Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,16 +1,24 @@
|
|
| 1 |
-
import streamlit as st
|
| 2 |
import os
|
| 3 |
-
|
|
|
|
| 4 |
import asyncio
|
| 5 |
import nest_asyncio
|
|
|
|
|
|
|
|
|
|
| 6 |
from contextlib import redirect_stdout
|
| 7 |
-
|
|
|
|
| 8 |
from fpdf import FPDF
|
| 9 |
-
from
|
| 10 |
-
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
#
|
| 14 |
def get_version(package_name, module=None):
|
| 15 |
try:
|
| 16 |
if module and hasattr(module, '__version__'):
|
|
@@ -18,71 +26,28 @@ def get_version(package_name, module=None):
|
|
| 18 |
else:
|
| 19 |
version = importlib.metadata.version(package_name)
|
| 20 |
print(f"{package_name} version: {version}")
|
| 21 |
-
except
|
| 22 |
-
|
| 23 |
-
except importlib.metadata.PackageNotFoundError:
|
| 24 |
-
print(f"{package_name} is not installed.")
|
| 25 |
|
| 26 |
-
# Check versions
|
| 27 |
get_version('streamlit', st)
|
| 28 |
get_version('gpt_researcher')
|
| 29 |
get_version('nest_asyncio', nest_asyncio)
|
| 30 |
get_version('fpdf')
|
| 31 |
|
| 32 |
-
# For standard library modules
|
| 33 |
-
standard_libs = ['os', 'asyncio', 'contextlib', 'io', 'datetime', 'uuid']
|
| 34 |
print("\nStandard Library Modules:")
|
| 35 |
-
for lib in
|
| 36 |
-
print(f"{lib} is part of the Python Standard Library
|
| 37 |
-
|
| 38 |
-
|
| 39 |
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
# Apply nest_asyncio for asyncio support in Streamlit
|
| 44 |
nest_asyncio.apply()
|
| 45 |
|
| 46 |
-
# Load API keys from environment variables
|
| 47 |
openai_api_key = os.getenv("OPENAI_API_KEY")
|
| 48 |
tavily_api_key = os.getenv("TAVILY_API_KEY")
|
| 49 |
-
|
| 50 |
-
# Check if the API keys are available
|
| 51 |
if not openai_api_key or not tavily_api_key:
|
| 52 |
-
st.error("API keys for OpenAI or Tavily are not set in the environment variables.
|
| 53 |
-
|
| 54 |
-
# Define the asynchronous function to get the report and capture logs
|
| 55 |
-
async def get_report(query: str, report_type: str, sources: list, report_source: str):
|
| 56 |
-
f = io.StringIO()
|
| 57 |
-
unique_key = str(uuid.uuid4()) # Generate a unique key for this run
|
| 58 |
-
|
| 59 |
-
with redirect_stdout(f):
|
| 60 |
-
if report_source == 'local':
|
| 61 |
-
# Set the DOC_PATH environment variable
|
| 62 |
-
os.environ['DOC_PATH'] = './uploads'
|
| 63 |
-
researcher = GPTResearcher(query=query, report_type=report_type, report_source=report_source)
|
| 64 |
-
else:
|
| 65 |
-
researcher = GPTResearcher(query=query, report_type=report_type, source_urls=sources)
|
| 66 |
-
|
| 67 |
-
await researcher.conduct_research()
|
| 68 |
-
|
| 69 |
-
max_attempts = 30 # Prevent infinite loop
|
| 70 |
-
attempts = 0
|
| 71 |
-
while attempts < max_attempts:
|
| 72 |
-
logs = f.getvalue()
|
| 73 |
-
|
| 74 |
-
# Break condition
|
| 75 |
-
if "Finalized research step" in logs:
|
| 76 |
-
break
|
| 77 |
-
|
| 78 |
-
await asyncio.sleep(1) # Update every second
|
| 79 |
-
attempts += 1
|
| 80 |
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
return report, logs
|
| 84 |
-
|
| 85 |
-
# Function to create PDF using fpdf with UTF-8 encoding
|
| 86 |
class PDF(FPDF):
|
| 87 |
def header(self):
|
| 88 |
self.set_font("Arial", "B", 12)
|
|
@@ -93,143 +58,144 @@ class PDF(FPDF):
|
|
| 93 |
self.set_font("Arial", "I", 8)
|
| 94 |
self.cell(0, 10, f"Page {self.page_no()}", 0, 0, "C")
|
| 95 |
|
| 96 |
-
def
|
| 97 |
pdf = PDF()
|
| 98 |
pdf.add_page()
|
| 99 |
pdf.set_auto_page_break(auto=True, margin=15)
|
| 100 |
pdf.set_font("Arial", size=12)
|
| 101 |
-
|
| 102 |
for line in report_text.split('\n'):
|
|
|
|
| 103 |
pdf.multi_cell(0, 10, line.encode('latin-1', 'replace').decode('latin-1'))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
|
| 105 |
-
|
| 106 |
|
| 107 |
-
#
|
| 108 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 109 |
|
|
|
|
|
|
|
|
|
|
| 110 |
st.title("GPT Researcher")
|
| 111 |
st.markdown("""
|
| 112 |
GPT Researcher is an autonomous agent designed for comprehensive online research tasks. It pulls information from the web or uploaded documents to create detailed, factual, research reports.
