Merge pull request #2 from Janarthanam/streamlit

Dockerfile

@@ -1,6 +1,12 @@
 # Use an official Python base image
 FROM python:3.10-slim
 
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+
+# Switch to the "user" user
+USER user
+
 # Set the working directory
 WORKDIR /app
 
@@ -11,14 +17,16 @@ COPY requirements.txt .
 RUN pip install --trusted-host pypi.python.org -r requirements.txt
 
 # Copy the rest of the application code into the container
-COPY api .
+COPY --chown=user run.sh api fe .
 
 # Expose the port the app runs on
-EXPOSE 8080
+EXPOSE 8080 8501
 
 #todo these keys are environment specific
 ENV OPENAI_API_KEY=zzz
 ENV QDRANT_URL="https://32f125d3-5ab1-4058-a10a-bd38a1ebd647.us-east-1-0.aws.cloud.qdrant.io"
 ENV STORE="QDRANT"
+ENV be_url="http://127.0.0.1:8080"
+
 # Start the application using Uvicorn
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8080"]
+CMD ["/bin/sh", "./run.sh"]

README.md

@@ -1,13 +1,13 @@
 ---
 title: Toypdf
 emoji: 📉
-colorFrom: pink
+colorFrom: blue
 colorTo: red
 sdk: docker
-app_port: 8080
+app_port: 8501
 pinned: true
-models: ["gpt2"]
-datasets: ["oscar-corpus/OSCAR-2109"]
+models: ["sentence-transformers/all-MiniLM-L6-v2"]
+datasets: ["multi_nli"]
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

api/db/vector_store.py

@@ -91,5 +91,5 @@ class QdrantVectorStore(Store):
     def list_collections(self) -> list[dict]:
         """ return a list of collections.
         """
-        return [ c for i,c in enumerate(self.client.get_collections().collections)]
+        return [ c.dict() for i,c in enumerate(self.client.get_collections().collections)]
     

fe/app.py

@@ -0,0 +1,25 @@
+import os
+import requests
+
+import streamlit as st
+
+BE = os.getenv("be_url")
+
+
+datasets = requests.get(f"{BE}/v1/datasets", timeout=500).json()
+
+st.sidebar.title("Datasets")
+ds = st.sidebar.selectbox(options=[ d["name"] for d in datasets], 
+                          label="Select your dataset")
+print(ds)
+if ds:
+    query = st.text_input("Enter your search query",
+                          placeholder="Ask your question")
+    if query:
+        answer = requests.get(f"http://localhost:8080/v1/datasets/{ds}/answer?query={query}", 
+                       timeout=5000 )
+
+        print(answer.json()["answer"])
+        st.write(answer.json()["answer"])
+else:
+    st.write("Choose your dataset!")

requirements.txt

@@ -10,4 +10,4 @@ faiss-cpu
 qdrant-client
 elasticsearch
 sentence_transformers
-
+streamlit

run.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+python -m uvicorn "main:app" "--host" "0.0.0.0" "--port" "8080" &
+
+#active wait- container won't quit
+while ! timeout 1 bash -c "echo > /dev/tcp/localhost/8080"; do sleep 5; done
+
+export be_url=`awk 'END{print "http://"$1":8080"}' /etc/hosts`
+python -m streamlit run app.py