proofrag-ai 0.1.0__tar.gz

proofrag_ai-0.1.0/PKG-INFO

@@ -0,0 +1,48 @@
+Metadata-Version: 2.4
+Name: proofrag-ai
+Version: 0.1.0
+Summary: Evidence-backed RAG with verified citations and refusal on insufficient evidence.
+Author: Mainak Sen
+Keywords: rag,retrieval-augmented-generation,llm,citations,grounded-ai,knowledge-base,okf,chroma,langchain,generative-ai
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: <3.14,>=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic<3.0,>=2.9
+Requires-Dist: pydantic-settings<3.0,>=2.6
+Requires-Dist: python-dotenv<2.0,>=1.0
+Requires-Dist: PyYAML<7.0,>=6.0
+Requires-Dist: pymupdf<2.0,>=1.24
+Requires-Dist: langchain<2.0,>=0.3
+Requires-Dist: langchain-community<1.0,>=0.3
+Requires-Dist: langchain-core<2.0,>=0.3
+Requires-Dist: langchain-chroma<1.0,>=0.2
+Requires-Dist: langchain-huggingface<1.0,>=0.1
+Requires-Dist: chromadb<2.0,>=0.5
+Requires-Dist: sentence-transformers<6.0,>=3.0
+Requires-Dist: groq<1.0,>=0.13
+Requires-Dist: langchain-groq<1.0,>=0.2
+Requires-Dist: fastapi<1.0,>=0.115
+Requires-Dist: uvicorn[standard]<1.0,>=0.32
+Requires-Dist: typer<1.0,>=0.15
+Requires-Dist: rich<15.0,>=13.9
+Requires-Dist: streamlit<2.0,>=1.40
+Requires-Dist: nltk<4.0,>=3.9
+Provides-Extra: dev
+Requires-Dist: pytest<9.0,>=8.3; extra == "dev"
+Requires-Dist: pytest-cov<8.0,>=6.0; extra == "dev"
+Requires-Dist: httpx<1.0,>=0.27; extra == "dev"
+Requires-Dist: ruff<1.0,>=0.8; extra == "dev"
+Requires-Dist: build<2.0,>=1.2; extra == "dev"
+Requires-Dist: twine<7.0,>=6.0; extra == "dev"
+Dynamic: license-file

proofrag_ai-0.1.0/pyproject.toml

@@ -0,0 +1,128 @@
+[build-system]
+requires = ["setuptools>=75.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+
+[project]
+name = "proofrag-ai"
+version = "0.1.0"
+description = "Evidence-backed RAG with verified citations and refusal on insufficient evidence."
+readme = "README.md"
+requires-python = ">=3.10,<3.14"
+license = { file = "LICENSE" }
+authors = [
+    { name = "Mainak Sen" }
+]
+keywords = [
+    "rag",
+    "retrieval-augmented-generation",
+    "llm",
+    "citations",
+    "grounded-ai",
+    "knowledge-base",
+    "okf",
+    "chroma",
+    "langchain",
+    "generative-ai"
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Software Development :: Libraries :: Python Modules"
+]
+
+dependencies = [
+    "pydantic>=2.9,<3.0",
+    "pydantic-settings>=2.6,<3.0",
+    "python-dotenv>=1.0,<2.0",
+
+    "PyYAML>=6.0,<7.0",
+
+    "pymupdf>=1.24,<2.0",
+
+    "langchain>=0.3,<2.0",
+    "langchain-community>=0.3,<1.0",
+    "langchain-core>=0.3,<2.0",
+    "langchain-chroma>=0.2,<1.0",
+    "langchain-huggingface>=0.1,<1.0",
+
+    "chromadb>=0.5,<2.0",
+    "sentence-transformers>=3.0,<6.0",
+
+    "groq>=0.13,<1.0",
+    "langchain-groq>=0.2,<1.0",
+
+    "fastapi>=0.115,<1.0",
+    "uvicorn[standard]>=0.32,<1.0",
+
+    "typer>=0.15,<1.0",
+    "rich>=13.9,<15.0",
+
+    "streamlit>=1.40,<2.0",
+    "nltk>=3.9,<4.0"
+]
+
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.3,<9.0",
+    "pytest-cov>=6.0,<8.0",
+    "httpx>=0.27,<1.0",
+    "ruff>=0.8,<1.0",
+    "build>=1.2,<2.0",
+    "twine>=6.0,<7.0"
+]
+
+
+[project.scripts]
+proofrag = "proofrag.cli:app"
+
+
+[tool.setuptools]
+package-dir = { "" = "src" }
+
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+addopts = "-ra"
+
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "F",
+    "I",
+    "B",
+    "UP"
+]
+
+
+[tool.coverage.run]
+source = ["proofrag"]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "if TYPE_CHECKING:"
+]
+
+
+[build]
+target = "proofrag"

