AutoRAG 0.3.12__tar.gz → 0.3.16__tar.gz

{autorag-0.3.12 → autorag-0.3.16}/.gitignore

@@ -162,6 +162,3 @@ pytest.ini
 .DS_Store
 projects/tutorial_1
 !projects/tutorial_1/config.yaml
-
-# Visual Studio Code
-.vscode/

autorag-0.3.16/AutoRAG.egg-info/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.4
+Name: AutoRAG
+Version: 0.3.16
+Summary: Automatically Evaluate RAG pipelines with your own data. Find optimal structure for new RAG product.
+Author-email: Marker-Inc <vkehfdl1@gmail.com>
+Project-URL: Homepage, https://github.com/Marker-Inc-Korea/AutoRAG
+Keywords: RAG,AutoRAG,autorag,rag-evaluation,evaluation,rag-auto,AutoML,AutoML-RAG
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic==2.9.2
+Requires-Dist: numpy==1.26.4
+Requires-Dist: pandas>=2.2.3
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: tiktoken>=0.9.0
+Requires-Dist: openai>=1.90.0
+Requires-Dist: rank_bm25>=0.2.2
+Requires-Dist: pyyaml>=6.0.2
+Requires-Dist: pyarrow>=20.0.0
+Requires-Dist: fastparquet>=2024.11.0
+Requires-Dist: sacrebleu>=2.5.1
+Requires-Dist: evaluate>=0.4.4
+Requires-Dist: rouge_score>=0.1.2
+Requires-Dist: rich>=14.0.0
+Requires-Dist: click>=8.2.1
+Requires-Dist: cohere>=5.8.0
+Requires-Dist: tokenlog>=0.0.2
+Requires-Dist: aiohttp>=3.12.13
+Requires-Dist: voyageai>=0.3.2
+Requires-Dist: mixedbread-ai>=2.2.6
+Requires-Dist: scikit-learn>=1.7.0
+Requires-Dist: emoji>=2.14.1
+Requires-Dist: fastapi>=0.115.13
+Requires-Dist: banks>=2.1.2
+Requires-Dist: grpcio<1.68.0,>=1.66.2
+Requires-Dist: grpcio-health-checking<1.68.0,>=1.66.2
+Requires-Dist: grpcio-status<1.68.0,>=1.66.2
+Requires-Dist: grpcio-tools<1.68.0,>=1.66.2
+Requires-Dist: pymilvus>=2.6.0b0
+Requires-Dist: chromadb>=1.0.0
+Requires-Dist: weaviate-client>=4.15.2
+Requires-Dist: pinecone[grpc]
+Requires-Dist: couchbase>=4.4.0
+Requires-Dist: qdrant-client>=1.12.1
+Requires-Dist: quart>=0.20.0
+Requires-Dist: pyngrok>=7.2.11
+Requires-Dist: llama-index>=0.12.42
+Requires-Dist: llama-index-core>=0.12.42
+Requires-Dist: llama-index-readers-file>=0.4.9
+Requires-Dist: llama-index-embeddings-openai>=0.3.1
+Requires-Dist: llama-index-embeddings-ollama>=0.6.0
+Requires-Dist: llama-index-embeddings-openai-like>=0.1.1
+Requires-Dist: llama-index-llms-openai>=0.4.7
+Requires-Dist: llama-index-llms-openai-like>=0.4.0
+Requires-Dist: llama-index-retrievers-bm25>=0.5.2
+Requires-Dist: llama-index-llms-bedrock>=0.3.8
+Requires-Dist: streamlit>=1.46.0
+Requires-Dist: gradio>=5.34.2
+Requires-Dist: langchain-core==0.2.43
+Requires-Dist: langchain-unstructured==0.1.2
+Requires-Dist: langchain-upstage==0.1.5
+Requires-Dist: langchain-community==0.2.19
+Requires-Dist: langsmith==0.1.147
+Requires-Dist: panel>=1.7.1
+Requires-Dist: seaborn>=0.13.2
+Requires-Dist: ipykernel>=6.29.5
+Requires-Dist: ipywidgets>=8.1.7
+Requires-Dist: ipywidgets_bokeh>=1.6.0
+Provides-Extra: ko
+Requires-Dist: kiwipiepy>=0.18.0; extra == "ko"
+Requires-Dist: konlpy>=0.6.0; extra == "ko"
+Provides-Extra: parse
+Requires-Dist: PyMuPDF>=1.26.1; extra == "parse"
+Requires-Dist: pdfminer.six>=20250506; extra == "parse"
+Requires-Dist: pdfplumber>=0.11.7; extra == "parse"
+Requires-Dist: jq>=1.9.1; extra == "parse"
+Requires-Dist: unstructured[pdf]>=0.17.2; extra == "parse"
+Requires-Dist: PyPDF2==2.12.1; extra == "parse"
+Requires-Dist: pdf2image>=1.17.0; extra == "parse"
+Provides-Extra: ja
+Requires-Dist: sudachipy>=0.6.8; extra == "ja"
+Requires-Dist: sudachidict_core; extra == "ja"
+Provides-Extra: gpu
+Requires-Dist: torch>=2.7.1; extra == "gpu"
+Requires-Dist: sentencepiece>=0.2.0; extra == "gpu"
+Requires-Dist: bert_score>=0.3.13; extra == "gpu"
+Requires-Dist: optimum[nncf,openvino]>=1.26.1; extra == "gpu"
+Requires-Dist: peft>=0.15.2; extra == "gpu"
+Requires-Dist: llmlingua>=0.2.2; extra == "gpu"
+Requires-Dist: FlagEmbedding>=1.2.11; extra == "gpu"
+Requires-Dist: sentence-transformers>=4.1.0; extra == "gpu"
+Requires-Dist: transformers>=4.51.3; extra == "gpu"
+Requires-Dist: llama-index-llms-ollama>=0.6.0; extra == "gpu"
+Requires-Dist: llama-index-embeddings-huggingface>=0.5.4; extra == "gpu"
+Requires-Dist: llama-index-llms-huggingface>=0.5.0; extra == "gpu"
+Requires-Dist: onnxruntime>=1.22.0; extra == "gpu"
+Provides-Extra: all
+Requires-Dist: AutoRAG[gpu]; extra == "all"
+Requires-Dist: AutoRAG[ko]; extra == "all"
+Requires-Dist: AutoRAG[parse]; extra == "all"
+Requires-Dist: AutoRAG[ja]; extra == "all"

