h-ai-brain 0.0.15__py3-none-any.whl → 0.0.16__py3-none-any.whl

h_ai/__init__.py

@@ -1,5 +1,3 @@
-__all__ = ['HaiService', 'WebDocsService']
-
-from .application.web_docs_service import WebDocsService
+__all__ = ['HaiService']
 
 from .application.hai_service import HaiService

h_ai/application/hai_service.py

@@ -1,58 +1,7 @@
 from h_message_bus import NatsPublisherAdapter
-from h_message_bus.domain.request_messages.twitter_get_user_request_message import TwitterGetUserRequestMessage
-from h_message_bus.domain.request_messages.twitter_get_user_response_message import TwitterGetUserResponseMessage
-from h_message_bus.domain.request_messages.vector_read_metadata_request_message import VectorReadMetaDataRequestMessage
-from h_message_bus.domain.request_messages.vector_read_metadata_response_message import \
-    VectorReadMetaDataResponseMessage
-from h_message_bus.domain.request_messages.vector_save_request_message import VectorSaveRequestMessage
-
-from .priority_queue_service import PriorityQueueService
-from ..application.web_docs_service import WebDocsService
-from ..infrastructure.priorityqueue.in_memory_priority_queue_repository import InMemoryPriorityQueueRepository
-
 
 class HaiService:
     def __init__(self, nats_publisher_adapter: NatsPublisherAdapter):
         self.nats_publisher_adapter = nats_publisher_adapter
-        self.web_docs_service = WebDocsService()
-        queue = InMemoryPriorityQueueRepository()
-        self.queue_service = PriorityQueueService(queue)
-
-    async def detect_and_store_documentation(self, twitter_screen_name: str):
-        req_message = TwitterGetUserRequestMessage.create_message(twitter_screen_name)
-        response = await self.nats_publisher_adapter.request(req_message)
-        twitter_user = TwitterGetUserResponseMessage.from_hai_message(response)
-
-        if twitter_user.url is not None:
-            print(f"Documentation found for {twitter_user.screen_name}: {twitter_user.url}")
-            docs = await self.web_docs_service.discover_documentation(twitter_user.url)
-
-            for doc in docs:
-                collection_name = f"{twitter_user.screen_name}_docs"
-                chapters = doc.chapters
-                for chapter in chapters:
-                    i = 0
-                    for text in chapter.paragraphs:
-                        document_id = f"{doc.title}_{chapter.heading}_{i}"
-
-                        req_metadata = {
-                            "source": doc.url
-                        }
-                        i = i + 1
-
-                        request = VectorSaveRequestMessage.create_message(
-                            collection_name=collection_name,
-                            document_id=document_id,
-                            content=text,
-                            metadata=req_metadata)
-
-                        await self.nats_publisher_adapter.publish(request)
 
-        else:
-            print(f"No documentation found for {twitter_user.screen_name}")
 
-    async def load_current_knowledge_base_metadata(self) -> VectorReadMetaDataResponseMessage:
-        message = VectorReadMetaDataRequestMessage.create_message()
-        response = await self.nats_publisher_adapter.request(message)
-        metadata_result = VectorReadMetaDataResponseMessage.from_hai_message(response)
-        return metadata_result

{h_ai_brain-0.0.15.dist-info → h_ai_brain-0.0.16.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: h_ai_brain
-Version: 0.0.15
+Version: 0.0.16
 Summary: AI Research agent API
 Author-email: shoebill <shoebill.hai@gmail.com>
 Classifier: Programming Language :: Python :: 3
@@ -10,13 +10,7 @@ Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 License-File: NOTICE.txt
-Requires-Dist: requests~=2.32.3
-Requires-Dist: h_message_bus~=0.0.19
-Requires-Dist: aiohttp~=3.11.16
-Requires-Dist: bs4~=0.0.2
-Requires-Dist: beautifulsoup4~=4.13.3
-Requires-Dist: tldextract~=5.2.0
-Requires-Dist: playwright~=1.51.0
+Requires-Dist: h_message_bus~=0.0.21
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Dynamic: license-file

