](https://youtu.be/2ojK8xjyXAU?feature=shared)
 # Index
 
 - [Quick Install](#quick-install)
+- [🐳 AutoRAG Docker Guide](#-autorag-docker-guide)
 - [Data Creation](#data-creation)
   - [Parsing](#1-parsing)
   - [Chunking](#2-chunking)
@@ -401,11 +402,11 @@ modules:
     chunk_method: Token
     chunk_size: 1024
     chunk_overlap: 24
-    add_file_name: english
+    add_file_name: en
 ```
 
 You can also use multiple Chunk modules at once.
-In this case, you need to use one corpus to create QA, and then map the rest of the corpus to QA Data.
+In this case, you need to use one corpus to create QA and then map the rest of the corpus to QA Data.
 If the chunk method is different, the retrieval_gt will be different, so we need to remap it to the QA dataset.
 
 #### Start Chunking
@@ -427,14 +428,14 @@ You can create QA dataset with just a few lines of code.
 import pandas as pd
 from llama_index.llms.openai import OpenAI
 
-from autorag.data.beta.filter.dontknow import dontknow_filter_rule_based
-from autorag.data.beta.generation_gt.llama_index_gen_gt import (
+from autorag.data.qa.filter.dontknow import dontknow_filter_rule_based
+from autorag.data.qa.generation_gt.llama_index_gen_gt import (
     make_basic_gen_gt,
     make_concise_gen_gt,
 )
-from autorag.data.beta.schema import Raw, Corpus
-from autorag.data.beta.query.llama_gen_query import factoid_query_gen
-from autorag.data.beta.sample import random_single_hop
+from autorag.data.qa.schema import Raw, Corpus
+from autorag.data.qa.query.llama_gen_query import factoid_query_gen
+from autorag.data.qa.sample import random_single_hop
 
 llm = OpenAI()
 raw_df = pd.read_parquet("your/path/to/corpus.parquet")
@@ -477,19 +478,87 @@ initial_qa.to_parquet('./qa.parquet', './corpus.parquet')
 
 ![rag_opt_gif](https://github.com/user-attachments/assets/55bd09cd-8420-4f6d-bc7d-0a66af288317)
 
+## 🐳 AutoRAG Docker Guide
+
+This guide provides a quick overview of building and running the AutoRAG Docker container for production, with instructions on setting up the environment for evaluation using your configuration and data paths.
+
+### 🚀 Building the Docker Image
+
+#### 1.Download dataset for [Turorial Step 1](https://colab.research.google.com/drive/19OEQXO_pHN6gnn2WdfPd4hjnS-4GurVd?usp=sharing)
+```bash
+python sample_dataset/eli5/load_eli5_dataset.py --save_path projects/tutorial_1
+```
+
+#### 2. Run `evaluate`
+> **Note**: This step may take a long time to complete and involves OpenAI API calls, which may cost approximately $0.30.
+
+```bash
+docker run --rm -it \
+  -v ~/.cache/huggingface:/root/.cache/huggingface \
+  -v $(pwd)/projects:/usr/src/app/projects \
+  -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+  autoraghq/autorag:all evaluate \
+  --config /usr/src/app/projects/tutorial_1/config.yaml \
+  --qa_data_path /usr/src/app/projects/tutorial_1/qa_test.parquet \
+  --corpus_data_path /usr/src/app/projects/tutorial_1/corpus.parquet \
+  --project_dir /usr/src/app/projects/tutorial_1/
+```
+
+
+#### 3. Run validate
+```bash
+docker run --rm -it \
+  -v ~/.cache/huggingface:/root/.cache/huggingface \
+  -v $(pwd)/projects:/usr/src/app/projects \
+  -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+  autoraghq/autorag:all validate \
+  --config /usr/src/app/projects/tutorial_1/config.yaml \
+  --qa_data_path /usr/src/app/projects/tutorial_1/qa_test.parquet \
+  --corpus_data_path /usr/src/app/projects/tutorial_1/corpus.parquet
+```
+
+
+#### 4. Run `dashboard`
+```bash
+docker run --rm -it \
+  -v ~/.cache/huggingface:/root/.cache/huggingface \
+  -v $(pwd)/projects:/usr/src/app/projects \
+  -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+  -p 8502:8502 \
+  autoraghq/autorag:all dashboard \
+    --trial_dir /usr/src/app/projects/tutorial_1/0
+```
+
+
+#### 4. Run `run_web`
+```bash
+docker run --rm -it \
+  -v ~/.cache/huggingface:/root/.cache/huggingface \
+  -v $(pwd)/projects:/usr/src/app/projects \
+  -e OPENAI_API_KEY=${OPENAI_API_KEY} \
+  -p 8501:8501 \
+  autoraghq/autorag:all run_web --trial_path ./projects/tutorial_1/0
+```
+
+#### Key Points :
+- **`-v ~/.cache/huggingface:/cache/huggingface`**: Mounts the host machine’s Hugging Face cache to `/cache/huggingface` in the container, enabling access to pre-downloaded models.
+- **`-e OPENAI_API_KEY: ${OPENAI_API_KEY}`**: Passes the `OPENAI_API_KEY` from your host environment.
+
+For more detailed instructions, refer to the [Docker Installation Guide](./docs/source/install.md#1-build-the-docker-image).
+
 ## Quick Start
 
 ### 1. Set YAML File
 
-First, you need to set the config yaml file for your RAG optimization.
+First, you need to set the config YAML file for your RAG optimization.
 
-You can get various config yaml files at [here](./sample_config).
-We highly recommend using pre-made config yaml files for starter.
+You can get various config YAML files at [here](./sample_config).
+We highly recommend using pre-made config YAML files for starter.
 
-If you want to make your own config yaml files, check out the [Config yaml file](#-create-your-own-config-yaml-file)
+If you want to make your own config YAML files, check out the [Config YAML file](#-create-your-own-config-yaml-file)
 section.
 
-Here is an example of the config yaml file to use `retrieval`, `prompt_maker`, and `generator` nodes.
+Here is an example of the config YAML file to use `retrieval`, `prompt_maker`, and `generator` nodes.
 
