ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

refactor(llm): rename LlmConfig to LLMConfig for consistency

Browse Source 
Rename LlmConfig to LLMConfig across the codebase to follow consistent naming conventions.
Update all imports and usages to use the new name.
Update documentation and examples to reflect the change.

BREAKING CHANGE: LlmConfig has been renamed to LLMConfig. Users need to update their imports and usage.
This commit is contained in:
UncleCode
2025-03-05 14:17:04 +08:00
parent e896c08f9c
commit baee4949d3
33 changed files with 362 additions and 174 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/examples/extraction_strategies_examples.py
View File

@@ -11,7 +11,7 @@ import asyncio
import os
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
from crawl4ai.extraction_strategy import (
LLMExtractionStrategy,
JsonCssExtractionStrategy,
@@ -61,19 +61,19 @@ async def main():
# 1. LLM Extraction with different input formats
markdown_strategy = LLMExtractionStrategy(
llmConfig = LlmConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY")),
llm_config = LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY")),
instruction="Extract product information including name, price, and description",
)
html_strategy = LLMExtractionStrategy(
input_format="html",
llmConfig=LlmConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY")),
llm_config=LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY")),
instruction="Extract product information from HTML including structured data",
)
fit_markdown_strategy = LLMExtractionStrategy(
input_format="fit_markdown",
llmConfig=LlmConfig(provider="openai/gpt-4o-mini",api_token=os.getenv("OPENAI_API_KEY")),
llm_config=LLMConfig(provider="openai/gpt-4o-mini",api_token=os.getenv("OPENAI_API_KEY")),
instruction="Extract product information from cleaned markdown",
)

4
docs/examples/llm_extraction_openai_pricing.py
View File

@@ -1,4 +1,4 @@
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
from crawl4ai import AsyncWebCrawler, LLMExtractionStrategy
import asyncio
import os
@@ -23,7 +23,7 @@ async def main():
word_count_threshold=1,
extraction_strategy=LLMExtractionStrategy(
# provider= "openai/gpt-4o", api_token = os.getenv('OPENAI_API_KEY'),
llmConfig=LlmConfig(provider="groq/llama-3.1-70b-versatile", api_token=os.getenv("GROQ_API_KEY")),
llm_config=LLMConfig(provider="groq/llama-3.1-70b-versatile", api_token=os.getenv("GROQ_API_KEY")),
schema=OpenAIModelFee.model_json_schema(),
extraction_type="schema",
instruction="From the crawled content, extract all mentioned model names along with their "

6
docs/examples/llm_markdown_generator.py
View File

@@ -1,7 +1,7 @@
import os
import asyncio
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
from crawl4ai.content_filter_strategy import LLMContentFilter
async def test_llm_filter():
@@ -23,7 +23,7 @@ async def test_llm_filter():
# Initialize LLM filter with focused instruction
filter = LLMContentFilter(
llmConfig=LlmConfig(provider="openai/gpt-4o", api_token=os.getenv('OPENAI_API_KEY')),
llm_config=LLMConfig(provider="openai/gpt-4o", api_token=os.getenv('OPENAI_API_KEY')),
instruction="""
Focus on extracting the core educational content about Python classes.
Include:
@@ -43,7 +43,7 @@ async def test_llm_filter():
)
filter = LLMContentFilter(
llmConfig=LlmConfig(provider="openai/gpt-4o",api_token=os.getenv('OPENAI_API_KEY')),
llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv('OPENAI_API_KEY')),
chunk_token_threshold=2 ** 12 * 2, # 2048 * 2
ignore_cache = True,
instruction="""

4
docs/examples/quickstart_async.config.py
View File

@@ -1,6 +1,6 @@
import os, sys
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
sys.path.append(
os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
@@ -211,7 +211,7 @@ async def extract_structured_data_using_llm(
word_count_threshold=1,
page_timeout=80000,
extraction_strategy=LLMExtractionStrategy(
llmConfig=LlmConfig(provider=provider,api_token=api_token),
llm_config=LLMConfig(provider=provider,api_token=api_token),
schema=OpenAIModelFee.model_json_schema(),
extraction_type="schema",
instruction="""From the crawled content, extract all mentioned model names along with their fees for input and output tokens.