h_ai_brain-0.0.16.dist-info/RECORD

@@ -0,0 +1,31 @@
+h_ai/__init__.py,sha256=63uVFHPxXmLrZVo2ZPixL2cU4jwf3XTAuwIVGHGkqJI,75
+h_ai/application/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/application/hai_service.py,sha256=bGKUpOnarxQKLqo7NIFFjDKTIDmzkSTydQIUjkfuTnE,206
+h_ai/application/system_prompts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/application/system_prompts/roles/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/domain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/domain/reasoning/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/domain/reasoning/llm_chat_repository.py,sha256=rY2izDyaDnoyyrCRS1qc9erHB98vARj4Mp-SnPwNhyY,211
+h_ai/domain/reasoning/llm_generate_respository.py,sha256=DPiV6ldCE8YhDdVb5rj98MBudKalDQHV3CZ2ADTm_f8,178
+h_ai/domain/reasoning/llm_tool_repository.py,sha256=nFwqtrJ0Gw8XUFX0uuO7-UejtgoqNuGeT51qZPQtxas,401
+h_ai/domain/reasoning/text_analysis.py,sha256=rmCUHWzJ3muFBorVXx7HcU2Sw-UfXFOuAVXRAPkqS8E,5183
+h_ai/domain/reasoning/tool_message.py,sha256=jpbfbJXj6oqZyB3lDxGOUyFB4faHtXAaEOVBHgTgSnk,67
+h_ai/infrastructure/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/infrastructure/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/infrastructure/llm/data_handler.py,sha256=M2h1azkjBP9GyaffTggKQZb2CQmOvAk2yo9NrsFMYAo,987
+h_ai/infrastructure/llm/llm_response_cleaner.py,sha256=pp1K7I77hagrC1r6Ib61-iSNQnU6wlM54bRmOUa7eFk,859
+h_ai/infrastructure/llm/prompt_helper.py,sha256=QjxPbNW7hu2wBIi9GLJ7r00ELytT2Wr1JKDAA1jB2U4,238
+h_ai/infrastructure/llm/prompt_loader.py,sha256=8h6QGq_h-s-UzC9fIxpeMCrhjHd7347NaAq7uLf-ook,455
+h_ai/infrastructure/llm/ollama/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/infrastructure/llm/ollama/ollama_chat_repository.py,sha256=GALea7UWLtKyt767Frtl3uv8rvy42HrOKMIQGpqq-H0,2108
+h_ai/infrastructure/llm/ollama/ollama_generate_repository.py,sha256=jorJrsIR3WPkvls7NE3BXllEtiDePCgMX5DFADz2s8E,1712
+h_ai/infrastructure/llm/ollama/ollama_tool_repository.py,sha256=7UZ-qsgXQUcJFx1qY7SVI7p3FhIy0Drdqs7jZIp42Ag,4683
+h_ai/infrastructure/llm/ollama/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+h_ai/infrastructure/llm/ollama/models/ollama_chat_message.py,sha256=ZIz4PQ3869vI3xAYYufPrxXpacajRDtOI8RDl5Dm9RQ,305
+h_ai/infrastructure/llm/ollama/models/ollama_chat_session.py,sha256=GZ_ddpbWa8iy6NZq50vokUFVZBiX0WNa81z9-r9RzTY,392
+h_ai_brain-0.0.16.dist-info/licenses/LICENSE,sha256=SbvpEU5JIU3yzMMkyzrI0dGqHDoJR_lMKGdl6GZHsy4,11558
+h_ai_brain-0.0.16.dist-info/licenses/NOTICE.txt,sha256=vxeIKUiGqAePLvDW4AVm3Xh-3BcsvMtCMn1tbsr9zsE,668
+h_ai_brain-0.0.16.dist-info/METADATA,sha256=gZ_38sf9j-XybYHejsoBrkTYJEhnq5dbT25w4mv6KrI,536
+h_ai_brain-0.0.16.dist-info/WHEEL,sha256=SmOxYU7pzNKBqASvQJ7DjX3XGUF92lrGhMb3R6_iiqI,91
+h_ai_brain-0.0.16.dist-info/top_level.txt,sha256=3MChDBWvDJV4cEHuZhzeODxQ4ewtw-arOuyaDOc6sIo,5
+h_ai_brain-0.0.16.dist-info/RECORD,,

