Initial setup of Streamlit app for Hugging Face Spaces

.gitignore

@@ -0,0 +1 @@
+.streamlit/secrets.toml

app.py

@@ -0,0 +1,53 @@
+import streamlit as st
+from gpt_researcher import GPTResearcher
+import asyncio
+import nest_asyncio
+
+# Access secrets
+openai_api_key = st.secrets["OPENAI_API_KEY"]
+tavily_api_key = st.secrets["TAVILY_API_KEY"]
+
+# Apply the asyncio patch from nest_asyncio if required
+nest_asyncio.apply()
+
+# Constants
+REPORT_TYPE = "research_report"  # Assuming this remains constant; modify as needed
+
+
+# Function to handle asynchronous calls
+def run_async(coroutine):
+    loop = asyncio.get_event_loop()
+    return loop.run_until_complete(coroutine)
+
+
+# Streamlit interface
+st.title("GPT Research Report Generator")
+
+# User inputs
+query = st.text_input(
+    "Enter your research query:",
+    "Extract all the information about how the ranking for internal links works.",
+)
+report_type = st.selectbox(
+    "Select report type:",
+    options=["research_report", "summary", "detailed_analysis"],
+    index=0,
+)
+sources = st.text_area("Enter source URLs (one per line if multiple):")
+
+# Processing the sources input into a list
+source_urls = [url.strip() for url in sources.split("\n") if url.strip()]
+
+# Button to generate report
+if st.button("Generate Report"):
+    if not query:
+        st.warning("Please enter a query to generate a report.")
+    else:
+        with st.spinner("Generating report..."):
+            # Fetch the report asynchronously
+            fetch_report_coroutine = fetch_report(
+                query, report_type, source_urls if source_urls else None
+            )
+            report = run_async(fetch_report_coroutine)
+            st.success("Report generated successfully!")
+            st.write(report)