Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.9-slim
+
+ENV PYTHONDONTWRITEBYTECODE 1
+ENV PYTHONUNBUFFERED 1
+
+WORKDIR /app
+
+# Install system packages
+RUN apt-get update && apt-get install -y \
+    libmagic1 \
+    build-essential \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY . .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+EXPOSE 8501
+
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0", "--server.enableXsrfProtection=false"]

app.py

@@ -0,0 +1,62 @@
+import langchain
+import streamlit as st
+import pickle as pkl
+from langchain.chains import RetrievalQAWithSourcesChain
+from langchain.document_loaders import UnstructuredURLLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import SentenceTransformerEmbeddings
+from langchain.vectorstores import Chroma, FAISS
+from langchain_openai import ChatOpenAI
+from dotenv import load_dotenv
+import time
+
+load_dotenv("ping.env")
+api_key=os.getenv("OPENAI_API_KEY")
+api_base=os.getenv("OPENAI_API_BASE")
+
+llm=ChatOpenAI(model_name="google/gemma-3n-e2b-it:free",temperature=0)
+
+path="embedmo.pkl"
+m1=pkl.load(open(path,"rb"))
+
+st.title("URL ANALYSER🔗")
+st.sidebar.title("Give your URls🔗?")
+mp=st.empty()
+
+
+urs = [st.sidebar.text_input(f"URL {i+1}🔗") for i in range(3)]
+urs = [url for url in urs if url.strip()]  # ✅ filters out empty inputs
+
+purs=st.button("gotcha", disabled=not any(url.strip() for url in urs))
+if purs:
+  mp.text("Loading..URl..Loader....☑️☑️☑️")
+  sic=UnstructuredURLLoader(urls=urs)
+  docs=sic.load()
+  mp.text("Loading..txt..splitter....☑️☑️☑️")
+  tot=RecursiveCharacterTextSplitter.from_tiktoken_encoder(encoding_name="cl100k_base",chunk_size=512,chunk_overlap=16)
+  doccs=tot.split_documents(docs)
+  mp.text("Loading..VB...☑️☑️☑️")
+  vv=FAISS.from_documents(doccs,m1)
+  r2=vv.as_retriever(search_type="similarity",search_kwargs={"k":4})
+  mp.text("Loading..Retri....☑️☑️☑️")
+  ra1=RetrievalQAWithSourcesChain.from_chain_type(llm=llm,retriever=r2,chain_type="map_reduce")
+  st.session_state.ra1=ra1
+  mp.text("DB & Retri Done ✅✅✅")
+  time.sleep(3)
+query=mp.text_input("UR Question??")
+if query:
+  if "ra1" not in st.session_state:
+    st.warning("pls give ur urls")
+  else:
+    with st.spinner("Wait for it..."):
+      result=st.session_state.ra1({"question":query},return_only_outputs=True)
+      st.header("Answer")
+      st.subheader(result["answer"])
+      g = st.button("Source")
+      if g:
+        sources = result.get("sources", "")
+        st.subheader("Sources")
+        for line in sources.split("\n"):
+          st.write(line)
+  
+

embedmo.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42660d3d488cc52774083dc5af8b2b5e81d27219ac0ed2de757d72a79d3df6a0
+size 91394790

ping.env

@@ -0,0 +1,2 @@
+OPENAI_API_KEY=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
+OPENAI_API_BASE=https://openrouter.ai/api/v1

requirements.txt

@@ -0,0 +1,8 @@
+streamlit
+langchain
+python-dotenv
+unstructured
+sentence-transformers
+faiss-cpu
+openai
+langchain-openai