{h_ai_brain-0.0.15.dist-info → h_ai_brain-0.0.16.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (79.0.0)
+Generator: setuptools (79.0.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

h_ai/application/priority_queue_service.py

@@ -1,30 +0,0 @@
-
-from typing import Any, List, Optional
-
-from ..domain.priorityqueue.priority_queue_repository import PriorityQueueRepository
-from ..domain.priorityqueue.queue_item import QueueItem
-
-
-class PriorityQueueService:
-    """Application service to manage priority queue operations"""
-
-    def __init__(self, repository: PriorityQueueRepository):
-        self.repository = repository
-
-    def add_item(self, queue_name: str, content: Any, priority: int, metadata: Optional[dict] = None) -> QueueItem:
-        """Add an item to the specified queue"""
-        item = QueueItem.create(content, priority, metadata)
-        self.repository.add_item(queue_name, item)
-        return item
-
-    def get_next_item(self, queue_name: str, block: bool = True, timeout: float = 30.0) -> Optional[QueueItem]:
-        """Get and remove the highest priority item from the queue"""
-        return self.repository.get_highest_priority_item(queue_name, block=block, timeout=timeout)
-
-    def get_queue_length(self, queue_name: str) -> int:
-        """Get the number of items in the queue"""
-        return self.repository.queue_length(queue_name)
-
-    def get_available_queues(self) -> List[str]:
-        """Get a list of all available queue names"""
-        return self.repository.get_queue_names()

h_ai/application/web_docs_service.py

@@ -1,36 +0,0 @@
-from typing import List, Optional
-
-from ..domain.web_docs.doc_link_scorer_service import DocLinkScorerService
-from ..domain.web_docs.documentation_pattern_repository import DocumentationPatternRepository
-from ..domain.web_docs.gitbook.text_page import TextPage
-from ..domain.web_docs.gitbook_web_fetcher_service import GitbookWebFetcherService
-from ..domain.web_docs.web_docs_link_detector import WebDocsLinkDetector
-from ..domain.web_docs.web_link import WebLink
-from ..infrastructure.playwright.playwright_web_content_fetcher import PlayWrightWebContentFetcher
-
-
-class WebDocsService:
-
-    def __init__(self):
-        self.pattern_repo = DocumentationPatternRepository()
-        self.scorer = DocLinkScorerService(self.pattern_repo)
-        self.headless_browser = PlayWrightWebContentFetcher()
-        self.web_link_detector = WebDocsLinkDetector(
-            self.scorer,
-            self.headless_browser)
-
-
-    async def discover_documentation(self, website_url: str) -> Optional[List[TextPage]]:
-        detected_links = await self.detect_documentation_links(website_url)
-        for link in detected_links:
-            print(f"Fetching {link.url}")
-            gitbook_fetcher = GitbookWebFetcherService(link.url)
-            gitbook_pages = await gitbook_fetcher.fetch()
-            return gitbook_pages
-
-    async def detect_documentation_links(self, website_url: str) -> List[WebLink]:
-        """
-        Function to detect documentation links from a website
-        Returns a list of potential documentation root URLs
-        """
-        return await self.web_link_detector.find_docs_links(website_url)

h_ai/domain/priorityqueue/priority_queue_repository.py

@@ -1,34 +0,0 @@
-
-from abc import ABC, abstractmethod
-from typing import List, Optional
-
-from .queue_item import QueueItem
-
-
-class PriorityQueueRepository(ABC):
-    """Repository interface for priority queue operations"""
-
-    @abstractmethod
-    def add_item(self, queue_name: str, item: QueueItem) -> None:
-        """Add an item to the specified queue"""
-        pass
-
-    @abstractmethod
-    def get_highest_priority_item(self, queue_name: str, block: bool = False, timeout: Optional[float] = None) -> Optional[QueueItem]:
-        """Get and remove the highest priority item from the queue"""
-        pass
-
-    # @abstractmethod
-    # def get_items(self, queue_name: str, limit: int = 10) -> List[QueueItem]:
-    #     """Get multiple items from the queue in priority order without removing them"""
-    #     pass
-
-    @abstractmethod
-    def queue_length(self, queue_name: str) -> int:
-        """Get the number of items in the queue"""
-        pass
-
-    @abstractmethod
-    def get_queue_names(self) -> List[str]:
-        """Get a list of all available queue names"""
-        pass

