add files

DockerFile

@@ -1,13 +0,0 @@
-FROM python:3.9
-
-RUN useradd -m -u 1000 user
-USER user
-ENV PATH="/home/user/.local/bin:$PATH"
-
-WORKDIR /app
-
-COPY --chown=user ./requirements.txt requirements.txt
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
-
-COPY --chown=user . /app
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

Dockerfile

@@ -1,5 +1,3 @@
-# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
-# you will also find guides on how best to write your Dockerfile
 
 FROM python:3.9
 

app.py

@@ -1,7 +1,190 @@
-from fastapi import FastAPI
+import os
+import shutil
+import tempfile
+from contextlib import asynccontextmanager
+from typing import Annotated
 
-app = FastAPI()
+from dotenv import dotenv_values
+from fastapi import FastAPI, File, Form, HTTPException, UploadFile
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+
+
+from helpers import (
+    generate_embedding_doc,
+    get_text_from_pdf,
+    run_rag_pipeline,
+    split_doc_chunks,
+)
+
+# --------------------------------------------------
+# CONFIG
+# --------------------------------------------------
+
+config = dotenv_values(".env")
+
+GROQ_API_KEY = config.get(
+    "GROQ_API_KEY",
+    os.getenv("GROQ_API_KEY", "")
+)
+
+if not GROQ_API_KEY:
+    raise RuntimeError("Missing GROQ_API_KEY")
+
+# --------------------------------------------------
+# SIMPLE LIST STORAGE: I Don't Use Chroma DB --> Deployment Causes
+# --------------------------------------------------
+
+chunked_documents = []
+
+# --------------------------------------------------
+# FASTAPI
+# --------------------------------------------------
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    print("API Started")
+    yield
+    print("API Stopped")
+
+app = FastAPI(
+    title="Simple RAG API",
+    lifespan=lifespan,
+)
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# --------------------------------------------------
+# SCHEMAS
+# --------------------------------------------------
+
+class QueryRequest(BaseModel):
+    question: str
+    top_k: int = 5
+    rerank_top_k: int = 3
+
+# --------------------------------------------------
+# ROUTES
+# --------------------------------------------------
 
 @app.get("/")
-def greet_json():
-    return {"Hello": "World!"}
+def home():
+    return {
+        "message": "RAG API Running"
+    }
+
+# --------------------------------------------------
+# UPLOAD PDF
+# --------------------------------------------------
+
+@app.post("/upload-pdf")
+async def upload_pdf(
+    file: Annotated[
+        UploadFile,
+        File(description="PDF file")
+    ],
+):
+    print("FILE SEND: ", file)
+
+    global chunked_documents
+
+    # -------------------------------
+    # CHECK PDF
+    # -------------------------------
+
+    if not file.filename.endswith(".pdf"):
+
+        raise HTTPException(
+            status_code=400,
+            detail="Only PDF allowed"
+        )
+
+    # -------------------------------
+    # SAVE TEMP PDF
+    # -------------------------------
+
+    with tempfile.NamedTemporaryFile(
+        delete=False,
+        suffix=".pdf"
+    ) as tmp:
+
+        shutil.copyfileobj(file.file, tmp)
+
+        tmp_path = tmp.name
+
+    try:
+
+        # -------------------------------
+        # EXTRACT TEXT
+        # -------------------------------
+
+        documents = get_text_from_pdf(tmp_path)
+
+        if not documents:
+
+            raise HTTPException(
+                status_code=400,
+                detail="No text found"
+            )
+
+        # -------------------------------
+        # CHUNKING
+        # -------------------------------
+
+        chunked_documents = split_doc_chunks(
+            documents
+        )
+
+        # -------------------------------
+        # GENERATE EMBEDDINGS
+        # -------------------------------
+
+        chunked_documents = generate_embedding_doc(
+            chunked_documents
+        )
+
+        return {
+            "message": "PDF indexed successfully",
+            "chunks": len(chunked_documents)
+        }
+
+    finally:
+
+        os.unlink(tmp_path)
+
+# --------------------------------------------------
+# QUERY
+# --------------------------------------------------
+
+@app.post("/query")
+def query(req: QueryRequest):
+
+    global chunked_documents
+    print("Question", req)
+
+    if not chunked_documents:
+
+        raise HTTPException(
+            status_code=400,
+            detail="Upload PDF first"
+        )
+
+    answer = run_rag_pipeline(
+        question=req.question,
+        chunked_documents=chunked_documents,
+        groq_api_key=GROQ_API_KEY,
+        top_k=req.top_k,
+        rerank_top_k=req.rerank_top_k,
+    )
+
+    return {
+        "question": req.question,
+        "answer": answer,
+    }
+
+

requirements.txt

@@ -1,2 +1,26 @@
-fastapi
-uvicorn[standard]
+# RAG API — Python dependencies
+
+# Web framework
+fastapi>=0.111.0
+uvicorn[standard]>=0.29.0
+python-multipart>=0.0.9
+
+# Environment
+python-dotenv>=1.0.0
+
+# LLM
+groq>=0.9.0
+
+# Embeddings
+sentence-transformers>=3.0.0
+
+# PDF extraction
+pdfplumber>=0.11.0
+
+# Retrieval / ranking
+rank-bm25>=0.2.2
+scikit-learn>=1.4.0
+numpy>=1.26.0
+
+# Validation
+pydantic>=2.7.0