autorag-0.3.16/AutoRAG.egg-info/SOURCES.txt

@@ -0,0 +1,224 @@
+.dockerignore
+.gitignore
+Dockerfile.base
+Dockerfile.gpu
+build_and_push.sh
+docker-compose.yml
+pyproject.toml
+uv.lock
+AutoRAG.egg-info/PKG-INFO
+AutoRAG.egg-info/SOURCES.txt
+AutoRAG.egg-info/dependency_links.txt
+AutoRAG.egg-info/entry_points.txt
+AutoRAG.egg-info/requires.txt
+AutoRAG.egg-info/top_level.txt
+autorag/VERSION
+autorag/__init__.py
+autorag/chunker.py
+autorag/cli.py
+autorag/dashboard.py
+autorag/evaluator.py
+autorag/node_line.py
+autorag/parser.py
+autorag/strategy.py
+autorag/support.py
+autorag/validator.py
+autorag/web.py
+autorag/data/__init__.py
+autorag/data/chunk/__init__.py
+autorag/data/chunk/base.py
+autorag/data/chunk/langchain_chunk.py
+autorag/data/chunk/llama_index_chunk.py
+autorag/data/chunk/run.py
+autorag/data/legacy/__init__.py
+autorag/data/legacy/corpus/__init__.py
+autorag/data/legacy/corpus/langchain.py
+autorag/data/legacy/corpus/llama_index.py
+autorag/data/legacy/qacreation/__init__.py
+autorag/data/legacy/qacreation/base.py
+autorag/data/legacy/qacreation/llama_index.py
+autorag/data/legacy/qacreation/llama_index_default_prompt.txt
+autorag/data/legacy/qacreation/ragas.py
+autorag/data/legacy/qacreation/simple.py
+autorag/data/parse/__init__.py
+autorag/data/parse/base.py
+autorag/data/parse/clova.py
+autorag/data/parse/langchain_parse.py
+autorag/data/parse/llamaparse.py
+autorag/data/parse/run.py
+autorag/data/parse/table_hybrid_parse.py
+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
+autorag/data/qa/generation_gt/llama_index_gen_gt.py
+autorag/data/qa/generation_gt/openai_gen_gt.py
+autorag/data/qa/generation_gt/prompt.py
+autorag/data/qa/query/__init__.py
+autorag/data/qa/query/llama_gen_query.py
+autorag/data/qa/query/openai_gen_query.py
+autorag/data/qa/query/prompt.py
+autorag/data/utils/__init__.py
+autorag/data/utils/util.py
+autorag/deploy/__init__.py
+autorag/deploy/api.py
+autorag/deploy/base.py
+autorag/deploy/gradio.py
+autorag/deploy/swagger.yml
+autorag/embedding/__init__.py
+autorag/embedding/base.py
+autorag/evaluation/__init__.py
+autorag/evaluation/generation.py
+autorag/evaluation/retrieval.py
+autorag/evaluation/retrieval_contents.py
+autorag/evaluation/util.py
+autorag/evaluation/metric/__init__.py
+autorag/evaluation/metric/deepeval_prompt.py
+autorag/evaluation/metric/generation.py
+autorag/evaluation/metric/retrieval.py
+autorag/evaluation/metric/retrieval_contents.py
+autorag/evaluation/metric/util.py
+autorag/evaluation/metric/g_eval_prompts/coh_detailed.txt
+autorag/evaluation/metric/g_eval_prompts/con_detailed.txt
+autorag/evaluation/metric/g_eval_prompts/flu_detailed.txt
+autorag/evaluation/metric/g_eval_prompts/rel_detailed.txt