proofrag_ai-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

proofrag_ai-0.1.0/src/proofrag/api.py

@@ -0,0 +1,65 @@
+from __future__ import annotations
+
+from fastapi import FastAPI, HTTPException
+
+from .config import get_settings
+from .models import ProofRAGRequest, ProofRAGResponse
+from .pipeline import PipelineError, ProofRAG
+
+settings = get_settings()
+
+app = FastAPI(
+    title=settings.app_name,
+    version=settings.app_version,
+    description=(
+        "Evidence-backed RAG with verified citations "
+        "and safe refusal on insufficient evidence."
+    ),
+)
+
+rag = ProofRAG()
+
+
+@app.get("/health")
+def health() -> dict[str, str]:
+    return {
+        "status": "ok",
+        "service": settings.app_name,
+        "version": settings.app_version,
+    }
+
+
+@app.post("/ingest")
+def ingest() -> dict[str, object]:
+    try:
+        documents = rag.ingest()
+    except PipelineError as exc:
+        raise HTTPException(
+            status_code=500,
+            detail=str(exc),
+        ) from exc
+
+    return {
+        "status": "ok",
+        "documents_indexed": len(documents),
+        "documents": [
+            document.filename
+            for document in documents
+        ],
+    }
+
+
+@app.post(
+    "/ask",
+    response_model=ProofRAGResponse,
+)
+def ask(
+    request: ProofRAGRequest,
+) -> ProofRAGResponse:
+    try:
+        return rag.ask(request)
+    except PipelineError as exc:
+        raise HTTPException(
+            status_code=500,
+            detail=str(exc),
+        ) from exc

proofrag_ai-0.1.0/src/proofrag/cli.py

@@ -0,0 +1,96 @@
+from __future__ import annotations
+
+import typer
+from rich.console import Console
+from rich.panel import Panel
+
+from .pipeline import PipelineError, ProofRAG
+
+app = typer.Typer(
+    name="proofrag",
+    help="Evidence-backed RAG with verified citations.",
+)
+
+console = Console()
+
+
+@app.command()
+def ingest() -> None:
+    """Index documents into OKF and Chroma."""
+
+    rag = ProofRAG()
+
+    try:
+        documents = rag.ingest()
+    except PipelineError as exc:
+        console.print(
+            f"[red]Error:[/red] {exc}"
+        )
+        raise typer.Exit(code=1)
+
+    console.print(
+        f"[green]Indexed {len(documents)} document(s).[/green]"
+    )
+
+    for document in documents:
+        console.print(
+            f"  • {document.filename}"
+        )
+
+
+@app.command()
+def ask(
+    question: str = typer.Argument(
+        ...,
+        help="Question to ask over the indexed documents.",
+    ),
+) -> None:
+    """Ask a question and display verified evidence."""
+
+    rag = ProofRAG()
+
+    try:
+        response = rag.ask(question)
+    except PipelineError as exc:
+        console.print(
+            f"[red]Error:[/red] {exc}"
+        )
+        raise typer.Exit(code=1)
+
+    console.print(
+        Panel(
+            response.answer,
+            title="ProofRAG Answer",
+        )
+    )
+
+    console.print(
+        f"Verified: {response.verified}"
+    )
+    console.print(
+        f"Refused: {response.refused}"
+    )
+    console.print(
+        f"Evidence: {response.evidence_count}"
+    )
+
+    for citation in response.citations:
+        console.print()
+        console.print(
+            f"[bold]Source:[/bold] {citation.filename}"
+        )
+        console.print(
+            f"[bold]Page:[/bold] {citation.page_number}"
+        )
+        console.print(
+            f"[bold]Status:[/bold] "
+            f"{citation.verification_status.value}"
+        )
+        console.print(
+            f"[bold]Evidence:[/bold] "
+            f"{citation.snippet}"
+        )
+
+
+if __name__ == "__main__":
+    app()