|
| 113 |
""")
|
|
|
|
| 114 |
with st.expander("Why Use GPT Researcher?", expanded=False):
|
| 115 |
st.markdown("""
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
For more details, visit the [GPT Researcher GitHub repository](https://github.com/assafelovic/gpt-researcher).
|
| 122 |
""")
|
| 123 |
|
| 124 |
-
# Custom CSS for styling the input label
|
| 125 |
st.markdown(
|
| 126 |
"""
|
| 127 |
<style>
|
| 128 |
-
.big-green-font {
|
| 129 |
-
|
| 130 |
-
font-weight: bold;
|
| 131 |
-
color: green;
|
| 132 |
-
margin-bottom: -10px;
|
| 133 |
-
}
|
| 134 |
-
.stTextInput > div > input {
|
| 135 |
-
margin-top: -25px;
|
| 136 |
-
}
|
| 137 |
</style>
|
| 138 |
""",
|
| 139 |
unsafe_allow_html=True,
|
| 140 |
)
|
| 141 |
|
| 142 |
st.markdown('<p class="big-green-font">Enter your research query:</p>', unsafe_allow_html=True)
|
| 143 |
-
|
| 144 |
-
# Default query with current context
|
| 145 |
default_query = "Why is the Stock Price of Nvidia Soaring?"
|
| 146 |
-
|
| 147 |
-
# Display the input field for the user
|
| 148 |
user_query = st.text_input("", default_query, help="Type your research question or topic.")
|
| 149 |
|
| 150 |
-
# Process the query to include the current date after the user inputs their query
|
| 151 |
if user_query:
|
| 152 |
current_date = datetime.now().strftime("%B %Y")
|
| 153 |
final_query = f"{user_query} Current Date is {current_date}"
|
|
|
|
|
|
|
| 154 |
|
| 155 |
st.sidebar.title("Research Settings")
|
| 156 |
-
|
| 157 |
with st.sidebar.expander("How to Use", expanded=False):
|
| 158 |
st.markdown("""
|
| 159 |
-
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
5. **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.
|
| 165 |
""")
|
| 166 |
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
report_type = st.selectbox("Select report type:", ["research_report", "resource_list", "article_outline"], help="Choose the format of the final report.")
|
| 170 |
-
|
| 171 |
-
if research_type == "Web Research":
|
| 172 |
-
sources_input = st.text_area("Enter your sources (optional, comma-separated URLs):", help="Provide a list of URLs to use as sources, separated by commas.")
|
| 173 |
-
sources = [url.strip() for url in sources_input.split(',') if url.strip()]
|
| 174 |
-
else:
|
| 175 |
-
uploaded_files = st.file_uploader("Upload files for local research:", accept_multiple_files=True, help="Upload documents for the research.")
|
| 176 |
-
sources = []
|
| 177 |
-
if uploaded_files:
|
| 178 |
-
os.makedirs("uploads", exist_ok=True)
|
| 179 |
-
for uploaded_file in uploaded_files:
|
| 180 |
-
file_path = os.path.join("uploads", uploaded_file.name)
|
| 181 |
-
with open(file_path, "wb") as f:
|
| 182 |
-
f.write(uploaded_file.getbuffer())
|
| 183 |
-
|
| 184 |
-
if st.button("Run Research"):
|
| 185 |
-
if not user_query:
|
| 186 |
-
st.warning("Please enter a research query.")
