From c09a57644f2b210f3af945cace6565890c892b27 Mon Sep 17 00:00:00 2001
From: Soham Kukreti <kukretisoham@gmail.com>
Date: Thu, 21 Aug 2025 19:11:31 +0530
Subject: [PATCH] =?UTF-8?q?docs:=20update=20adaptive=20crawler=20docs=20an?=
 =?UTF-8?q?d=20cache=20defaults;=20remove=20deprecated=20examples=20(#1330?=
 =?UTF-8?q?)=20-=20Replace=20BaseStrategy=20with=20CrawlStrategy=20in=20cu?=
 =?UTF-8?q?stom=20strategy=20examples=20(DomainSpecificStrategy,=20HybridS?=
 =?UTF-8?q?trategy)=20-=20Remove=20=E2=80=9CCustom=20Link=20Scoring?=
 =?UTF-8?q?=E2=80=9D=20and=20=E2=80=9CCaching=20Strategy=E2=80=9D=20sectio?=
 =?UTF-8?q?ns=20no=20longer=20aligned=20with=20current=20library=20-=20Rev?=
 =?UTF-8?q?ise=20memory=20pruning=20example=20to=20use=20adaptive.get=5Fre?=
 =?UTF-8?q?levant=5Fcontent=20and=20index-based=20retention=20of=20top=205?=
 =?UTF-8?q?00=20docs=20-=20Correct=20Quickstart=20note:=20default=20cache?=
 =?UTF-8?q?=20mode=20is=20CacheMode.BYPASS;=20instruct=20enabling=20with?=
 =?UTF-8?q?=20CacheMode.ENABLED?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 docs/md_v2/advanced/adaptive-strategies.md | 50 ++++------------------
 docs/md_v2/core/quickstart.md              |  2 +-
 2 files changed, 10 insertions(+), 42 deletions(-)

diff --git a/docs/md_v2/advanced/adaptive-strategies.md b/docs/md_v2/advanced/adaptive-strategies.md
index 4ab5b4cd..11c5585a 100644
--- a/docs/md_v2/advanced/adaptive-strategies.md
+++ b/docs/md_v2/advanced/adaptive-strategies.md
@@ -126,30 +126,6 @@ Factors:
 - URL depth (fewer slashes = higher authority)
 - Clean URL structure
 
-### Custom Link Scoring
-
-```python
-class CustomLinkScorer:
-    def score(self, link: Link, query: str, state: CrawlState) -> float:
-        # Prioritize specific URL patterns
-        if "/api/reference/" in link.href:
-            return 2.0  # Double the score
-        
-        # Deprioritize certain sections
-        if "/archive/" in link.href:
-            return 0.1  # Reduce score by 90%
-        
-        # Default scoring
-        return 1.0
-
-# Use with adaptive crawler
-adaptive = AdaptiveCrawler(
-    crawler,
-    config=config,
-    link_scorer=CustomLinkScorer()
-)
-```
-
 ## Domain-Specific Configurations
 
 ### Technical Documentation
@@ -230,8 +206,12 @@ config = AdaptiveConfig(
 
 # Periodically clean state
 if len(state.knowledge_base) > 1000:
-    # Keep only most relevant
-    state.knowledge_base = get_top_relevant(state.knowledge_base, 500)
+    # Keep only the top 500 most relevant docs
+    top_content = adaptive.get_relevant_content(top_k=500)
+    keep_indices = {d["index"] for d in top_content}
+    state.knowledge_base = [
+        doc for i, doc in enumerate(state.knowledge_base) if i in keep_indices
+    ]
 ```
 
 ### Parallel Processing
@@ -252,18 +232,6 @@ tasks = [
 results = await asyncio.gather(*tasks)
 ```
 
-### Caching Strategy
-
-```python
-# Enable caching for repeated crawls
-async with AsyncWebCrawler(
-    config=BrowserConfig(
-        cache_mode=CacheMode.ENABLED
-    )
-) as crawler:
-    adaptive = AdaptiveCrawler(crawler, config)
-```
-
 ## Debugging & Analysis
 
 ### Enable Verbose Logging
@@ -322,9 +290,9 @@ with open("crawl_analysis.json", "w") as f:
 ### Implementing a Custom Strategy
 
 ```python
-from crawl4ai.adaptive_crawler import BaseStrategy
+from crawl4ai.adaptive_crawler import CrawlStrategy
 
-class DomainSpecificStrategy(BaseStrategy):
+class DomainSpecificStrategy(CrawlStrategy):
     def calculate_coverage(self, state: CrawlState) -> float:
         # Custom coverage calculation
         # e.g., weight certain terms more heavily
@@ -351,7 +319,7 @@ adaptive = AdaptiveCrawler(
 ### Combining Strategies
 
 ```python
-class HybridStrategy(BaseStrategy):
+class HybridStrategy(CrawlStrategy):
     def __init__(self):
         self.strategies = [
             TechnicalDocStrategy(),
diff --git a/docs/md_v2/core/quickstart.md b/docs/md_v2/core/quickstart.md
index e9a4b987..83cb6cef 100644
--- a/docs/md_v2/core/quickstart.md
+++ b/docs/md_v2/core/quickstart.md
@@ -79,7 +79,7 @@ if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-> IMPORTANT: By default cache mode is set to `CacheMode.ENABLED`. So to have fresh content, you need to set it to `CacheMode.BYPASS`
+> IMPORTANT: By default cache mode is set to `CacheMode.BYPASS` to have fresh content. Set `CacheMode.ENABLED` to enable caching.
 
 We’ll explore more advanced config in later tutorials (like enabling proxies, PDF output, multi-tab sessions, etc.). For now, just note how you pass these objects to manage crawling.