Initial backend-only RAG (no PDFs)

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,18 @@
+# Python
+__pycache__/
+*.pyc
+
+# Chroma DB
+chroma_db/
+data/
+
+# Environment
+.env
+
+# Frontend (DO NOT COMMIT)
+frontend/node_modules/
+frontend/dist/
+frontend/.vite/
+
+kb_docs/
+*.pdf

Dockerfile

@@ -0,0 +1,23 @@
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY app.py rag.py ingest.py guardrails.py config.py ./
+COPY kb_docs ./kb_docs
+
+# Hugging Face Spaces expects port 7860
+EXPOSE 7860
+
+# Start FastAPI
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -0,0 +1,11 @@
+---
+title: HubRAG
+emoji: 📊
+colorFrom: green
+colorTo: purple
+sdk: docker
+pinned: false
+short_description: Ask anything about Gandhi ji.
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,20 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+from rag import ask_rag_with_status
+
+app = FastAPI(title="HubRAG API")
+
+class Question(BaseModel):
+    question: str
+
+@app.get("/")
+def root():
+    return {
+        "status": "ok",
+        "message": "RAG API is running"
+    }
+
+@app.post("/chat")
+def chat(req: Question):
+    return ask_rag_with_status(req.question)

config.py

@@ -0,0 +1,9 @@
+import os
+
+HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+if not HUGGINGFACEHUB_API_TOKEN:
+    raise RuntimeError(
+        "HUGGINGFACEHUB_API_TOKEN is not set. "
+        "Set it as an environment variable or HF Space Secret."
+    )

guardrails.py

@@ -0,0 +1,2 @@
+def validate_question(question: str) -> bool:
+    return bool(question and question.strip())

ingest.py

@@ -0,0 +1,17 @@
+from langchain_community.document_loaders import DirectoryLoader, PyPDFLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+
+def load_and_split_docs(path="kb_docs"):
+    loader = DirectoryLoader(
+        path,
+        glob="**/*.pdf",
+        loader_cls=PyPDFLoader
+    )
+    docs = loader.load()
+
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=800,
+        chunk_overlap=100
+    )
+
+    return splitter.split_documents(docs)

rag.py

@@ -0,0 +1,49 @@
+from langchain_huggingface import HuggingFaceEmbeddings, ChatHuggingFace
+from langchain_chroma import Chroma
+from langchain.schema import SystemMessage, HumanMessage
+
+from ingest import load_and_split_docs
+
+print("⏳ Indexing documents...")
+
+embeddings = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/all-MiniLM-L6-v2"
+)
+
+documents = load_and_split_docs()
+
+vectorstore = Chroma.from_documents(
+    documents,
+    embedding=embeddings
+)
+
+retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
+
+llm = ChatHuggingFace(
+    repo_id="microsoft/Phi-4-mini-instruct",
+    temperature=0.2
+)
+
+print("✅ Indexing complete.")
+
+def ask_rag_with_status(question: str):
+    status = [
+        "🔍 Retrieving relevant documents...",
+        "🧠 Building context...",
+        "💭 Thinking..."
+    ]
+
+    docs = retriever.get_relevant_documents(question)
+    context = "\n\n".join(d.page_content for d in docs)
+
+    messages = [
+        SystemMessage(content="You are a helpful assistant. Answer using the context."),
+        HumanMessage(content=f"Context:\n{context}\n\nQuestion: {question}")
+    ]
+
+    response = llm.invoke(messages)
+
+    return {
+        "status": status,
+        "answer": response.content
+    }

requirements.txt

@@ -0,0 +1,14 @@
+fastapi
+uvicorn
+pydantic
+python-dotenv
+
+langchain
+langchain-community
+langchain-core
+langchain-huggingface
+
+chromadb
+sentence-transformers
+pypdf
+huggingface_hub