+autorag/nodes/__init__.py
+autorag/nodes/util.py
+autorag/nodes/generator/__init__.py
+autorag/nodes/generator/base.py
+autorag/nodes/generator/llama_index_llm.py
+autorag/nodes/generator/openai_llm.py
+autorag/nodes/generator/run.py
+autorag/nodes/generator/vllm.py
+autorag/nodes/generator/vllm_api.py
+autorag/nodes/passageaugmenter/__init__.py
+autorag/nodes/passageaugmenter/base.py
+autorag/nodes/passageaugmenter/pass_passage_augmenter.py
+autorag/nodes/passageaugmenter/prev_next_augmenter.py
+autorag/nodes/passageaugmenter/run.py
+autorag/nodes/passagecompressor/__init__.py
+autorag/nodes/passagecompressor/base.py
+autorag/nodes/passagecompressor/longllmlingua.py
+autorag/nodes/passagecompressor/pass_compressor.py
+autorag/nodes/passagecompressor/refine.py
+autorag/nodes/passagecompressor/run.py
+autorag/nodes/passagecompressor/tree_summarize.py
+autorag/nodes/passagefilter/__init__.py
+autorag/nodes/passagefilter/base.py
+autorag/nodes/passagefilter/pass_passage_filter.py
+autorag/nodes/passagefilter/percentile_cutoff.py
+autorag/nodes/passagefilter/recency.py
+autorag/nodes/passagefilter/run.py
+autorag/nodes/passagefilter/similarity_percentile_cutoff.py
+autorag/nodes/passagefilter/similarity_threshold_cutoff.py
+autorag/nodes/passagefilter/threshold_cutoff.py
+autorag/nodes/passagereranker/__init__.py
+autorag/nodes/passagereranker/base.py
+autorag/nodes/passagereranker/cohere.py
+autorag/nodes/passagereranker/colbert.py
+autorag/nodes/passagereranker/flag_embedding.py
+autorag/nodes/passagereranker/flag_embedding_llm.py
+autorag/nodes/passagereranker/flashrank.py
+autorag/nodes/passagereranker/jina.py
+autorag/nodes/passagereranker/koreranker.py
+autorag/nodes/passagereranker/mixedbreadai.py
+autorag/nodes/passagereranker/monot5.py
+autorag/nodes/passagereranker/openvino.py
+autorag/nodes/passagereranker/pass_reranker.py
+autorag/nodes/passagereranker/rankgpt.py
+autorag/nodes/passagereranker/run.py
+autorag/nodes/passagereranker/sentence_transformer.py
+autorag/nodes/passagereranker/time_reranker.py
+autorag/nodes/passagereranker/upr.py
+autorag/nodes/passagereranker/voyageai.py
+autorag/nodes/passagereranker/tart/__init__.py
+autorag/nodes/passagereranker/tart/modeling_enc_t5.py
+autorag/nodes/passagereranker/tart/tart.py
+autorag/nodes/passagereranker/tart/tokenization_enc_t5.py
+autorag/nodes/promptmaker/__init__.py
+autorag/nodes/promptmaker/base.py
+autorag/nodes/promptmaker/fstring.py
+autorag/nodes/promptmaker/long_context_reorder.py
+autorag/nodes/promptmaker/run.py
+autorag/nodes/promptmaker/window_replacement.py
+autorag/nodes/queryexpansion/__init__.py
+autorag/nodes/queryexpansion/base.py
+autorag/nodes/queryexpansion/hyde.py