h_ai/domain/priorityqueue/queue_item.py

@@ -1,43 +0,0 @@
-
-import uuid
-from dataclasses import dataclass
-from datetime import datetime
-from typing import Optional
-
-from h_message_bus import HaiMessage
-
-
-@dataclass(frozen=True)
-class QueueItem:
-    """Value object representing an item in the priority queue"""
-    id: str
-    content: HaiMessage
-    priority: int
-    created_at: datetime
-    metadata: Optional[dict] = None
-
-    @classmethod
-    def create(cls, content: HaiMessage, priority: int, metadata: Optional[dict] = None) -> "QueueItem":
-        """Factory method to create a new QueueItem"""
-        return cls(
-            id=str(uuid.uuid4()),
-            content=content,
-            priority=priority,
-            created_at=datetime.utcnow(),
-            metadata=metadata
-        )
-
-    def __lt__(self, other):
-        """Comparison method for priority queue ordering
-        - Primary sort by priority: Higher number = higher priority
-        - Secondary sort by timestamp: Earlier timestamp = higher priority (FIFO)
-        """
-        if not isinstance(other, QueueItem):
-            return NotImplemented
-
-        # First, compare by priority (higher priority value comes first)
-        if self.priority != other.priority:
-            return self.priority > other.priority
-
-        # If priorities are equal, compare by timestamp (older timestamp comes first)
-        return self.created_at < other.created_at

h_ai/domain/web_docs/doc_link_scorer_service.py

@@ -1,45 +0,0 @@
-import re
-from urllib.parse import urlparse
-
-from ...domain.web_docs.documentation_pattern_repository import DocumentationPatternRepository
-
-
-class DocLinkScorerService:
-    """Service for scoring potential documentation links"""
-
-    def __init__(self, pattern_repo: DocumentationPatternRepository):
-        self.pattern_repo = pattern_repo
-
-    def score(self, full_url: str, link_text: str) -> float:
-        """
-        Score a link based on how likely it is to be documentation
-        Returns a value between 0.0 and 1.0
-        """
-        score = 0.0
-        max_score = 3.0  # Maximum possible score
-
-        # Parse the URL
-        parsed_url = urlparse(full_url)
-        domain = parsed_url.netloc
-        path = parsed_url.path
-
-        # Check domain patterns
-        for doc_domain in self.pattern_repo.doc_domains:
-            if doc_domain in domain:
-                score += 1.0
-                break
-
-        # Check path patterns
-        for path_pattern in self.pattern_repo.doc_path_patterns:
-            if re.search(path_pattern, path):
-                score += 1.0
-                break
-
-        # Check link text patterns
-        for text_pattern in self.pattern_repo.doc_text_patterns:
-            if re.search(text_pattern, link_text):
-                score += 1.0
-                break
-
-        # Normalize score to 0.0-1.0 range
-        return min(score / max_score, 1.0)

h_ai/domain/web_docs/documentation_pattern_repository.py

@@ -1,44 +0,0 @@
-class DocumentationPatternRepository:
-    """Repository of patterns that indicate documentation links"""
-
-    def __init__(self):
-        # Domain patterns that commonly host documentation
-        self.doc_domains = [
-            "gitbook.io",
-            "readthedocs.io",
-            "docs.github.com",
-            "developer.mozilla.org",
-            "confluence.",
-            "zendesk.com",
-            "help.",
-            "support.",
-            "wiki.",
-        ]
-
-        # URL path patterns that commonly indicate documentation
-        self.doc_path_patterns = [
-            r"/docs/",
-            r"/documentation/",
-            r"/guide/",
-            r"/manual/",
-            r"/help/",
-            r"/knowledge/",
-            r"/support/",
-            r"/api/",
-            r"/reference/",
-            r"/wiki/",
-        ]
-
-        # Link text patterns that suggest documentation
-        self.doc_text_patterns = [
-            r"(?i)documentation",
-            r"(?i)docs",
-            r"(?i)developer guide",
-            r"(?i)user guide",
-            r"(?i)knowledge base",
-            r"(?i)help center",
-            r"(?i)manual",
-            r"(?i)api reference",
-            r"(?i)getting started",
-            r"(?i)learn more",
-        ]