|
| 187 |
-
else:
|
| 188 |
-
# Set the retriever environment variable (using Tavily in this case)
|
| 189 |
-
os.environ['RETRIEVER'] = 'tavily'
|
| 190 |
-
|
| 191 |
-
report_source = 'local' if research_type == "Document Research" else 'web'
|
| 192 |
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
st.session_state.report = report
|
| 197 |
-
st.session_state.logs = logs
|
| 198 |
|
| 199 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 200 |
if 'report' in st.session_state:
|
| 201 |
st.markdown("### Research Report")
|
| 202 |
st.markdown(st.session_state.report)
|
| 203 |
-
|
| 204 |
-
#
|
| 205 |
-
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
|
| 212 |
-
|
| 213 |
-
file_name="report.pdf",
|
| 214 |
-
mime="application/pdf"
|
| 215 |
-
)
|
| 216 |
|
| 217 |
st.markdown("### Agent Logs")
|
| 218 |
-
|
| 219 |
-
|
| 220 |
-
|
| 221 |
-
|
| 222 |
-
|
| 223 |
-
|
| 224 |
-
st.text_area("Logs will appear here during the research process",
|
| 225 |
-
height=200,
|
| 226 |
-
key=f"logs_{uuid.uuid4()}")
|
| 227 |
|
| 228 |
-
# Hide Streamlit
|
| 229 |
-
|
| 230 |
<style>
|
| 231 |
#MainMenu {visibility: hidden;}
|
| 232 |
footer {visibility: hidden;}
|
| 233 |
</style>
|
| 234 |
-
"""
|
| 235 |
-
st.markdown(hide_streamlit_style, unsafe_allow_html=True)
|
|
|
|
|
|
|
| 1 |
import os
|
| 2 |
+
import io
|
| 3 |
+
import uuid
|
| 4 |
import asyncio
|
| 5 |
import nest_asyncio
|
| 6 |
+
import importlib.metadata
|
| 7 |
+
import tempfile
|
| 8 |
+
from datetime import datetime
|
| 9 |
from contextlib import redirect_stdout
|
| 10 |
+
|
| 11 |
+
import streamlit as st
|
| 12 |
from fpdf import FPDF
|
| 13 |
+
from gpt_researcher import GPTResearcher
|
| 14 |
+
|
| 15 |
+
# ---------- sensible defaults to avoid KeyError in gpt_researcher ----------
|
| 16 |
+
os.environ.setdefault("LLM_PROVIDER", "openai")
|
| 17 |
+
os.environ.setdefault("EMBEDDING_PROVIDER", "openai")
|
| 18 |
+
os.environ.setdefault("EMBEDDING_MODEL", "text-embedding-3-small")
|
| 19 |
+
# you'll set RETRIEVER later to 'tavily'
|
| 20 |
|
| 21 |
+
# ---------- version printing (optional) ----------
|
| 22 |
def get_version(package_name, module=None):
|
| 23 |
try:
|
| 24 |
if module and hasattr(module, '__version__'):
|
|
|
|
| 26 |
else:
|
| 27 |
version = importlib.metadata.version(package_name)
|
| 28 |
print(f"{package_name} version: {version}")
|
| 29 |
+
except Exception:
|
| 30 |
+
pass
|
|
|
|
|
|
|
| 31 |
|
|
|
|
| 32 |
get_version('streamlit', st)
|
| 33 |
get_version('gpt_researcher')
|
| 34 |
get_version('nest_asyncio', nest_asyncio)
|
| 35 |
get_version('fpdf')
|
| 36 |
|
|
|
|
|
|
|
| 37 |
print("\nStandard Library Modules:")
|
| 38 |
+
for lib in ['os','asyncio','contextlib','io','datetime','uuid','tempfile']:
|
| 39 |
+
print(f"{lib} is part of the Python Standard Library.")
