Skip to content

refactor: consolidate imports and remove duplicates #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
naveen-malla wants to merge 1 commit into
base: main
Choose a base branch
from
Open

refactor: consolidate imports and remove duplicates #10

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
65 changes: 13 additions & 52 deletions src/research_tools.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,43 +1,21 @@
from typing import List, Dict
import requests
# Standard library imports
import os
import re
import time
import xml.etree.ElementTree as ET
from io import BytesIO
from typing import List, Dict, Optional
import os, re, tempfile
import requests
from pdfminer.high_level import extract_text

session = requests.Session()
session.headers.update(
{"User-Agent": "LF-ADP-Agent/1.0 (mailto:your.email@example.com)"}
)

## -----

from typing import List, Dict, Optional
import os, re, time, tempfile
# Third-party imports
import requests
import xml.etree.ElementTree as ET

# ----- Session with retries & headers -----
import wikipedia
from dotenv import load_dotenv
from requests.adapters import HTTPAdapter
from tavily import TavilyClient
from urllib3.util.retry import Retry

from typing import List, Dict, Optional
import os, re, time
import requests
import xml.etree.ElementTree as ET
from io import BytesIO


from typing import List, Dict, Optional
import os, re, time
import requests
import xml.etree.ElementTree as ET
from io import BytesIO

# ----- Session with retries & headers -----
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry
# Load environment variables
load_dotenv()


def _build_session(
Expand Down Expand Up @@ -83,8 +61,6 @@ def ensure_pdf_url(abs_or_pdf_url: str) -> str:


def _safe_filename(name: str) -> str:
import re

name = re.sub(r"[^A-Za-z0-9._-]+", "_", name)
if not name.lower().endswith(".pdf"):
name += ".pdf"
Expand Down Expand Up @@ -141,12 +117,6 @@ def maybe_save_pdf(pdf_bytes: bytes, dest_dir: str, filename: str) -> str:


# ----- arXiv search -----
from typing import List, Dict
import time, requests, xml.etree.ElementTree as ET
from io import BytesIO

# session = _build_session()
# ensure_pdf_url(), clean_text(), fetch_pdf_bytes(), pdf_bytes_to_text(), maybe_save_pdf()


def arxiv_search_tool(
Expand Down Expand Up @@ -264,14 +234,7 @@ def arxiv_search_tool(
}


## -----


import os
from dotenv import load_dotenv
from tavily import TavilyClient

load_dotenv() # Loads environment variables from a .env file
# ----- Tavily search (Web search) -----


def tavily_search_tool(
Expand Down Expand Up @@ -347,10 +310,8 @@ def tavily_search_tool(
},
}

## Wikipedia search tool

from typing import List, Dict
import wikipedia
# ----- Wikipedia search -----


def wikipedia_search_tool(query: str, sentences: int = 5) -> List[Dict]:
Expand Down