+autorag/nodes/queryexpansion/multi_query_expansion.py
+autorag/nodes/queryexpansion/pass_query_expansion.py
+autorag/nodes/queryexpansion/query_decompose.py
+autorag/nodes/queryexpansion/run.py
+autorag/nodes/retrieval/__init__.py
+autorag/nodes/retrieval/base.py
+autorag/nodes/retrieval/bm25.py
+autorag/nodes/retrieval/hybrid_cc.py
+autorag/nodes/retrieval/hybrid_rrf.py
+autorag/nodes/retrieval/run.py
+autorag/nodes/retrieval/vectordb.py
+autorag/schema/__init__.py
+autorag/schema/base.py
+autorag/schema/metricinput.py
+autorag/schema/module.py
+autorag/schema/node.py
+autorag/utils/__init__.py
+autorag/utils/preprocess.py
+autorag/utils/util.py
+autorag/vectordb/__init__.py
+autorag/vectordb/base.py
+autorag/vectordb/chroma.py
+autorag/vectordb/couchbase.py
+autorag/vectordb/milvus.py
+autorag/vectordb/pinecone.py
+autorag/vectordb/qdrant.py
+autorag/vectordb/weaviate.py
+sample_config/chunk/chunk_full.yaml
+sample_config/chunk/chunk_ko.yaml
+sample_config/chunk/simple_chunk.yaml
+sample_config/parse/all_files_full.yaml
+sample_config/parse/file_types_full.yaml
+sample_config/parse/parse_hybird.yaml
+sample_config/parse/parse_ko.yaml
+sample_config/parse/parse_multimodal.yaml
+sample_config/parse/parse_ocr.yaml
+sample_config/parse/simple_parse.yaml
+sample_config/rag/extracted_sample.yaml
+sample_config/rag/full.yaml
+sample_config/rag/english/gpu/compact_local.yaml
+sample_config/rag/english/gpu/compact_openai.yaml
+sample_config/rag/english/gpu/full.yaml
+sample_config/rag/english/gpu/half.yaml
+sample_config/rag/english/gpu_api/compact.yaml
+sample_config/rag/english/gpu_api/full.yaml
+sample_config/rag/english/gpu_api/half.yaml
+sample_config/rag/english/non_gpu/compact.yaml
+sample_config/rag/english/non_gpu/full.yaml
+sample_config/rag/english/non_gpu/half.yaml
+sample_config/rag/english/non_gpu/simple_bedrock.yaml
+sample_config/rag/english/non_gpu/simple_local.yaml
+sample_config/rag/english/non_gpu/simple_ollama.yaml
+sample_config/rag/english/non_gpu/simple_openai.yaml
+sample_config/rag/korean/gpu/compact_korean.yaml
+sample_config/rag/korean/gpu/full_korean.yaml
+sample_config/rag/korean/gpu/half_korean.yaml
+sample_config/rag/korean/gpu_api/compact_korean.yaml
+sample_config/rag/korean/gpu_api/full_korean.yaml
+sample_config/rag/korean/gpu_api/half_korean.yaml
+sample_config/rag/korean/non_gpu/compact_korean.yaml
+sample_config/rag/korean/non_gpu/full_korean.yaml
+sample_config/rag/korean/non_gpu/half_korean.yaml
+sample_config/rag/korean/non_gpu/simple_korean.yaml
+sample_dataset/README.md
+sample_dataset/eli5/load_eli5_dataset.py
+sample_dataset/hotpotqa/load_hotpotqa_dataset.py
+sample_dataset/msmarco/load_msmarco_dataset.py
+sample_dataset/triviaqa/load_triviaqa_dataset.py

