Create app.py

app.py

@@ -0,0 +1,153 @@
+import streamlit as st
+import os
+from gpt_researcher import GPTResearcher
+import asyncio
+import nest_asyncio
+from contextlib import redirect_stdout
+import io
+from fpdf import FPDF
+
+# Apply nest_asyncio for asyncio support in Streamlit
+nest_asyncio.apply()
+
+# Define the asynchronous function to get the report and capture logs
+async def get_report(query: str, report_type: str, sources: list, report_source: str):
+    f = io.StringIO()
+    logs_container = st.empty()
+    with redirect_stdout(f):
+        if report_source == 'local':
+            # Set the DOC_PATH environment variable
+            os.environ['DOC_PATH'] = './uploads'
+            researcher = GPTResearcher(query=query, report_type=report_type, report_source=report_source)
+        else:
+            researcher = GPTResearcher(query=query, report_type=report_type, source_urls=sources)
+
+        await researcher.conduct_research()
+
+        while True:
+            logs = f.getvalue()
+            logs_container.text_area("Agent Logs", logs, height=200)
+            await asyncio.sleep(1)  # Update every second
+            if "Finalized research step" in logs:
+                break
+
+        report = await researcher.write_report()
+    return report, f.getvalue()
+
+# Function to create PDF using fpdf with UTF-8 encoding
+class PDF(FPDF):
+    def header(self):
+        self.set_font("Arial", "B", 12)
+        self.cell(0, 10, "Research Report", 0, 1, "C")
+
+    def footer(self):
+        self.set_y(-15)
+        self.set_font("Arial", "I", 8)
+        self.cell(0, 10, f"Page {self.page_no()}", 0, 0, "C")
+
+    def chapter_title(self, title):
+        self.set_font("Arial", "B", 12)
+        self.cell(0, 10, title, 0, 1, "L")
+        self.ln(5)
+
+    def chapter_body(self, body):
+        self.set_font("Arial", "", 12)
+        self.multi_cell(0, 10, body)
+        self.ln()
+
+def create_pdf(report_text, pdf_path):
+    pdf = PDF()
+    pdf.add_page()
+    pdf.set_auto_page_break(auto=True, margin=15)
+    pdf.set_font("Arial", size=12)
+
+    for line in report_text.split('\n'):
+        pdf.multi_cell(0, 10, line.encode('latin-1', 'replace').decode('latin-1'))
+
+    pdf.output(pdf_path, 'F')
+
+# Streamlit interface
+st.set_page_config(layout="wide")
+
+st.title("GPT Researcher")
+st.markdown("""
+### What is GPT Researcher?
+GPT Researcher is an app that uses GPT (Generative Pre-trained Transformer) to conduct research based on user queries. It can pull information from the web or from uploaded documents to create comprehensive research reports.
+
+### How to Use
+1. **Enter API Keys**: Provide your OpenAI and Tavily API keys in the sidebar.
+2. **Select Research Type**: Choose between Web Research and Document Research.
+3. **Enter Research Query**: Type in your research question or topic.
+4. **Choose Report Type**: Select the format of the report you want (research report, resource list, or article outline).
+5. **Provide Sources or Upload Files**: For Web Research, you can enter URLs. For Document Research, upload the necessary files.
+6. **Run Research**: Click the "Run Research" button to start. The logs will update in real-time, and the final report will be displayed and available for download as a PDF.
+
+""")
+
+with st.sidebar:
+    st.markdown("### API Keys")
+    openai_api_key = st.text_input("Enter your OpenAI API key:", "sk-proj-vFPqdrr801blzZCRBjztT3BlbkFJJJeQVcc62PA40cQ1S9Zv", type="password")
+    tavily_api_key = st.text_input("Enter your Tavily API key:", "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", type="password")
+
+    st.markdown("### Research Settings")
+    research_type = st.selectbox("Select research type:", ["Web Research", "Document Research"])
+    query = st.text_input("Enter your research query:", "What is the Latest in Investing using AI?")
+    report_type = st.selectbox("Select report type:", ["research_report", "resource_list", "article_outline"])
+
+    if research_type == "Web Research":
+        sources_input = st.text_area("Enter your sources (optional, comma-separated URLs):")
+        sources = [url.strip() for url in sources_input.split(',') if url.strip()]
+    else:
+        uploaded_files = st.file_uploader("Upload files for local research:", accept_multiple_files=True)
+        sources = []
+        if uploaded_files:
+            os.makedirs("uploads", exist_ok=True)
+            for uploaded_file in uploaded_files:
+                file_path = os.path.join("uploads", uploaded_file.name)
+                with open(file_path, "wb") as f:
+                    f.write(uploaded_file.getbuffer())
+
+    if st.button("Run Research"):
+        if not openai_api_key or not tavily_api_key:
+            st.warning("Please enter both API keys.")
+        elif not query:
+            st.warning("Please enter a research query.")
+        else:
+            # Set the API keys as environment variables
+            os.environ['OPENAI_API_KEY'] = openai_api_key
+            os.environ['TAVILY_API_KEY'] = tavily_api_key
+
+            # Set the retriever environment variable
+            os.environ['RETRIEVER'] = 'tavily'
+
+            report_source = 'local' if research_type == "Document Research" else 'web'
+
+            with st.spinner("Running research..."):
+                # Run the research and get the report and logs
+                report, logs = asyncio.run(get_report(query, report_type, sources, report_source))
+                st.session_state.report = report
+                st.session_state.logs = logs
+
+# Display outputs in the main section
+if 'report' in st.session_state:
+    st.markdown("### Research Report")
+    st.markdown(st.session_state.report)
+    
+    # Create PDF
+    pdf_path = "report.pdf"
+    create_pdf(st.session_state.report, pdf_path)
+    
+    # Provide download link for the PDF
+    with open(pdf_path, "rb") as pdf_file:
+        st.download_button(
+            label="Download report as PDF",
+            data=pdf_file,
+            file_name="report.pdf",
+            mime="application/pdf"
+        )
+
+st.markdown("### Agent Logs")
+if 'logs' in st.session_state:
+    st.text_area("Logs will appear here during the research process.", st.session_state.logs, height=200)
+else:
+    st.text_area("Logs will appear here during the research process.", height=200)