6
docs/examples/quickstart_async.py
View File

@@ -1,6 +1,6 @@
import os, sys
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
# append parent directory to system path
sys.path.append(
@@ -147,7 +147,7 @@ async def extract_structured_data_using_llm(
url="https://openai.com/api/pricing/",
word_count_threshold=1,
extraction_strategy=LLMExtractionStrategy(
llmConfig=LlmConfig(provider=provider,api_token=api_token),
llm_config=LLMConfig(provider=provider,api_token=api_token),
schema=OpenAIModelFee.model_json_schema(),
extraction_type="schema",
instruction="""From the crawled content, extract all mentioned model names along with their fees for input and output tokens.
@@ -570,7 +570,7 @@ async def generate_knowledge_graph():
relationships: List[Relationship]
extraction_strategy = LLMExtractionStrategy(
llmConfig=LlmConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY")), # In case of Ollama just pass "no-token"
llm_config=LLMConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI_API_KEY")), # In case of Ollama just pass "no-token"
schema=KnowledgeGraph.model_json_schema(),
extraction_type="schema",
instruction="""Extract entities and relationships from the given text.""",

8
docs/examples/quickstart_sync.py
View File

@@ -1,6 +1,6 @@
import os
import time
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
from crawl4ai.web_crawler import WebCrawler
from crawl4ai.chunking_strategy import *
from crawl4ai.extraction_strategy import *
@@ -179,7 +179,7 @@ def add_llm_extraction_strategy(crawler):
result = crawler.run(
url="https://www.nbcnews.com/business",
extraction_strategy=LLMExtractionStrategy(
llmConfig = LlmConfig(provider="openai/gpt-4o", api_token=os.getenv("OPENAI_API_KEY"))
llm_config = LLMConfig(provider="openai/gpt-4o", api_token=os.getenv("OPENAI_API_KEY"))
),
)
cprint(
@@ -198,7 +198,7 @@ def add_llm_extraction_strategy(crawler):
result = crawler.run(
url="https://www.nbcnews.com/business",
extraction_strategy=LLMExtractionStrategy(
llmConfig=LlmConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")),
llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")),
instruction="I am interested in only financial news",
),
)
@@ -210,7 +210,7 @@ def add_llm_extraction_strategy(crawler):
result = crawler.run(
url="https://www.nbcnews.com/business",
extraction_strategy=LLMExtractionStrategy(
llmConfig=LlmConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")),
llm_config=LLMConfig(provider="openai/gpt-4o",api_token=os.getenv("OPENAI_API_KEY")),
instruction="Extract only content related to technology",
),
)

18
docs/examples/tutorial_v0.5.py
View File

@@ -17,7 +17,7 @@ from crawl4ai.configs import ProxyConfig
from crawl4ai import RoundRobinProxyStrategy
from crawl4ai.content_filter_strategy import LLMContentFilter
from crawl4ai import DefaultMarkdownGenerator
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
from crawl4ai.processors.pdf import PDFCrawlerStrategy, PDFContentScrapingStrategy
from pprint import pprint
@@ -284,9 +284,9 @@ async def llm_content_filter():
PART 5: LLM Content Filter
This function demonstrates:
- Configuring LLM providers via LlmConfig
- Configuring LLM providers via LLMConfig
- Using LLM to generate focused markdown
- LlmConfig for configuration
- LLMConfig for configuration
Note: Requires a valid API key for the chosen LLM provider
"""
@@ -296,7 +296,7 @@ async def llm_content_filter():
# Create LLM configuration
# Replace with your actual API key or set as environment variable
llm_config = LlmConfig(
llm_config = LLMConfig(
provider="gemini/gemini-1.5-pro",
api_token="env:GEMINI_API_KEY" # Will read from GEMINI_API_KEY environment variable
)
@@ -309,7 +309,7 @@ async def llm_content_filter():
# Create markdown generator with LLM filter
markdown_generator = DefaultMarkdownGenerator(
content_filter=LLMContentFilter(
llmConfig=llm_config,
llm_config=llm_config,
instruction="Extract key concepts and summaries"
)
)
@@ -381,7 +381,7 @@ async def llm_schema_generation():
PART 7: LLM Schema Generation
This function demonstrates:
- Configuring LLM providers via LlmConfig
- Configuring LLM providers via LLMConfig
- Using LLM to generate extraction schemas
- JsonCssExtractionStrategy
@@ -406,9 +406,9 @@ async def llm_schema_generation():
<div class="rating">4.7/5</div>
</div>
"""
print("\n📊 Setting up LlmConfig...")
print("\n📊 Setting up LLMConfig...")
# Create LLM configuration
llm_config = LlmConfig(
llm_config = LLMConfig(
provider="gemini/gemini-1.5-pro",
api_token="env:GEMINI_API_KEY"
)
@@ -416,7 +416,7 @@ async def llm_schema_generation():
print(" This would use the LLM to analyze HTML and create an extraction schema")
schema = JsonCssExtractionStrategy.generate_schema(
html=sample_html,
llmConfig = llm_config,
llm_config = llm_config,
query="Extract product name and price"
)
print("\n✅ Generated Schema:")