|
|
|
|
|
|
|
| 40 |
|
| 41 |
+
# ---------- streamlit setup ----------
|
| 42 |
+
st.set_page_config(layout="wide")
|
|
|
|
|
|
|
| 43 |
nest_asyncio.apply()
|
| 44 |
|
|
|
|
| 45 |
openai_api_key = os.getenv("OPENAI_API_KEY")
|
| 46 |
tavily_api_key = os.getenv("TAVILY_API_KEY")
|
|
|
|
|
|
|
| 47 |
if not openai_api_key or not tavily_api_key:
|
| 48 |
+
st.error("API keys for OpenAI or Tavily are not set in the environment variables.")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
+
# ---------- PDF helpers (in-memory, no filesystem writes) ----------
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
class PDF(FPDF):
|
| 52 |
def header(self):
|
| 53 |
self.set_font("Arial", "B", 12)
|
|
|
|
| 58 |
self.set_font("Arial", "I", 8)
|
| 59 |
self.cell(0, 10, f"Page {self.page_no()}", 0, 0, "C")
|
| 60 |
|
| 61 |
+
def create_pdf_bytes(report_text: str) -> bytes:
|
| 62 |
pdf = PDF()
|
| 63 |
pdf.add_page()
|
| 64 |
pdf.set_auto_page_break(auto=True, margin=15)
|
| 65 |
pdf.set_font("Arial", size=12)
|
|
|
|
| 66 |
for line in report_text.split('\n'):
|
| 67 |
+
# keep compatibility with latin-1 fonts
|
| 68 |
pdf.multi_cell(0, 10, line.encode('latin-1', 'replace').decode('latin-1'))
|
| 69 |
+
# dest='S' returns a latin-1 str; encode to bytes for download
|
| 70 |
+
return pdf.output(dest='S').encode('latin-1')
|
| 71 |
+
|
| 72 |
+
# ---------- async research ----------
|
| 73 |
+
async def get_report(query: str, report_type: str, sources: list, report_source: str, doc_dir: str):
|
| 74 |
+
f = io.StringIO()
|
| 75 |
+
with redirect_stdout(f):
|
| 76 |
+
if report_source == 'local':
|
| 77 |
+
os.environ['DOC_PATH'] = doc_dir # ensure gpt_researcher looks in /tmp/uploads
|
| 78 |
+
researcher = GPTResearcher(query=query, report_type=report_type, report_source='local')
|
| 79 |
+
else:
|
| 80 |
+
researcher = GPTResearcher(query=query, report_type=report_type, source_urls=sources)
|
| 81 |
|
| 82 |
+
await researcher.conduct_research()
|
| 83 |
|
| 84 |
+
# simple loop to let logs flush
|
| 85 |
+
for _ in range(30):
|
| 86 |
+
logs = f.getvalue()
|
| 87 |
+
if "Finalized research step" in logs:
|
| 88 |
+
break
|
| 89 |
+
await asyncio.sleep(1)
|
| 90 |
+
|
| 91 |
+
report = await researcher.write_report()
|
| 92 |
|
| 93 |
+
return report, f.getvalue()
|
| 94 |
+
|
| 95 |
+
# ---------- UI ----------
|
| 96 |
st.title("GPT Researcher")
|
| 97 |
st.markdown("""
|
| 98 |
GPT Researcher is an autonomous agent designed for comprehensive online research tasks. It pulls information from the web or uploaded documents to create detailed, factual, research reports.
|
| 99 |
""")
|
| 100 |
+
|
| 101 |
with st.expander("Why Use GPT Researcher?", expanded=False):
|
| 102 |
st.markdown("""
|
| 103 |
+
- **Objective and Unbiased**: Delivers accurate, factual information.
|
| 104 |
+
- **Time-Efficient**: Reduces manual research time.
|
| 105 |
+
- **Up-to-Date**: Minimizes outdated info and hallucinations.
|
| 106 |
+
- **Comprehensive**: Can produce long, detailed reports (2,000+ words).
|
| 107 |
+
- **Reduced Misinformation**: Considers multiple sources.
|
|
|
|
| 108 |
""")
|
| 109 |
|
|
|
|
| 110 |
st.markdown(
|
| 111 |
"""
|
| 112 |
<style>
|
| 113 |
+
.big-green-font { font-size:20px !important; font-weight:bold; color: green; margin-bottom:-10px; }
|
| 114 |
+
.stTextInput > div > input { margin-top:-25px; }
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
</style>
|
| 116 |
""",
|
| 117 |
unsafe_allow_html=True,
|
| 118 |
)
|
| 119 |
|
| 120 |
st.markdown('<p class="big-green-font">Enter your research query:</p>', unsafe_allow_html=True)
|
|
|
|
|
|
|
| 121 |
default_query = "Why is the Stock Price of Nvidia Soaring?"
|
|
|
|
|
|
|
| 122 |
user_query = st.text_input("", default_query, help="Type your research question or topic.")