h_ai/domain/web_docs/ecosystem_link_scorer_service.py

@@ -1,83 +0,0 @@
-import re
-from urllib.parse import urlparse
-
-from ...domain.web_docs.ecosystem_pattern_repository import EcosystemPatternRepository
-
-
-class EcosystemLinkScorerService:
-    """Service for scoring potential ecosystem-related links and content"""
-
-    def __init__(self, pattern_repo: EcosystemPatternRepository):
-        self.pattern_repo = pattern_repo
-
-    def score(self, full_url: str, link_text: str) -> float:
-        """
-        Score a link based on how likely it is to be ecosystem-related
-        Returns a value between 0.0 and 1.0
-        """
-        score = 0.0
-        max_score = 3.0  # Maximum possible score
-
-        # Parse the URL
-        parsed_url = urlparse(full_url)
-        domain = parsed_url.netloc
-        path = parsed_url.path
-
-        # Check domain patterns
-        for eco_domain in self.pattern_repo.ecosystem_domains:
-            if eco_domain in domain:
-                score += 1.0
-                break
-
-        # Check path patterns
-        for path_pattern in self.pattern_repo.ecosystem_path_patterns:
-            if re.search(path_pattern, path):
-                score += 1.0
-                break
-
-        # Check link text patterns
-        for text_pattern in self.pattern_repo.ecosystem_text_patterns:
-            if re.search(text_pattern, link_text):
-                score += 1.0
-                break
-
-        # Normalize score to 0.0-1.0 range
-        return min(score / max_score, 1.0)
-
-    def score_page(self, page_url: str, page_title: str, page_content: str) -> float:
-        """
-        Score an entire page based on how likely it is to contain ecosystem information
-        Returns a value between 0.0 and 1.0
-
-        Args:
-            page_url: The URL of the page
-            page_title: The title of the page
-            page_content: The full text content of the page
-        """
-        # Start with the URL and title scoring
-        url_score = self.score(page_url, page_title)
-
-        # Content-based scoring
-        content_score = 0.0
-        max_content_score = 2.0
-
-        # Check content patterns
-        content_matches = 0
-        for content_pattern in self.pattern_repo.ecosystem_content_patterns:
-            if re.search(content_pattern, page_content):
-                content_matches += 1
-
-        # Score based on number of content matches
-        if content_matches >= 3:
-            content_score += 1.0
-        elif content_matches > 0:
-            content_score += 0.5
-
-        # Check for header patterns
-        for header_pattern in self.pattern_repo.ecosystem_header_patterns:
-            if re.search(header_pattern, page_content):
-                content_score += 1.0
-                break
-
-        # Combined score with higher weight on content
-        return min((url_score + (content_score / max_content_score) * 2) / 3, 1.0)

