intentkit 0.8.6.dev2__py3-none-any.whl → 0.8.17__py3-none-any.whl

intentkit/skills/firecrawl/query.py

@@ -1,5 +1,4 @@
 import logging
-from typing import Type
 
 from pydantic import BaseModel, Field
 
@@ -37,7 +36,7 @@ class FirecrawlQueryIndexedContent(FirecrawlBaseTool):
         "Use this tool to search through content that was previously scraped and indexed using Firecrawl tools.\n"
         "This tool can help answer questions based on the indexed web content from Firecrawl scraping/crawling."
     )
-    args_schema: Type[BaseModel] = FirecrawlQueryInput
+    args_schema: type[BaseModel] = FirecrawlQueryInput
 
     async def _arun(
         self,
@@ -62,12 +61,14 @@ class FirecrawlQueryIndexedContent(FirecrawlBaseTool):
             # Import query utilities from firecrawl utils
             from intentkit.skills.firecrawl.utils import (
                 FirecrawlDocumentProcessor,
+                FirecrawlVectorStoreManager,
                 query_indexed_content,
             )
 
             # Query the indexed content
+            vector_manager = FirecrawlVectorStoreManager()
             docs = await query_indexed_content(
-                query, agent_id, self.skill_store, max_results
+                query, agent_id, vector_manager, max_results
             )
 
             if not docs:

intentkit/skills/firecrawl/scrape.py

@@ -1,5 +1,4 @@
 import logging
-from typing import List, Optional, Type
 
 import httpx
 from langchain_core.documents import Document
@@ -16,7 +15,7 @@ class FirecrawlScrapeInput(BaseModel):
     url: str = Field(
         description="The URL to scrape. Must be a valid HTTP or HTTPS URL."
     )
-    formats: List[str] = Field(
+    formats: list[str] = Field(
         description="Output formats to include in the response. Options: 'markdown', 'html', 'rawHtml', 'screenshot', 'links', 'json'",
         default=["markdown"],
     )
@@ -24,11 +23,11 @@ class FirecrawlScrapeInput(BaseModel):
         description="Whether to extract only the main content (excluding headers, footers, navigation, etc.)",
         default=True,
     )
-    include_tags: Optional[List[str]] = Field(
+    include_tags: list[str] | None = Field(
         description="HTML tags, classes, or IDs to include in the response (e.g., ['h1', 'p', '.main-content'])",
         default=None,
     )
-    exclude_tags: Optional[List[str]] = Field(
+    exclude_tags: list[str] | None = Field(
         description="HTML tags, classes, or IDs to exclude from the response (e.g., ['#ad', '#footer'])",
         default=None,
     )
@@ -81,15 +80,15 @@ class FirecrawlScrape(FirecrawlBaseTool):
         "This tool can handle JavaScript-rendered content, PDFs, and dynamic websites. "
         "Use this when you want to refresh/update content from a URL that was previously scraped."
     )
-    args_schema: Type[BaseModel] = FirecrawlScrapeInput
+    args_schema: type[BaseModel] = FirecrawlScrapeInput
 
     async def _arun(
         self,
         url: str,
-        formats: List[str] = None,
+        formats: list[str] = None,
         only_main_content: bool = True,
-        include_tags: Optional[List[str]] = None,
-        exclude_tags: Optional[List[str]] = None,
+        include_tags: list[str] | None = None,
+        exclude_tags: list[str] | None = None,
         wait_for: int = 0,
         timeout: int = 30000,
         index_content: bool = True,
@@ -124,9 +123,8 @@ class FirecrawlScrape(FirecrawlBaseTool):
                 "rate_limit_minutes"
             ):
                 await self.user_rate_limit_by_category(
-                    context.user_id,
                     skill_config["rate_limit_number"],
-                    skill_config["rate_limit_minutes"],
+                    skill_config["rate_limit_minutes"] * 60,
                 )
 
         # Get the API key from the agent's configuration
@@ -265,11 +263,8 @@ class FirecrawlScrape(FirecrawlBaseTool):
                         # Get agent ID for indexing
                         agent_id = context.agent_id
                         if agent_id:
-                            # Initialize managers
-                            vs_manager = FirecrawlVectorStoreManager(self.skill_store)
-                            metadata_manager = FirecrawlMetadataManager(
-                                self.skill_store
-                            )
+                            # Initialize vector store manager
+                            vs_manager = FirecrawlVectorStoreManager()
 