autorag-0.3.16/AutoRAG.egg-info/requires.txt

@@ -0,0 +1,96 @@
+pydantic==2.9.2
+numpy==1.26.4
+pandas>=2.2.3
+tqdm>=4.67.1
+tiktoken>=0.9.0
+openai>=1.90.0
+rank_bm25>=0.2.2
+pyyaml>=6.0.2
+pyarrow>=20.0.0
+fastparquet>=2024.11.0
+sacrebleu>=2.5.1
+evaluate>=0.4.4
+rouge_score>=0.1.2
+rich>=14.0.0
+click>=8.2.1
+cohere>=5.8.0
+tokenlog>=0.0.2
+aiohttp>=3.12.13
+voyageai>=0.3.2
+mixedbread-ai>=2.2.6
+scikit-learn>=1.7.0
+emoji>=2.14.1
+fastapi>=0.115.13
+banks>=2.1.2
+grpcio<1.68.0,>=1.66.2
+grpcio-health-checking<1.68.0,>=1.66.2
+grpcio-status<1.68.0,>=1.66.2
+grpcio-tools<1.68.0,>=1.66.2
+pymilvus>=2.6.0b0
+chromadb>=1.0.0
+weaviate-client>=4.15.2
+pinecone[grpc]
+couchbase>=4.4.0
+qdrant-client>=1.12.1
+quart>=0.20.0
+pyngrok>=7.2.11
+llama-index>=0.12.42
+llama-index-core>=0.12.42
+llama-index-readers-file>=0.4.9
+llama-index-embeddings-openai>=0.3.1
+llama-index-embeddings-ollama>=0.6.0
+llama-index-embeddings-openai-like>=0.1.1
+llama-index-llms-openai>=0.4.7
+llama-index-llms-openai-like>=0.4.0
+llama-index-retrievers-bm25>=0.5.2
+llama-index-llms-bedrock>=0.3.8
+streamlit>=1.46.0
+gradio>=5.34.2
+langchain-core==0.2.43
+langchain-unstructured==0.1.2
+langchain-upstage==0.1.5
+langchain-community==0.2.19
+langsmith==0.1.147
+panel>=1.7.1
+seaborn>=0.13.2
+ipykernel>=6.29.5
+ipywidgets>=8.1.7
+ipywidgets_bokeh>=1.6.0
+
+[all]
+AutoRAG[gpu]
+AutoRAG[ko]
+AutoRAG[parse]
+AutoRAG[ja]
+
+[gpu]
+torch>=2.7.1
+sentencepiece>=0.2.0
+bert_score>=0.3.13
+optimum[nncf,openvino]>=1.26.1
+peft>=0.15.2
+llmlingua>=0.2.2
+FlagEmbedding>=1.2.11
+sentence-transformers>=4.1.0
+transformers>=4.51.3
+llama-index-llms-ollama>=0.6.0
+llama-index-embeddings-huggingface>=0.5.4
+llama-index-llms-huggingface>=0.5.0
+onnxruntime>=1.22.0
+
+[ja]
+sudachipy>=0.6.8
+sudachidict_core
+
+[ko]
+kiwipiepy>=0.18.0
+konlpy>=0.6.0
+
+[parse]
+PyMuPDF>=1.26.1
+pdfminer.six>=20250506
+pdfplumber>=0.11.7
+jq>=1.9.1
+unstructured[pdf]>=0.17.2
+PyPDF2==2.12.1
+pdf2image>=1.17.0