proofrag_ai-0.1.0/src/proofrag/config.py

@@ -0,0 +1,108 @@
+from __future__ import annotations
+
+from functools import lru_cache
+from pathlib import Path
+
+from pydantic import Field
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+PROJECT_ROOT = Path(__file__).resolve().parents[2]
+
+
+class Settings(BaseSettings):
+    """Application configuration for ProofRAG."""
+
+    model_config = SettingsConfigDict(
+        env_file=PROJECT_ROOT / ".env",
+        env_file_encoding="utf-8",
+        case_sensitive=False,
+        extra="ignore",
+    )
+
+    # ------------------------------------------------------------------
+    # Application
+    # ------------------------------------------------------------------
+
+    app_name: str = "ProofRAG"
+    app_version: str = "0.1.0"
+    environment: str = "development"
+
+    # ------------------------------------------------------------------
+    # Paths
+    # ------------------------------------------------------------------
+
+    data_dir: Path = PROJECT_ROOT / "data"
+    documents_dir: Path = PROJECT_ROOT / "data" / "documents"
+    okf_dir: Path = PROJECT_ROOT / "data" / "okf"
+    chroma_dir: Path = PROJECT_ROOT / "data" / "chroma"
+
+    # ------------------------------------------------------------------
+    # LLM
+    # ------------------------------------------------------------------
+
+    groq_api_key: str = Field(default="", repr=False)
+    llm_model: str = "openai/gpt-oss-120b"
+    llm_temperature: float = 0.0
+    llm_timeout: int = 60
+
+    # ------------------------------------------------------------------
+    # Embeddings
+    # ------------------------------------------------------------------
+
+    embedding_model: str = "sentence-transformers/all-MiniLM-L6-v2"
+
+    # ------------------------------------------------------------------
+    # Chunking
+    # ------------------------------------------------------------------
+
+    chunk_size: int = 1000
+    chunk_overlap: int = 150
+
+    # ------------------------------------------------------------------
+    # Retrieval
+    # ------------------------------------------------------------------
+
+    retrieval_top_k: int = 5
+    retrieval_score_threshold: float = 0.35
+
+    # ------------------------------------------------------------------
+    # Citation verification
+    # ------------------------------------------------------------------
+
+    citation_keyword_threshold: float = 0.20
+    citation_embedding_threshold: float = 0.60
+
+    # ------------------------------------------------------------------
+    # API
+    # ------------------------------------------------------------------
+
+    api_host: str = "127.0.0.1"
+    api_port: int = 8000
+
+    # ------------------------------------------------------------------
+    # Safety / limits
+    # ------------------------------------------------------------------
+
+    max_question_length: int = 2000
+    max_context_chunks: int = 8
+
+    def ensure_directories(self) -> None:
+        """Create required runtime directories if they do not exist."""
+
+        for directory in (
+            self.data_dir,
+            self.documents_dir,
+            self.okf_dir,
+            self.chroma_dir,
+        ):
+            directory.mkdir(parents=True, exist_ok=True)
+
+
+@lru_cache(maxsize=1)
+def get_settings() -> Settings:
+    """Return the cached application settings."""
+
+    settings = Settings()
+    settings.ensure_directories()
+    return settings

proofrag_ai-0.1.0/src/proofrag/embeddings.py

@@ -0,0 +1,53 @@
+from __future__ import annotations
+
+from functools import lru_cache
+
+from langchain_huggingface import HuggingFaceEmbeddings
+
+from .config import get_settings
+
+
+@lru_cache(maxsize=1)
+def get_embedding_model() -> HuggingFaceEmbeddings:
+    """
+    Create and cache the ProofRAG embedding model.
+
+    The model runs locally through sentence-transformers.
+    """
+
+    settings = get_settings()
+
+    return HuggingFaceEmbeddings(
+        model_name=settings.embedding_model,
+        model_kwargs={
+            "device": "cpu",
+        },
+        encode_kwargs={
+            "normalize_embeddings": True,
+        },
+    )
+
+
+def embed_text(text: str) -> list[float]:
+    """Generate an embedding for a single text."""
+
+    if not text.strip():
+        raise ValueError("Cannot embed empty text.")
+
+    return get_embedding_model().embed_query(text)
+
+
+def embed_documents(
+    texts: list[str],
+) -> list[list[float]]:
+    """Generate embeddings for multiple documents."""
+
+    if not texts:
+        return []
+
+    if any(not text.strip() for text in texts):
+        raise ValueError(
+            "Document texts cannot contain empty strings."
+        )
+
+    return get_embedding_model().embed_documents(texts)