h_ai/domain/web_docs/ecosystem_pattern_repository.py

@@ -1,182 +0,0 @@
-class EcosystemPatternRepository:
-    """Repository of patterns that identify ecosystem relationships, builders, and collaboration"""
-
-    def __init__(self):
-        # Domains commonly associated with ecosystem and project showcases
-        self.ecosystem_domains = [
-            "showcase.",
-            "ecosystem.",
-            "community.",
-            "gallery.",
-            "partners.",
-            "developers.",
-            "marketplace.",
-            "expo.",
-            "apps.",
-            "extensions.",
-            "plugins.",
-        ]
-
-        # URL path patterns indicating ecosystem/builder content
-        self.ecosystem_path_patterns = [
-            r"/ecosystem/",
-            r"/showcase/",
-            r"/community/",
-            r"/built-with/",
-            r"/case-studies/",
-            r"/customers/",
-            r"/partners/",
-            r"/users/",
-            r"/success-stories/",
-            r"/integrations/",
-            r"/extensions/",
-            r"/marketplace/",
-            r"/plugins/",
-            r"/addons/",
-            r"/gallery/",
-            r"/examples/",
-            r"/projects/",
-            r"/contributors/",
-            r"/whos-using/",
-        ]
-
-        # Link text patterns suggesting ecosystem content
-        self.ecosystem_text_patterns = [
-            r"(?i)ecosystem",
-            r"(?i)showcase",
-            r"(?i)built with",
-            r"(?i)powered by",
-            r"(?i)case stud(y|ies)",
-            r"(?i)success stor(y|ies)",
-            r"(?i)who('s| is) using",
-            r"(?i)our users",
-            r"(?i)our customers",
-            r"(?i)integrations?",
-            r"(?i)extensions?",
-            r"(?i)plugins?",
-            r"(?i)addons?",
-            r"(?i)community projects",
-            r"(?i)community contributions",
-            r"(?i)user contributions",
-            r"(?i)featured projects",
-            r"(?i)gallery",
-        ]
-
-        # Header/title patterns suggesting ecosystem sections
-        self.ecosystem_header_patterns = [
-            r"(?i)ecosystem",
-            r"(?i)who('s| is) using",
-            r"(?i)built (on|with)",
-            r"(?i)powered by",
-            r"(?i)trusted by",
-            r"(?i)customer(s| success)",
-            r"(?i)case stud(y|ies)",
-            r"(?i)success stor(y|ies)",
-            r"(?i)showcase",
-            r"(?i)featured (users|customers|projects)",
-            r"(?i)community (projects|showcase)",
-            r"(?i)partner(s| program)",
-            r"(?i)(our|notable) users",
-            r"(?i)companies using",
-            r"(?i)in production",
-            r"(?i)contributor(s| showcase)",
-            r"(?i)extension (gallery|showcase)",
-            r"(?i)plugin (directory|marketplace)",
-            r"(?i)apps? (built|marketplace|gallery)",
-        ]
-
-        # Content phrases that suggest ecosystem descriptions
-        self.ecosystem_content_patterns = [
-            r"(?i)built (on|with) (our|this)",
-            r"(?i)(companies|organizations|projects) (using|powered by)",
-            r"(?i)(is|are) using (our|this)",
-            r"(?i)powered by (our|this)",
-            r"(?i)extend(s|ing)? (the|our) (platform|ecosystem)",
-            r"(?i)integrated with",
-            r"(?i)build(s|ing)? (on top of|with)",
-            r"(?i)leverage(s|ing)? (our|this)",
-            r"(?i)extend(s|ing)? (the|our) (functionality|capabilities)",
-            r"(?i)based on (our|this)",
-            r"(?i)implemented (with|using)",
-            r"(?i)developed (with|using)",
-            r"(?i)(join|be part of) (our|the) ecosystem",
-        ]
-
-        # Builder and contribution-specific patterns
-        self.builder_patterns = [
-            r"(?i)how to (build|contribute)",
-            r"(?i)build(ing)? (with|on)",
-            r"(?i)develop(ing)? (with|on)",
-            r"(?i)contribute to",
-            r"(?i)contributor guide",
-            r"(?i)developer program",
-            r"(?i)join (our|the) (ecosystem|community)",
-            r"(?i)become a (contributor|partner)",
-            r"(?i)extend (our|the) (platform|ecosystem)",
-            r"(?i)create (your own|an?) (plugin|extension|integration)",
-            r"(?i)developer (resources|portal)",
-            r"(?i)sdk",
-            r"(?i)api (access|integration)",
-            r"(?i)partner (program|portal)",
-        ]
-
-        # Visual cues that often indicate ecosystem showcases
-        self.visual_indicators = [
-            r"logo grid",
-            r"logo carousel",
-            r"client logos",
-            r"partner logos",
-            r"customer logos",
-            r"company logos",
-            r"card gallery",
-            r"project cards",
-            r"showcase gallery",
-            r"case study cards",
-            r"testimonials",
-            r"user testimonials",
-        ]
-
-        # Collaboration-specific patterns
-        self.collaboration_patterns = [
-            r"(?i)how to collaborate",
-            r"(?i)collaboration (guide|opportunities)",
-            r"(?i)working together",
-            r"(?i)partner(ship|ing) (opportunities|program)",
-            r"(?i)join (our|the) (community|ecosystem)",
-            r"(?i)community (contribution|participation)",
-            r"(?i)open (source|collaboration)",
-            r"(?i)contribute (code|documentation|resources)",
-            r"(?i)become a (partner|contributor|maintainer)",
-            r"(?i)collaboration (framework|model)",
-            r"(?i)(business|technical) partnership",
-            r"(?i)developer relations",
-            r"(?i)community (engagement|involvement)",
-        ]
-
-        # Key meta tags that might indicate ecosystem content
-        self.meta_tag_patterns = [
-            r"(?i)ecosystem",
-            r"(?i)showcase",
-            r"(?i)community",
-            r"(?i)partner program",
-            r"(?i)integration",
-            r"(?i)extension",
-            r"(?i)plugin",
-            r"(?i)marketplace",
-            r"(?i)collaboration",
-            r"(?i)use cases",
-            r"(?i)case studies",
-            r"(?i)success stories",
-        ]
-
-        # Schema.org types that often indicate ecosystem relationships
-        self.schema_types = [
-            "Product",
-            "SoftwareApplication",
-            "Organization",
-            "BusinessPartner",
-            "ProgramMembership",
-            "CreativeWork",
-            "SoftwareSourceCode",
-            "WebApplication",
-        ]

h_ai/domain/web_docs/gitbook/text_chapter.py

@@ -1,18 +0,0 @@
-from dataclasses import dataclass, field
-from typing import List
-
-
-@dataclass
-class TextChapter:
-    """Represents a chapter/section in a page defined by a heading."""
-    heading: str
-    level: int  # h1=1, h2=2, etc.
-    paragraphs: List[str] = field(default_factory=list)
-
-    def to_dict(self):
-        """Convert this TextChapter instance to a serializable dictionary"""
-        return {
-            'heading': self.heading,
-            'level': self.level,
-            'paragraphs': self.paragraphs
-        }