{autorag-0.3.12 → autorag-0.3.16}/Dockerfile.base

@@ -68,4 +68,4 @@ RUN apt-get update && \
     pip install --no-cache-dir "AutoRAG[parse]" && \
     rm -rf /var/lib/apt/lists/* && \
     rm -rf /root/.cache/pip/*
-ENTRYPOINT ["python", "-m", "autorag.cli"]
+ENTRYPOINT ["python", "-m", "autorag.cli"]

autorag-0.3.16/PKG-INFO

@@ -0,0 +1,109 @@
+Metadata-Version: 2.4
+Name: AutoRAG
+Version: 0.3.16
+Summary: Automatically Evaluate RAG pipelines with your own data. Find optimal structure for new RAG product.
+Author-email: Marker-Inc <vkehfdl1@gmail.com>
+Project-URL: Homepage, https://github.com/Marker-Inc-Korea/AutoRAG
+Keywords: RAG,AutoRAG,autorag,rag-evaluation,evaluation,rag-auto,AutoML,AutoML-RAG
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+Requires-Dist: pydantic==2.9.2
+Requires-Dist: numpy==1.26.4
+Requires-Dist: pandas>=2.2.3
+Requires-Dist: tqdm>=4.67.1
+Requires-Dist: tiktoken>=0.9.0
+Requires-Dist: openai>=1.90.0
+Requires-Dist: rank_bm25>=0.2.2
+Requires-Dist: pyyaml>=6.0.2
+Requires-Dist: pyarrow>=20.0.0
+Requires-Dist: fastparquet>=2024.11.0
+Requires-Dist: sacrebleu>=2.5.1
+Requires-Dist: evaluate>=0.4.4
+Requires-Dist: rouge_score>=0.1.2
+Requires-Dist: rich>=14.0.0
+Requires-Dist: click>=8.2.1
+Requires-Dist: cohere>=5.8.0
+Requires-Dist: tokenlog>=0.0.2
+Requires-Dist: aiohttp>=3.12.13
+Requires-Dist: voyageai>=0.3.2
+Requires-Dist: mixedbread-ai>=2.2.6
+Requires-Dist: scikit-learn>=1.7.0
+Requires-Dist: emoji>=2.14.1
+Requires-Dist: fastapi>=0.115.13
+Requires-Dist: banks>=2.1.2
+Requires-Dist: grpcio<1.68.0,>=1.66.2
+Requires-Dist: grpcio-health-checking<1.68.0,>=1.66.2
+Requires-Dist: grpcio-status<1.68.0,>=1.66.2
+Requires-Dist: grpcio-tools<1.68.0,>=1.66.2
+Requires-Dist: pymilvus>=2.6.0b0
+Requires-Dist: chromadb>=1.0.0
+Requires-Dist: weaviate-client>=4.15.2
+Requires-Dist: pinecone[grpc]
+Requires-Dist: couchbase>=4.4.0
+Requires-Dist: qdrant-client>=1.12.1
+Requires-Dist: quart>=0.20.0
+Requires-Dist: pyngrok>=7.2.11
+Requires-Dist: llama-index>=0.12.42
+Requires-Dist: llama-index-core>=0.12.42
+Requires-Dist: llama-index-readers-file>=0.4.9
+Requires-Dist: llama-index-embeddings-openai>=0.3.1
+Requires-Dist: llama-index-embeddings-ollama>=0.6.0
