Create app.py

app.py

@@ -0,0 +1,128 @@
+
+
+import os
+import re
+import gradio as gr
+import pdfplumber
+import pytesseract
+from PIL import Image
+from langchain.docstore.document import Document
+from langchain.vectorstores import FAISS
+from langchain.embeddings.base import Embeddings
+from sklearn.feature_extraction.text import TfidfVectorizer
+from langchain.chains import RetrievalQA
+from langchain.prompts import PromptTemplate
+from langchain_openai import ChatOpenAI
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+
+os.environ["OPENAI_API_KEY"] = os.getenv("OPENROUTER_API_KEY")
+os.environ["OPENAI_API_BASE"] = "https://openrouter.ai/api/v1"
+os.environ["OPENAI_API_HEADERS"] = '{"HTTP-Referer":"https://huggingface.co/spaces/saadawaissheikh/SystemsHealthcareChatbot", "X-Title":"PDF Chatbot"}'
+
+# ✅ Load PDF once at startup
+PDF_PATH = "HealthCare Policy.pdf"
+
+class TfidfEmbedding(Embeddings):
+    def __init__(self):
+        self.vectorizer = TfidfVectorizer()
+
+    def fit(self, texts):
+        self.vectorizer.fit(texts)
+
+    def embed_documents(self, texts):
+        return self.vectorizer.transform(texts).toarray()
+
+    def embed_query(self, text):
+        return self.vectorizer.transform([text]).toarray()[0]
+
+def load_pdf_chunks(pdf_path):
+    with pdfplumber.open(pdf_path) as pdf:
+        full_text = "\n".join([page.extract_text() or "" for page in pdf.pages])
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=50)
+    chunks = splitter.split_text(full_text)
+    return [Document(page_content=chunk) for chunk in chunks]
+
+def setup_vectordb(docs):
+    texts = [doc.page_content for doc in docs]
+    embedder = TfidfEmbedding()
+    embedder.fit(texts)
+    vectordb = FAISS.from_texts(texts, embedder)
+    return vectordb
+
+def get_llm():
+    return ChatOpenAI(
+        model="tngtech/deepseek-r1t2-chimera:free",
+        temperature=0.0
+    )
+
+def get_qa_chain():
+    docs = load_pdf_chunks(PDF_PATH)
+    vectordb = setup_vectordb(docs)
+    retriever = vectordb.as_retriever()
+    prompt = PromptTemplate.from_template("Answer with Yes or No first. Then explain: {context}\nQuestion: {question}")
+    llm = get_llm()
+    return RetrievalQA.from_chain_type(
+        llm=llm,
+        retriever=retriever,
+        chain_type="stuff",
+        return_source_documents=False,
+        chain_type_kwargs={"prompt": prompt}
+    )
+
+qa_chain = get_qa_chain()
+
+# ✅ Standard PDF QA
+def ask_question(query):
+    try:
+        return qa_chain.run(query)
+    except Exception as e:
+        return f"Error: {e}"
+
+# ✅ Extract Tablets from Image
+def extract_tablet_names(text):
+    medicines = []
+    for line in text.splitlines():
+        match = re.search(r"\\b([A-Za-z]+(?:\\s+[A-Za-z]+)*)\\s*(\\d+mg|\\d+\\s*mg)?\\b", line)
+        if match:
+            name = match.group(1).strip()
+            if name.lower() not in ["cash", "scaling", "polish"]:
+                medicines.append(name)
+    return list(set(medicines))
+
+def extract_text_from_image(img_path):
+    image = Image.open(img_path)
+    raw_text = pytesseract.image_to_string(image)
+    return extract_tablet_names(raw_text)
+
+# ✅ Tablet Claim Checker
+def check_tablets(img):
+    tablets = extract_text_from_image(img)
+    if not tablets:
+        return "❌ No tablets found in receipt."
+    result = ""
+    for med in tablets:
+        question = f"Is the medicine {med} covered under the healthcare policy?"
+        answer = qa_chain.run(question)
+        result += f"🧾 **{med}** → {answer}\n\n"
+    return result
+
+# ✅ Gradio UI
+with gr.Blocks(title="Healthcare Chatbot") as app:
+    gr.Markdown("# 💬 Systems Healthcare Chatbot")
+    gr.Markdown("📄 Policy document loaded. You may now ask questions or upload a medicine receipt to check claims.")
+
+    with gr.Tab("Ask about Policy"):
+        with gr.Row():
+            txt = gr.Textbox(label="Your Question")
+            ans = gr.Textbox(label="Answer")
+        txt.submit(fn=ask_question, inputs=txt, outputs=ans)
+
+    with gr.Tab("Check Tablet Claim"):
+        with gr.Row():
+            img = gr.Image(type="filepath", label="Upload Tablet Receipt")
+            out = gr.Textbox(label="Result")
+        img.change(fn=check_tablets, inputs=img, outputs=out)
+
+# ✅ Launch App
+app.launch()