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

Merge branch 'vr0.5.0.post1' into next

Browse Source
This commit is contained in:
UncleCode
2025-03-05 14:17:19 +08:00
parent 9c58e4ce2e baee4949d3
commit b3ec7ce960
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:")

8
docs/md_v2/api/parameters.md
View File

@@ -245,8 +245,8 @@ run_config = CrawlerRunConfig(
)
```
# 3. **LlmConfig** - Setting up LLM providers
LlmConfig is useful to pass LLM provider config to strategies and functions that rely on LLMs to do extraction, filtering, schema generation etc. Currently it can be used in the following -
# 3. **LLMConfig** - Setting up LLM providers
LLMConfig is useful to pass LLM provider config to strategies and functions that rely on LLMs to do extraction, filtering, schema generation etc. Currently it can be used in the following -
1. LLMExtractionStrategy
2. LLMContentFilter
@@ -262,7 +262,7 @@ LlmConfig is useful to pass LLM provider config to strategies and functions that
## 3.2 Example Usage
```python
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"))
```
## 4. Putting It All Together
@@ -270,7 +270,7 @@ llmConfig = LlmConfig(provider="openai/gpt-4o-mini", api_token=os.getenv("OPENAI
- **Use** `BrowserConfig` for **global** browser settings: engine, headless, proxy, user agent.
- **Use** `CrawlerRunConfig` for each crawl’s **context**: how to filter content, handle caching, wait for dynamic elements, or run JS.
- **Pass** both configs to `AsyncWebCrawler` (the `BrowserConfig`) and then to `arun()` (the `CrawlerRunConfig`).
- **Use** `LlmConfig` for LLM provider configurations that can be used across all extraction, filtering, schema generation tasks. Can be used in - `LLMExtractionStrategy`, `LLMContentFilter`, `JsonCssExtractionStrategy.generate_schema` & `JsonXPathExtractionStrategy.generate_schema`
- **Use** `LLMConfig` for LLM provider configurations that can be used across all extraction, filtering, schema generation tasks. Can be used in - `LLMExtractionStrategy`, `LLMContentFilter`, `JsonCssExtractionStrategy.generate_schema` & `JsonXPathExtractionStrategy.generate_schema`
```python
# Create a modified copy with the clone() method

8
docs/md_v2/api/strategies.md
View File

@@ -131,7 +131,7 @@ OverlappingWindowChunking(
```python
from pydantic import BaseModel
from crawl4ai.extraction_strategy import LLMExtractionStrategy
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
# Define schema
class Article(BaseModel):
@@ -141,7 +141,7 @@ class Article(BaseModel):
# Create strategy
strategy = LLMExtractionStrategy(
llmConfig = LlmConfig(provider="ollama/llama2"),
llm_config = LLMConfig(provider="ollama/llama2"),
schema=Article.schema(),
instruction="Extract article details"
)
@@ -198,7 +198,7 @@ result = await crawler.arun(
```python
from crawl4ai.chunking_strategy import OverlappingWindowChunking
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
# Create chunking strategy
chunker = OverlappingWindowChunking(
@@ -208,7 +208,7 @@ chunker = OverlappingWindowChunking(
# Use with extraction strategy
strategy = LLMExtractionStrategy(
llmConfig = LlmConfig(provider="ollama/llama2"),
llm_config = LLMConfig(provider="ollama/llama2"),
chunking_strategy=chunker
)

