defer numpy, bs4 and jsonschema

aider/coders/base_coder.py

@@ -13,7 +13,6 @@ from json.decoder import JSONDecodeError
 from pathlib import Path
 
 import git
-from jsonschema import Draft7Validator
 from rich.console import Console, Text
 from rich.markdown import Markdown
 
@@ -346,6 +345,8 @@ class Coder:
 
         # validate the functions jsonschema
         if self.functions:
+            from jsonschema import Draft7Validator
+
             for function in self.functions:
                 Draft7Validator.check_schema(function)
 

aider/scrape.py

@@ -5,7 +5,6 @@ import sys
 
 import playwright
 import pypandoc
-from bs4 import BeautifulSoup
 from playwright.sync_api import sync_playwright
 
 from aider import __version__, urls
@@ -58,7 +57,6 @@ class Scraper:
         self.try_pandoc()
 
         content = self.html_to_markdown(content)
-        # content = html_to_text(content)
 
         return content
 
@@ -139,6 +137,8 @@ class Scraper:
         self.pandoc_available = True
 
     def html_to_markdown(self, page_source):
+        from bs4 import BeautifulSoup
+
         soup = BeautifulSoup(page_source, "html.parser")
         soup = slimdown_html(soup)
         page_source = str(soup)
@@ -174,24 +174,6 @@ def slimdown_html(soup):
     return soup
 
 
-# Adapted from AutoGPT, MIT License
-#
-# https://github.com/Significant-Gravitas/AutoGPT/blob/fe0923ba6c9abb42ac4df79da580e8a4391e0418/autogpts/autogpt/autogpt/commands/web_selenium.py#L173
-
-
-def html_to_text(page_source: str) -> str:
-    soup = BeautifulSoup(page_source, "html.parser")
-
-    for script in soup(["script", "style"]):
-        script.extract()
-
-    text = soup.get_text()
-    lines = (line.strip() for line in text.splitlines())
-    chunks = (phrase.strip() for line in lines for phrase in line.split("  "))
-    text = "\n".join(chunk for chunk in chunks if chunk)
-    return text
-
-
 def main(url):
     scraper = Scraper()
     content = scraper.scrape(url)

aider/voice.py

@@ -1,10 +1,9 @@
+import math
 import os
 import queue
 import tempfile
 import time
 
-import numpy as np
-
 from aider.litellm import litellm
 
 try:
@@ -41,6 +40,8 @@ class Voice:
 
     def callback(self, indata, frames, time, status):
         """This is called (from a separate thread) for each audio block."""
+        import numpy as np
+
         rms = np.sqrt(np.mean(indata**2))
         self.max_rms = max(self.max_rms, rms)
         self.min_rms = min(self.min_rms, rms)
@@ -55,7 +56,7 @@ class Voice:
 
     def get_prompt(self):
         num = 10
-        if np.isnan(self.pct) or self.pct < self.threshold:
+        if math.isnan(self.pct) or self.pct < self.threshold:
             cnt = 0
         else:
             cnt = int(self.pct * 10)
@@ -78,7 +79,7 @@ class Voice:
         filename = tempfile.mktemp(suffix=".wav")
 
         try:
-            sample_rate = int(self.sd.query_devices(None, 'input')['default_samplerate'])
+            sample_rate = int(self.sd.query_devices(None, "input")["default_samplerate"])
         except (TypeError, ValueError):
             sample_rate = 16000  # fallback to 16kHz if unable to query device