 ```yaml
 node_lines:
@@ -541,13 +610,13 @@ evaluator = Evaluator(qa_data_path='your/path/to/qa.parquet', corpus_data_path='
 evaluator.start_trial('your/path/to/config.yaml')
 ```
 
-or you can use command line interface
+or you can use the command line interface
 
 ```bash
 autorag evaluate --config your/path/to/default_config.yaml --qa_data_path your/path/to/qa.parquet --corpus_data_path your/path/to/corpus.parquet
 ```
 
-Once it is done, you can see several files and folders created at your current directory.
+Once it is done, you can see several files and folders created in your current directory.
 At the trial folder named to numbers (like 0),
 you can check `summary.csv` file that summarizes the evaluation results and the best RAG pipeline for your data.
 
@@ -556,7 +625,7 @@ at [here](https://docs.auto-rag.com/optimization/folder_structure.html).
 
 ### 3. Run Dashboard
 
-You can run dashboard to easily see the result.
+You can run a dashboard to easily see the result.
 
 ```bash
 autorag dashboard --trial_dir /your/path/to/trial_dir
@@ -568,14 +637,15 @@ autorag dashboard --trial_dir /your/path/to/trial_dir
 
 ### 4. Deploy your optimal RAG pipeline (for testing)
 
-### 4-1. Run as a CLI
+### 4-1. Run as a Code
 
-You can use a found optimal RAG pipeline right away with extracted yaml file.
+You can use an optimal RAG pipeline right away from the trial folder.
+The trial folder is the directory used in the running dashboard. (like 0, 1, 2, ...)
 
 ```python
 from autorag.deploy import Runner
 
-runner = Runner.from_yaml('your/path/to/pipeline.yaml')
+runner = Runner.from_trial_folder('/your/path/to/trial_dir')
 runner.run('your question')
 ```
 
@@ -583,12 +653,12 @@ runner.run('your question')
 
 You can run this pipeline as an API server.
 
-Check out API endpoint at [here](deploy/api_endpoint.md).
+Check out the API endpoint at [here](deploy/api_endpoint.md).
 
 ```python
 from autorag.deploy import Runner
 
-runner = Runner.from_yaml('your/path/to/pipeline.yaml')
+runner = Runner.from_trial_folder('/your/path/to/trial_dir')
 runner.run_api_server()
 ```
 
@@ -596,11 +666,13 @@ runner.run_api_server()
 autorag run_api --config_path your/path/to/pipeline.yaml --host 0.0.0.0 --port 8000
 ```
 
+The cli command uses extracted config YAML file. If you want to know it more, check out [here](https://docs.auto-rag.com/tutorial.html#extract-pipeline-and-evaluate-test-dataset).
+
 ### 4-3. Run as a Web Interface
 
 you can run this pipeline as a web interface.
 
-Check out web interface at [here](deploy/web.md).
+Check out the web interface at [here](deploy/web.md).
 