+Requires-Dist: llama-index-embeddings-openai-like>=0.1.1
+Requires-Dist: llama-index-llms-openai>=0.4.7
+Requires-Dist: llama-index-llms-openai-like>=0.4.0
+Requires-Dist: llama-index-retrievers-bm25>=0.5.2
+Requires-Dist: llama-index-llms-bedrock>=0.3.8
+Requires-Dist: streamlit>=1.46.0
+Requires-Dist: gradio>=5.34.2
+Requires-Dist: langchain-core==0.2.43
+Requires-Dist: langchain-unstructured==0.1.2
+Requires-Dist: langchain-upstage==0.1.5
+Requires-Dist: langchain-community==0.2.19
+Requires-Dist: langsmith==0.1.147
+Requires-Dist: panel>=1.7.1
+Requires-Dist: seaborn>=0.13.2
+Requires-Dist: ipykernel>=6.29.5
+Requires-Dist: ipywidgets>=8.1.7
+Requires-Dist: ipywidgets_bokeh>=1.6.0
+Provides-Extra: ko
+Requires-Dist: kiwipiepy>=0.18.0; extra == "ko"
+Requires-Dist: konlpy>=0.6.0; extra == "ko"
+Provides-Extra: parse
+Requires-Dist: PyMuPDF>=1.26.1; extra == "parse"
+Requires-Dist: pdfminer.six>=20250506; extra == "parse"
+Requires-Dist: pdfplumber>=0.11.7; extra == "parse"
+Requires-Dist: jq>=1.9.1; extra == "parse"
+Requires-Dist: unstructured[pdf]>=0.17.2; extra == "parse"
+Requires-Dist: PyPDF2==2.12.1; extra == "parse"
+Requires-Dist: pdf2image>=1.17.0; extra == "parse"
+Provides-Extra: ja
+Requires-Dist: sudachipy>=0.6.8; extra == "ja"
+Requires-Dist: sudachidict_core; extra == "ja"
+Provides-Extra: gpu
+Requires-Dist: torch>=2.7.1; extra == "gpu"
+Requires-Dist: sentencepiece>=0.2.0; extra == "gpu"
+Requires-Dist: bert_score>=0.3.13; extra == "gpu"
+Requires-Dist: optimum[nncf,openvino]>=1.26.1; extra == "gpu"
+Requires-Dist: peft>=0.15.2; extra == "gpu"
+Requires-Dist: llmlingua>=0.2.2; extra == "gpu"
+Requires-Dist: FlagEmbedding>=1.2.11; extra == "gpu"
+Requires-Dist: sentence-transformers>=4.1.0; extra == "gpu"
+Requires-Dist: transformers>=4.51.3; extra == "gpu"
+Requires-Dist: llama-index-llms-ollama>=0.6.0; extra == "gpu"
+Requires-Dist: llama-index-embeddings-huggingface>=0.5.4; extra == "gpu"
+Requires-Dist: llama-index-llms-huggingface>=0.5.0; extra == "gpu"
+Requires-Dist: onnxruntime>=1.22.0; extra == "gpu"
+Provides-Extra: all
+Requires-Dist: AutoRAG[gpu]; extra == "all"
+Requires-Dist: AutoRAG[ko]; extra == "all"
+Requires-Dist: AutoRAG[parse]; extra == "all"
+Requires-Dist: AutoRAG[ja]; extra == "all"

