mirror of
https://github.com/The-Pocket/PocketFlow-Tutorial-Codebase-Knowledge.git
synced 2026-08-29 08:34:31 +08:00
fix: improve file filtering, add new utility,
- Improved the speed of file filtering in `crawl_local_files.py` with folder-level exclusion - Added `fix_yaml.py` utility for YAML indentation fixes - Updated `nodes.py` to support up to 20 core abstractions - add option for no cache.
This commit is contained in:
remy
+109
-27
@@ -3,86 +3,93 @@ import os
|
||||
import logging
|
||||
import json
|
||||
from datetime import datetime
|
||||
import requests
|
||||
|
||||
# Configure logging
|
||||
log_directory = os.getenv("LOG_DIR", "logs")
|
||||
os.makedirs(log_directory, exist_ok=True)
|
||||
log_file = os.path.join(log_directory, f"llm_calls_{datetime.now().strftime('%Y%m%d')}.log")
|
||||
log_file = os.path.join(
|
||||
log_directory, f"llm_calls_{datetime.now().strftime('%Y%m%d')}.log"
|
||||
)
|
||||
|
||||
# Set up logger
|
||||
logger = logging.getLogger("llm_logger")
|
||||
logger.setLevel(logging.INFO)
|
||||
logger.propagate = False # Prevent propagation to root logger
|
||||
file_handler = logging.FileHandler(log_file)
|
||||
file_handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s'))
|
||||
file_handler.setFormatter(
|
||||
logging.Formatter("%(asctime)s - %(levelname)s - %(message)s")
|
||||
)
|
||||
logger.addHandler(file_handler)
|
||||
|
||||
# Simple cache configuration
|
||||
cache_file = "llm_cache.json"
|
||||
|
||||
|
||||
# By default, we Google Gemini 2.5 pro, as it shows great performance for code understanding
|
||||
def call_llm(prompt: str, use_cache: bool = True) -> str:
|
||||
# Log the prompt
|
||||
logger.info(f"PROMPT: {prompt}")
|
||||
|
||||
|
||||
# Check cache if enabled
|
||||
if use_cache:
|
||||
# Load cache from disk
|
||||
cache = {}
|
||||
if os.path.exists(cache_file):
|
||||
try:
|
||||
with open(cache_file, 'r') as f:
|
||||
with open(cache_file, "r") as f:
|
||||
cache = json.load(f)
|
||||
except:
|
||||
logger.warning(f"Failed to load cache, starting with empty cache")
|
||||
|
||||
|
||||
# Return from cache if exists
|
||||
if prompt in cache:
|
||||
logger.info(f"RESPONSE: {cache[prompt]}")
|
||||
return cache[prompt]
|
||||
|
||||
|
||||
# Call the LLM if not in cache or cache disabled
|
||||
client = genai.Client(
|
||||
vertexai=True,
|
||||
# TODO: change to your own project id and location
|
||||
project=os.getenv("GEMINI_PROJECT_ID", "your-project-id"),
|
||||
location=os.getenv("GEMINI_LOCATION", "us-central1")
|
||||
)
|
||||
# You can comment the previous line and use the AI Studio key instead:
|
||||
# client = genai.Client(
|
||||
# api_key=os.getenv("GEMINI_API_KEY", "your-api_key"),
|
||||
# vertexai=True,
|
||||
# # TODO: change to your own project id and location
|
||||
# project=os.getenv("GEMINI_PROJECT_ID", "your-project-id"),
|
||||
# location=os.getenv("GEMINI_LOCATION", "us-central1")
|
||||
# )
|
||||
model = os.getenv("GEMINI_MODEL", "gemini-2.5-pro-exp-03-25")
|
||||
response = client.models.generate_content(
|
||||
model=model,
|
||||
contents=[prompt]
|
||||
|
||||
# You can comment the previous line and use the AI Studio key instead:
|
||||
client = genai.Client(
|
||||
api_key=os.getenv("GEMINI_API_KEY", ""),
|
||||
)
|
||||
response_text = response.text
|
||||
# model = os.getenv("GEMINI_MODEL", "gemini-2.5-pro-exp-03-25")
|
||||
model = os.getenv("GEMINI_MODEL", "gemini-2.0-flash-exp")
|
||||
|
||||
response = client.models.generate_content(model=model, contents=[prompt])
|
||||
response_text = response.text
|
||||
|
||||
# Log the response
|
||||
logger.info(f"RESPONSE: {response_text}")
|
||||
|
||||
|
||||
# Update cache if enabled
|
||||
if use_cache:
|
||||
# Load cache again to avoid overwrites
|
||||
cache = {}
|
||||
if os.path.exists(cache_file):
|
||||
try:
|
||||
with open(cache_file, 'r') as f:
|
||||
with open(cache_file, "r") as f:
|
||||
cache = json.load(f)
|
||||
except:
|
||||
pass
|
||||
|
||||
|
||||
# Add to cache and save
|
||||
cache[prompt] = response_text
|
||||
try:
|
||||
with open(cache_file, 'w') as f:
|
||||
with open(cache_file, "w") as f:
|
||||
json.dump(cache, f)
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to save cache: {e}")
|
||||
|
||||
|
||||
return response_text
|
||||
|
||||
|
||||
# # Use Anthropic Claude 3.7 Sonnet Extended Thinking
|
||||
# def call_llm(prompt, use_cache: bool = True):
|
||||
# from anthropic import Anthropic
|
||||
@@ -101,7 +108,7 @@ def call_llm(prompt: str, use_cache: bool = True) -> str:
|
||||
# return response.content[1].text
|
||||
|
||||
# # Use OpenAI o1
|
||||
# def call_llm(prompt, use_cache: bool = True):
|
||||
# def call_llm(prompt, use_cache: bool = True):
|
||||
# from openai import OpenAI
|
||||
# client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY", "your-api-key"))
|
||||
# r = client.chat.completions.create(
|
||||
@@ -115,11 +122,86 @@ def call_llm(prompt: str, use_cache: bool = True) -> str:
|
||||
# )
|
||||
# return r.choices[0].message.content
|
||||
|
||||
# Use OpenRouter API
|
||||
# def call_llm(prompt: str, use_cache: bool = True) -> str:
|
||||
# # Log the prompt
|
||||
# logger.info(f"PROMPT: {prompt}")
|
||||
|
||||
# # Check cache if enabled
|
||||
# if use_cache:
|
||||
# # Load cache from disk
|
||||
# cache = {}
|
||||
# if os.path.exists(cache_file):
|
||||
# try:
|
||||
# with open(cache_file, "r") as f:
|
||||
# cache = json.load(f)
|
||||
# except:
|
||||
# logger.warning(f"Failed to load cache, starting with empty cache")
|
||||
|
||||
# # Return from cache if exists
|
||||
# if prompt in cache:
|
||||
# logger.info(f"RESPONSE: {cache[prompt]}")
|
||||
# return cache[prompt]
|
||||
|
||||
# # OpenRouter API configuration
|
||||
# api_key = os.getenv("OPENROUTER_API_KEY", "")
|
||||
# model = os.getenv("OPENROUTER_MODEL", "google/gemini-2.0-flash-exp:free")
|
||||
|
||||
# headers = {
|
||||
# "Authorization": f"Bearer {api_key}",
|
||||
# }
|
||||
|
||||
# data = {
|
||||
# "model": model,
|
||||
# "messages": [{"role": "user", "content": prompt}]
|
||||
# }
|
||||
|
||||
# response = requests.post(
|
||||
# "https://openrouter.ai/api/v1/chat/completions",
|
||||
# headers=headers,
|
||||
# json=data
|
||||
# )
|
||||
|
||||
# if response.status_code != 200:
|
||||
# error_msg = f"OpenRouter API call failed with status {response.status_code}: {response.text}"
|
||||
# logger.error(error_msg)
|
||||
# raise Exception(error_msg)
|
||||
# try:
|
||||
# response_text = response.json()["choices"][0]["message"]["content"]
|
||||
# except Exception as e:
|
||||
# error_msg = f"Failed to parse OpenRouter response: {e}; Response: {response.text}"
|
||||
# logger.error(error_msg)
|
||||
# raise Exception(error_msg)
|
||||
|
||||
|
||||
# # Log the response
|
||||
# logger.info(f"RESPONSE: {response_text}")
|
||||
|
||||
# # Update cache if enabled
|
||||
# if use_cache:
|
||||
# # Load cache again to avoid overwrites
|
||||
# cache = {}
|
||||
# if os.path.exists(cache_file):
|
||||
# try:
|
||||
# with open(cache_file, "r") as f:
|
||||
# cache = json.load(f)
|
||||
# except:
|
||||
# pass
|
||||
|
||||
# # Add to cache and save
|
||||
# cache[prompt] = response_text
|
||||
# try:
|
||||
# with open(cache_file, "w") as f:
|
||||
# json.dump(cache, f)
|
||||
# except Exception as e:
|
||||
# logger.error(f"Failed to save cache: {e}")
|
||||
|
||||
# return response_text
|
||||
|
||||
if __name__ == "__main__":
|
||||
test_prompt = "Hello, how are you?"
|
||||
|
||||
|
||||
# First call - should hit the API
|
||||
print("Making call...")
|
||||
response1 = call_llm(test_prompt, use_cache=False)
|
||||
print(f"Response: {response1}")
|
||||
|
||||
|
||||
Reference in New Issue
Block a user