 ```bash
 autorag run_web --trial_path your/path/to/trial_path
@@ -611,7 +683,7 @@ autorag run_web --trial_path your/path/to/trial_path
 <img width="1491" alt="web_interface" src="https://github.com/Marker-Inc-Korea/AutoRAG/assets/96727832/f6b00353-f6bb-4d8f-8740-1c264c0acbb8">
 
 ## 📌 Supporting Data Creation Modules
-![Data Creation](https://github.com/user-attachments/assets/383876cc-0d02-4e5f-9528-87f36489640f)
+![Data Creation](https://github.com/user-attachments/assets/0e5872de-2892-46b4-9ecd-e395671e324c)
 
 - You can check our all Parsing Modules at [here](https://edai.notion.site/Supporting-Parse-Modules-e0b7579c7c0e4fb2963e408eeccddd75?pvs=4)
 - You can check our all Chunk Modules at [here](https://edai.notion.site/Supporting-Chunk-Modules-8db803dba2ec4cd0a8789659106e86a3?pvs=4)

{autorag-0.3.0 → autorag-0.3.2}/AutoRAG.egg-info/SOURCES.txt

@@ -1,9 +1,12 @@
+.dockerignore
 .gitignore
 .pre-commit-config.yaml
 CODE_OF_CONDUCT.md
 CONTRIBUTING.md
+Dockerfile
 LICENSE
 README.md
+docker-compose.yml
 pyproject.toml
 requirements.txt
 .github/FUNDING.yml
@@ -59,8 +62,13 @@ autorag/data/qa/__init__.py
 autorag/data/qa/extract_evidence.py
 autorag/data/qa/sample.py
 autorag/data/qa/schema.py
+autorag/data/qa/evolve/__init__.py
+autorag/data/qa/evolve/llama_index_query_evolve.py
+autorag/data/qa/evolve/openai_query_evolve.py
+autorag/data/qa/evolve/prompt.py
 autorag/data/qa/filter/__init__.py
 autorag/data/qa/filter/dontknow.py
+autorag/data/qa/filter/passage_dependency.py
 autorag/data/qa/filter/prompt.py
 autorag/data/qa/generation_gt/__init__.py
 autorag/data/qa/generation_gt/base.py
@@ -205,17 +213,13 @@ docs/source/_static/roadmap/cycle.png
 docs/source/_static/roadmap/merger.png
 docs/source/_static/roadmap/node_line_modular.png
 docs/source/_static/roadmap/policy.png
-docs/source/api_spec/autorag.data.beta.filter.rst
-docs/source/api_spec/autorag.data.beta.generation_gt.rst
-docs/source/api_spec/autorag.data.beta.query.rst
-docs/source/api_spec/autorag.data.beta.rst
-docs/source/api_spec/autorag.data.beta.schema.rst
 docs/source/api_spec/autorag.data.chunk.rst
 docs/source/api_spec/autorag.data.corpus.rst
 docs/source/api_spec/autorag.data.legacy.corpus.rst
 docs/source/api_spec/autorag.data.legacy.qacreation.rst
 docs/source/api_spec/autorag.data.legacy.rst
 docs/source/api_spec/autorag.data.parse.rst
+docs/source/api_spec/autorag.data.qa.evolve.rst
 docs/source/api_spec/autorag.data.qa.filter.rst
 docs/source/api_spec/autorag.data.qa.generation_gt.rst
 docs/source/api_spec/autorag.data.qa.query.rst
@@ -245,6 +249,7 @@ docs/source/data_creation/tutorial.md
 docs/source/data_creation/chunk/chunk.md
 docs/source/data_creation/chunk/langchain_chunk.md
 docs/source/data_creation/chunk/llama_index_chunk.md
+docs/source/data_creation/legacy/legacy.md
 docs/source/data_creation/legacy/ragas.md
 docs/source/data_creation/legacy/tutorial.md
 docs/source/data_creation/parse/clova.md
@@ -253,6 +258,7 @@ docs/source/data_creation/parse/llama_parse.md
 docs/source/data_creation/parse/parse.md
 docs/source/data_creation/parse/table_hybrid_parse.md
 docs/source/data_creation/qa_creation/answer_gen.md
+docs/source/data_creation/qa_creation/evolve.md
 docs/source/data_creation/qa_creation/filter.md
 docs/source/data_creation/qa_creation/qa_creation.md
 docs/source/data_creation/qa_creation/query_gen.md
@@ -309,6 +315,7 @@ docs/source/optimization/folder_structure.md
 docs/source/optimization/optimization.md
 docs/source/optimization/strategies.md
 docs/source/roadmap/modular_rag.md
+projects/tutorial_1/config.yaml
 sample_config/chunk/chunk_full.yaml
 sample_config/chunk/chunk_ko.yaml
 sample_config/chunk/simple_chunk.yaml
@@ -348,7 +355,7 @@ tests/autorag/data/chunk/test_chunk_base.py
 tests/autorag/data/chunk/test_chunk_run.py
 tests/autorag/data/chunk/test_langchain_chunk.py
 tests/autorag/data/chunk/test_llama_index_chunk.py
-tests/autorag/data/legacy/corpus/test_base.py
+tests/autorag/data/legacy/corpus/test_base_corpus_legacy.py
 tests/autorag/data/legacy/corpus/test_langchain.py
 tests/autorag/data/legacy/corpus/test_llama_index_corpus.py
 tests/autorag/data/legacy/qacreation/test_base_qacreation.py
@@ -364,7 +371,11 @@ tests/autorag/data/parse/test_table_hybrid_parse.py
 tests/autorag/data/qa/test_data_creation_piepline.py
 tests/autorag/data/qa/test_sample.py
 tests/autorag/data/qa/test_schema.py
+tests/autorag/data/qa/evolve/base_test_query_evolve.py
+tests/autorag/data/qa/evolve/test_llama_index_query_evolve.py
+tests/autorag/data/qa/evolve/test_openai_query_evolve.py
 tests/autorag/data/qa/filter/test_dontknow.py
+tests/autorag/data/qa/filter/test_passage_dependency.py
 tests/autorag/data/qa/generation_gt/base_test_generation_gt.py
 tests/autorag/data/qa/generation_gt/test_llama_index_gen_gt.py
 tests/autorag/data/qa/generation_gt/test_openai_gen_gt.py