|
| 123 |
|
|
|
|
| 124 |
if user_query:
|
| 125 |
current_date = datetime.now().strftime("%B %Y")
|
| 126 |
final_query = f"{user_query} Current Date is {current_date}"
|
| 127 |
+
else:
|
| 128 |
+
final_query = None
|
| 129 |
|
| 130 |
st.sidebar.title("Research Settings")
|
|
|
|
| 131 |
with st.sidebar.expander("How to Use", expanded=False):
|
| 132 |
st.markdown("""
|
| 133 |
+
1. **Select Research Type**: Web or Document Research.
|
| 134 |
+
2. **Enter Research Query**.
|
| 135 |
+
3. **Choose Report Type**.
|
| 136 |
+
4. **Provide Sources or Upload Files**.
|
| 137 |
+
5. **Run Research** and download the PDF.
|
|
|
|
| 138 |
""")
|
| 139 |
|
| 140 |
+
research_type = st.sidebar.selectbox("Select research type:", ["Web Research", "Document Research"])
|
| 141 |
+
report_type = st.sidebar.selectbox("Select report type:", ["research_report", "resource_list", "article_outline"])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 142 |
|
| 143 |
+
# use a guaranteed-writable location
|
| 144 |
+
UPLOAD_DIR = os.path.join(tempfile.gettempdir(), "uploads")
|
| 145 |
+
os.makedirs(UPLOAD_DIR, exist_ok=True)
|
|
|
|
|
|
|
| 146 |
|
| 147 |
+
if research_type == "Web Research":
|
| 148 |
+
sources_input = st.sidebar.text_area("Enter your sources (optional, comma-separated URLs):")
|
| 149 |
+
sources = [u.strip() for u in sources_input.split(',') if u.strip()]
|
| 150 |
+
else:
|
| 151 |
+
uploaded_files = st.sidebar.file_uploader("Upload files for local research:", accept_multiple_files=True)
|
| 152 |
+
sources = []
|
| 153 |
+
if uploaded_files:
|
| 154 |
+
for uploaded_file in uploaded_files:
|
| 155 |
+
with open(os.path.join(UPLOAD_DIR, uploaded_file.name), "wb") as f:
|
| 156 |
+
f.write(uploaded_file.getbuffer())
|
| 157 |
+
|
| 158 |
+
run_clicked = st.sidebar.button("Run Research")
|
| 159 |
+
|
| 160 |
+
if run_clicked:
|
| 161 |
+
if not final_query:
|
| 162 |
+
st.warning("Please enter a research query.")
|
| 163 |
+
else:
|
| 164 |
+
# set retriever
|
| 165 |
+
os.environ['RETRIEVER'] = 'tavily'
|
| 166 |
+
report_source = 'local' if research_type == "Document Research" else 'web'
|
| 167 |
+
with st.spinner("Running research..."):
|
| 168 |
+
report, logs = asyncio.run(get_report(final_query, report_type, sources, report_source, UPLOAD_DIR))
|
| 169 |
+
st.session_state.report = report
|
| 170 |
+
st.session_state.logs = logs
|
| 171 |
+
|
| 172 |
+
# ---------- outputs ----------
|
| 173 |
if 'report' in st.session_state:
|
| 174 |
st.markdown("### Research Report")
|
| 175 |
st.markdown(st.session_state.report)
|
| 176 |
+
|
| 177 |
+
# in-memory PDF (no filesystem writes)
|
| 178 |
+
pdf_bytes = create_pdf_bytes(st.session_state.report)
|
| 179 |
+
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
| 180 |
+
st.download_button(
|
| 181 |
+
label="Download report as PDF",
|
| 182 |
+
data=pdf_bytes,
|
| 183 |
+
file_name=f"report_{timestamp}.pdf",
|
| 184 |
+
mime="application/pdf",
|
| 185 |
+
)
|
|
|
|
|
|
|
|
|
|
| 186 |
|
| 187 |
st.markdown("### Agent Logs")
|
| 188 |
+
st.text_area(
|
| 189 |
+
"Logs will appear here during the research process:",
|
| 190 |
+
value=st.session_state.get('logs', ''),
|
| 191 |
+
height=200,
|
| 192 |
+
key=f"logs_{uuid.uuid4()}",
|
| 193 |
+
)
|
|
|
|
|
|
|
|
|
|
| 194 |
|
| 195 |
+
# Hide Streamlit UI chrome
|
| 196 |
+
st.markdown("""
|
| 197 |
<style>
|
| 198 |
#MainMenu {visibility: hidden;}
|
| 199 |
footer {visibility: hidden;}
|
| 200 |
</style>
|
| 201 |
+
""", unsafe_allow_html=True)
|
|
|