4
docs/md_v2/blog/index.md
View File

@@ -16,7 +16,7 @@ My dear friends and crawlers, there you go, this is the release of Crawl4AI v0.5
* **Multiple Crawler Strategies:** Choose between the full-featured Playwright browser-based crawler or a new, *much* faster HTTP-only crawler for simpler tasks.
* **Docker Deployment:** Deploy Crawl4AI as a scalable, self-contained service with built-in API endpoints and optional JWT authentication.
* **Command-Line Interface (CLI):** Interact with Crawl4AI directly from your terminal. Crawl, configure, and extract data with simple commands.
* **LLM Configuration (`LlmConfig`):** A new, unified way to configure LLM providers (OpenAI, Anthropic, Ollama, etc.) for extraction, filtering, and schema generation. Simplifies API key management and switching between models.
* **LLM Configuration (`LLMConfig`):** A new, unified way to configure LLM providers (OpenAI, Anthropic, Ollama, etc.) for extraction, filtering, and schema generation. Simplifies API key management and switching between models.
**Minor Updates & Improvements:**
@@ -47,7 +47,7 @@ This release includes several breaking changes to improve the library's structur
* **Config**: FastFilterChain has been replaced with FilterChain
* **Deep-Crawl**: DeepCrawlStrategy.arun now returns Union[CrawlResultT, List[CrawlResultT], AsyncGenerator[CrawlResultT, None]]
* **Proxy**: Removed synchronous WebCrawler support and related rate limiting configurations
* **LLM Parameters:** Use the new `LlmConfig` object instead of passing `provider`, `api_token`, `base_url`, and `api_base` directly to `LLMExtractionStrategy` and `LLMContentFilter`.
* **LLM Parameters:** Use the new `LLMConfig` object instead of passing `provider`, `api_token`, `base_url`, and `api_base` directly to `LLMExtractionStrategy` and `LLMContentFilter`.
**In short:** Update imports, adjust `arun_many()` usage, check for optional fields, and review the Docker deployment guide.

24
docs/md_v2/blog/releases/0.5.0.md
View File

@@ -305,13 +305,13 @@ asyncio.run(main())
```python
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, DefaultMarkdownGenerator
from crawl4ai.content_filter_strategy import LLMContentFilter
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
import asyncio
llm_config = LlmConfig(provider="gemini/gemini-1.5-pro", api_token="env:GEMINI_API_KEY")
llm_config = LLMConfig(provider="gemini/gemini-1.5-pro", api_token="env:GEMINI_API_KEY")
markdown_generator = DefaultMarkdownGenerator(
content_filter=LLMContentFilter(llmConfig=llm_config, instruction="Extract key concepts and summaries")
content_filter=LLMContentFilter(llm_config=llm_config, instruction="Extract key concepts and summaries")
)
config = CrawlerRunConfig(markdown_generator=markdown_generator)
@@ -335,13 +335,13 @@ asyncio.run(main())
```python
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
llm_config = LlmConfig(provider="gemini/gemini-1.5-pro", api_token="env:GEMINI_API_KEY")
llm_config = LLMConfig(provider="gemini/gemini-1.5-pro", api_token="env:GEMINI_API_KEY")
schema = JsonCssExtractionStrategy.generate_schema(
html="<div class='product'><h2>Product Name</h2><span class='price'>$99</span></div>",
llmConfig = llm_config,
llm_config = llm_config,
query="Extract product name and price"
)
print(schema)
@@ -394,20 +394,20 @@ print(schema)
serialization, especially for sets of allowed/blocked domains. No code changes
required.
- **Added: New `LlmConfig` parameter.** This new parameter can be passed for
- **Added: New `LLMConfig` parameter.** This new parameter can be passed for
extraction, filtering, and schema generation tasks. It simplifies passing
provider strings, API tokens, and base URLs across all sections where LLM
configuration is necessary. It also enables reuse and allows for quick
experimentation between different LLM configurations.
```python
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
from crawl4ai.extraction_strategy import LLMExtractionStrategy
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
# Example of using LlmConfig with LLMExtractionStrategy
llm_config = LlmConfig(provider="openai/gpt-4o", api_token="YOUR_API_KEY")
strategy = LLMExtractionStrategy(llmConfig=llm_config, schema=...)
# Example of using LLMConfig with LLMExtractionStrategy
llm_config = LLMConfig(provider="openai/gpt-4o", api_token="YOUR_API_KEY")
strategy = LLMExtractionStrategy(llm_config=llm_config, schema=...)
# Example usage within a crawler
async with AsyncWebCrawler() as crawler:
@@ -418,7 +418,7 @@ print(schema)
```
**Breaking Change:** Removed old parameters like `provider`, `api_token`,
`base_url`, and `api_base` from `LLMExtractionStrategy` and
`LLMContentFilter`. Users should migrate to using the `LlmConfig` object.
`LLMContentFilter`. Users should migrate to using the `LLMConfig` object.
- **Changed: Improved browser context management and added shared data support.
(Breaking Change:** `BrowserContext` API updated). Browser contexts are now