{autorag-0.3.0 → autorag-0.3.2}/AutoRAG.egg-info/requires.txt

@@ -40,7 +40,7 @@ llama-index-retrievers-bm25
 streamlit
 gradio
 langchain-core>=0.3.0
-langchain_unstructured
+langchain-unstructured>=0.1.5
 langchain-upstage
 panel
 seaborn

autorag-0.3.2/Dockerfile

@@ -0,0 +1,45 @@
+# Base stage: Install dependencies
+FROM python:3.10-slim AS base
+
+# Install system dependencies
+RUN apt-get update && \
+    apt-get install -y \
+    build-essential \
+    gcc \
+    libssl-dev \
+    poppler-utils \
+    tesseract-ocr \
+    tesseract-ocr-eng \
+    tesseract-ocr-kor && \
+    rm -rf /var/lib/apt/lists/*
+
+# Set work directory
+WORKDIR /usr/src/app
+
+# Install Python dependencies
+RUN pip install --upgrade pip setuptools setuptools-scm
+COPY requirements.txt /usr/src/app/requirements.txt
+
+RUN pip install -r requirements.txt
+
+# Copy project files
+COPY . /usr/src/app
+RUN pip install -e ./
+
+# Test stage: Run tests if CI=true
+FROM base AS test
+
+# Install testing dependencies
+RUN pip install pytest pytest-xdist
+
+# Run tests if CI is set to true
+RUN pytest -o log_cli=true --log-cli-level=INFO -n auto tests
+
+# Production stage: Create final image for production
+FROM base AS production
+
+COPY projects /usr/src/app/projects
+
+# Set the entrypoint for the production application
+ENTRYPOINT ["python", "-m", "autorag.cli"]
+# ENTRYPOINT ["bash"]