autorag-0.3.16/autorag/VERSION

@@ -0,0 +1 @@
+0.3.16

{autorag-0.3.12 → autorag-0.3.16}/autorag/__init__.py

@@ -41,13 +41,6 @@ class LazyInit:
 		return getattr(self._instance, name)
 
 
-class MockEmbeddingRandom(MockEmbedding):
-	"""Mock embedding with random vectors."""
-
-	def _get_vector(self) -> List[float]:
-		return [random() for _ in range(self.embed_dim)]
-
-
 rich_format = "[%(filename)s:%(lineno)s] >> %(message)s"
 logging.basicConfig(
 	level="INFO", format=rich_format, handlers=[RichHandler(rich_tracebacks=True)]
@@ -62,46 +55,6 @@ def handle_exception(exc_type, exc_value, exc_traceback):
 
 sys.excepthook = handle_exception
 
-embedding_models = {
-	# llama index
-	"openai": LazyInit(
-		OpenAIEmbedding
-	),  # default model is OpenAIEmbeddingModelType.TEXT_EMBED_ADA_002
-	"openai_embed_3_large": LazyInit(
-		OpenAIEmbedding, model_name=OpenAIEmbeddingModelType.TEXT_EMBED_3_LARGE
-	),
-	"openai_embed_3_small": LazyInit(
-		OpenAIEmbedding, model_name=OpenAIEmbeddingModelType.TEXT_EMBED_3_SMALL
-	),
-	"mock": LazyInit(MockEmbeddingRandom, embed_dim=768),
-	# langchain
-	"openai_langchain": LazyInit(OpenAIEmbeddings),
-}
-
-try:
-	# you can use your own model in this way.
-	from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-
-	embedding_models["huggingface_baai_bge_small"] = LazyInit(
-		HuggingFaceEmbedding, model_name="BAAI/bge-small-en-v1.5"
-	)
-	embedding_models["huggingface_cointegrated_rubert_tiny2"] = LazyInit(
-		HuggingFaceEmbedding, model_name="cointegrated/rubert-tiny2"
-	)
-	embedding_models["huggingface_all_mpnet_base_v2"] = LazyInit(
-		HuggingFaceEmbedding,
-		model_name="sentence-transformers/all-mpnet-base-v2",
-		max_length=512,
-	)
-	embedding_models["huggingface_bge_m3"] = LazyInit(
-		HuggingFaceEmbedding, model_name="BAAI/bge-m3"
-	)
-except ImportError:
-	logger.info(
-		"You are using API version of AutoRAG."
-		"To use local version, run pip install 'AutoRAG[gpu]'"
-	)
-
 
 class AutoRAGBedrock(Bedrock):
 	async def acomplete(

{autorag-0.3.12 → autorag-0.3.16}/autorag/data/__init__.py

@@ -16,7 +16,7 @@ from langchain_community.document_loaders import (
 	DirectoryLoader,
 )
 from langchain_unstructured import UnstructuredLoader
-from langchain_upstage import UpstageDocumentParseLoader
+from langchain_upstage import UpstageLayoutAnalysisLoader
 
 from llama_index.core.node_parser import (
 	TokenTextSplitter,
@@ -59,7 +59,7 @@ parse_modules = {
 	# 6. All files
 	"directory": DirectoryLoader,
 	"unstructured": UnstructuredLoader,
-	"upstagedocumentparse": UpstageDocumentParseLoader,
+	"upstagedocumentparse": UpstageLayoutAnalysisLoader,
 }
 
 chunk_modules = {

{autorag-0.3.12 → autorag-0.3.16}/autorag/data/chunk/base.py

@@ -4,7 +4,7 @@ from typing import Tuple, List, Dict, Any
 
 import pandas as pd
 
-from autorag import embedding_models
+from autorag.embedding.base import EmbeddingModel
 from autorag.data import chunk_modules, sentence_splitter_modules
 from autorag.utils import result_to_dataframe
 
@@ -80,7 +80,7 @@ def __get_chunk_instance(module_type: str, chunk_method: str, **kwargs):
 		if _embed_model_str == "openai":
 			if _module_type == "langchain_chunk":
 				_embed_model_str = "openai_langchain"
-		return embedding_models[_embed_model_str]()
+		return EmbeddingModel.load(_embed_model_str)()
 
 	# Add embed_model to kwargs
 	embedding_available_methods = ["semantic_llama_index", "semantic_langchain"]

{autorag-0.3.12 → autorag-0.3.16}/autorag/data/legacy/qacreation/base.py

@@ -130,7 +130,7 @@ def make_qa_with_existing_qa(
 	:param output_filepath: Optional filepath to save the parquet file.
 	:param embedding_model: The embedding model to use for vectorization.
 	    You can add your own embedding model in the autorag.embedding_models.
-	    Please refer to how to add an embedding model in this doc: https://docs.auto-rag.com/local_model.html
+	    Please refer to how to add an embedding model in this doc: https://marker-inc-korea.github.io/AutoRAG/local_model.html
 	    The default is 'openai_embed_3_large'.
 	:param collection: The chromadb collection to use for vector DB.
 	    You can make any chromadb collection and use it here.