18
docs/md_v2/core/browser-crawler-config.md
View File

@@ -4,7 +4,7 @@ Crawl4AI’s flexibility stems from two key classes:
1. **`BrowserConfig`** – Dictates **how** the browser is launched and behaves (e.g., headless or visible, proxy, user agent).
2. **`CrawlerRunConfig`** – Dictates **how** each **crawl** operates (e.g., caching, extraction, timeouts, JavaScript code to run, etc.).
3. **`LlmConfig`** - Dictates **how** LLM providers are configured. (model, api token, base url, temperature etc.)
3. **`LLMConfig`** - Dictates **how** LLM providers are configured. (model, api token, base url, temperature etc.)
In most examples, you create **one** `BrowserConfig` for the entire crawler session, then pass a **fresh** or re-used `CrawlerRunConfig` whenever you call `arun()`. This tutorial shows the most commonly used parameters. If you need advanced or rarely used fields, see the [Configuration Parameters](../api/parameters.md).
@@ -239,7 +239,7 @@ The `clone()` method:
## 3. LlmConfig Essentials
## 3. LLMConfig Essentials
### Key fields to note
@@ -256,16 +256,16 @@ The `clone()` method:
- If your provider has a custom endpoint
```python
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"))
```
## 4. Putting It All Together
In a typical scenario, you define **one** `BrowserConfig` for your crawler session, then create **one or more** `CrawlerRunConfig` & `LlmConfig` depending on each call’s needs:
In a typical scenario, you define **one** `BrowserConfig` for your crawler session, then create **one or more** `CrawlerRunConfig` & `LLMConfig` depending on each call’s needs:
```python
import asyncio
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LlmConfig
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LLMConfig
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
async def main():
@@ -289,14 +289,14 @@ async def main():
# 3) Example LLM content filtering
gemini_config = LlmConfig(
gemini_config = LLMConfig(
provider="gemini/gemini-1.5-pro"
api_token = "env:GEMINI_API_TOKEN"
)
# Initialize LLM filter with specific instruction
filter = LLMContentFilter(
llmConfig=gemini_config, # or your preferred provider
llm_config=gemini_config, # or your preferred provider
instruction="""
Focus on extracting the core educational content.
Include:
@@ -343,7 +343,7 @@ if __name__ == "__main__":
For a **detailed list** of available parameters (including advanced ones), see:
- [BrowserConfig, CrawlerRunConfig & LlmConfig Reference](../api/parameters.md)
- [BrowserConfig, CrawlerRunConfig & LLMConfig Reference](../api/parameters.md)
You can explore topics like:
@@ -356,7 +356,7 @@ You can explore topics like:
## 6. Conclusion
**BrowserConfig**, **CrawlerRunConfig** and **LlmConfig** give you straightforward ways to define:
**BrowserConfig**, **CrawlerRunConfig** and **LLMConfig** give you straightforward ways to define:
- **Which** browser to launch, how it should run, and any proxy or user agent needs.
- **How** each crawl should behave—caching, timeouts, JavaScript code, extraction strategies, etc.

4
docs/md_v2/core/content-selection.md
View File

@@ -211,7 +211,7 @@ if __name__ == "__main__":
import asyncio
import json
from pydantic import BaseModel, Field
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, LlmConfig
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, LLMConfig
from crawl4ai.extraction_strategy import LLMExtractionStrategy
class ArticleData(BaseModel):
@@ -220,7 +220,7 @@ class ArticleData(BaseModel):
async def main():
llm_strategy = LLMExtractionStrategy(
llmConfig = LlmConfig(provider="openai/gpt-4",api_token="sk-YOUR_API_KEY")
llm_config = LLMConfig(provider="openai/gpt-4",api_token="sk-YOUR_API_KEY")
schema=ArticleData.schema(),
extraction_type="schema",
instruction="Extract 'headline' and a short 'summary' from the content."

4
docs/md_v2/core/markdown-generation.md
View File

@@ -175,13 +175,13 @@ prune_filter = PruningContentFilter(
For intelligent content filtering and high-quality markdown generation, you can use the **LLMContentFilter**. This filter leverages LLMs to generate relevant markdown while preserving the original content's meaning and structure:
```python
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, LlmConfig
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, LLMConfig
from crawl4ai.content_filter_strategy import LLMContentFilter
async def main():
# Initialize LLM filter with specific instruction
filter = LLMContentFilter(
llmConfig = LlmConfig(provider="openai/gpt-4o",api_token="your-api-token"), #or use environment variable
llm_config = LLMConfig(provider="openai/gpt-4o",api_token="your-api-token"), #or use environment variable
instruction="""
Focus on extracting the core educational content.
Include:

10
docs/md_v2/core/quickstart.md
View File

@@ -128,7 +128,7 @@ Crawl4AI can also extract structured data (JSON) using CSS or XPath selectors. B
```python
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
# Generate a schema (one-time cost)
html = "<div class='product'><h2>Gaming Laptop</h2><span class='price'>$999.99</span></div>"
@@ -136,13 +136,13 @@ html = "<div class='product'><h2>Gaming Laptop</h2><span class='price'>$999.99</
# Using OpenAI (requires API token)
schema = JsonCssExtractionStrategy.generate_schema(
html,
llmConfig = LlmConfig(provider="openai/gpt-4o",api_token="your-openai-token") # Required for OpenAI
llm_config = LLMConfig(provider="openai/gpt-4o",api_token="your-openai-token") # Required for OpenAI
)
# Or using Ollama (open source, no token needed)
schema = JsonCssExtractionStrategy.generate_schema(
html,
llmConfig = LlmConfig(provider="ollama/llama3.3", api_token=None) # Not needed for Ollama
llm_config = LLMConfig(provider="ollama/llama3.3", api_token=None) # Not needed for Ollama
)
# Use the schema for fast, repeated extractions
@@ -211,7 +211,7 @@ import os
import json
import asyncio
from pydantic import BaseModel, Field
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, LlmConfig
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, LLMConfig
from crawl4ai.extraction_strategy import LLMExtractionStrategy
class OpenAIModelFee(BaseModel):
@@ -241,7 +241,7 @@ 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/md_v2/extraction/llm-strategies.md
View File

@@ -71,7 +71,7 @@ Below is an overview of important LLM extraction parameters. All are typically s
```python
extraction_strategy = LLMExtractionStrategy(
llmConfig = LlmConfig(provider="openai/gpt-4", api_token="YOUR_OPENAI_KEY"),
llm_config = LLMConfig(provider="openai/gpt-4", api_token="YOUR_OPENAI_KEY"),
schema=MyModel.model_json_schema(),
extraction_type="schema",
instruction="Extract a list of items from the text with 'name' and 'price' fields.",
@@ -96,7 +96,7 @@ import asyncio
import json
from pydantic import BaseModel, Field
from typing import List
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LlmConfig
from crawl4ai import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode, LLMConfig
from crawl4ai.extraction_strategy import LLMExtractionStrategy
class Product(BaseModel):
@@ -106,7 +106,7 @@ class Product(BaseModel):
async def main():
# 1. Define the LLM extraction strategy
llm_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')),
schema=Product.schema_json(), # Or use model_json_schema()
extraction_type="schema",
instruction="Extract all product objects with 'name' and 'price' from the content.",

6
docs/md_v2/extraction/no-llm-strategies.md
View File

@@ -415,7 +415,7 @@ The schema generator is available as a static method on both `JsonCssExtractionS
```python
from crawl4ai.extraction_strategy import JsonCssExtractionStrategy, JsonXPathExtractionStrategy
from crawl4ai.async_configs import LlmConfig
from crawl4ai.types import LLMConfig
# Sample HTML with product information
html = """
@@ -435,14 +435,14 @@ html = """
css_schema = JsonCssExtractionStrategy.generate_schema(
html,
schema_type="css",
llmConfig = LlmConfig(provider="openai/gpt-4o",api_token="your-openai-token")
llm_config = LLMConfig(provider="openai/gpt-4o",api_token="your-openai-token")
)
# Option 2: Using Ollama (open source, no token needed)
xpath_schema = JsonXPathExtractionStrategy.generate_schema(
html,
schema_type="xpath",
llmConfig = LlmConfig(provider="ollama/llama3.3", api_token=None) # Not needed for Ollama
llm_config = LLMConfig(provider="ollama/llama3.3", api_token=None) # Not needed for Ollama
)
# Use the generated schema for fast, repeated extractions