                             # Load existing vector store
                             existing_vector_store = await vs_manager.load_vector_store(
@@ -368,10 +363,8 @@ class FirecrawlScrape(FirecrawlBaseTool):
                             # Update metadata to track all URLs
                             # Get existing metadata to preserve other URLs
                             metadata_key = f"indexed_urls_{agent_id}"
-                            existing_metadata = (
-                                await self.skill_store.get_agent_skill_data(
-                                    agent_id, "firecrawl", metadata_key
-                                )
+                            existing_metadata = await self.get_agent_skill_data_raw(
+                                "firecrawl", metadata_key
                             )
 
                             if existing_metadata and existing_metadata.get("urls"):
@@ -388,11 +381,13 @@ class FirecrawlScrape(FirecrawlBaseTool):
                                 }
                             else:
                                 # Create new metadata
-                                updated_metadata = metadata_manager.create_url_metadata(
-                                    [url], [document], "firecrawl_scrape"
+                                updated_metadata = (
+                                    FirecrawlMetadataManager.create_url_metadata(
+                                        [url], [document], "firecrawl_scrape"
+                                    )
                                 )
 
-                            await metadata_manager.update_metadata(
+                            await FirecrawlMetadataManager.update_metadata(
                                 agent_id, updated_metadata
                             )
 

intentkit/skills/firecrawl/utils.py

@@ -2,14 +2,15 @@
 
 import logging
 import re
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any
 
-from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import FAISS
 from langchain_core.documents import Document
 from langchain_openai import OpenAIEmbeddings
+from langchain_text_splitters import RecursiveCharacterTextSplitter
 
-from intentkit.abstracts.skill import SkillStoreABC
+from intentkit.config.config import config
+from intentkit.models.skill import AgentSkillData, AgentSkillDataCreate
 
 logger = logging.getLogger(__name__)
 
@@ -35,8 +36,8 @@ class FirecrawlDocumentProcessor:
 
     @staticmethod
     def split_documents(
-        documents: List[Document], chunk_size: int = 1000, chunk_overlap: int = 200
-    ) -> List[Document]:
+        documents: list[Document], chunk_size: int = 1000, chunk_overlap: int = 200
+    ) -> list[Document]:
         """Split documents into smaller chunks for better indexing."""
         text_splitter = RecursiveCharacterTextSplitter(
             chunk_size=chunk_size,
@@ -62,20 +63,25 @@ class FirecrawlDocumentProcessor:
 class FirecrawlVectorStoreManager:
     """Manages vector store operations for Firecrawl content."""
 
-    def __init__(self, skill_store: SkillStoreABC):
-        self.skill_store = skill_store
+    def __init__(self, embedding_api_key: str | None = None):
+        self._embedding_api_key = embedding_api_key
+
+    def _resolve_api_key(self) -> str:
+        """Resolve the API key to use for embeddings."""
+        if self._embedding_api_key:
+            return self._embedding_api_key
+        if config.openai_api_key:
+            return config.openai_api_key
+        raise ValueError("OpenAI API key not found in system configuration")
 
     def create_embeddings(self) -> OpenAIEmbeddings:
         """Create OpenAI embeddings instance."""
-        openai_api_key = self.skill_store.get_system_config("openai_api_key")
-        if not openai_api_key:
-            raise ValueError("OpenAI API key not found in system configuration")
-
+        openai_api_key = self._resolve_api_key()
         return OpenAIEmbeddings(
             openai_api_key=openai_api_key, model="text-embedding-3-small"
         )
 
-    def encode_vector_store(self, vector_store: FAISS) -> Dict[str, str]:
+    def encode_vector_store(self, vector_store: FAISS) -> dict[str, str]:
         """Encode FAISS vector store to base64 for storage (compatible with web_scraper)."""
         import base64
         import os
@@ -100,7 +106,7 @@ class FirecrawlVectorStoreManager:
             raise
 
     def decode_vector_store(
-        self, encoded_files: Dict[str, str], embeddings: OpenAIEmbeddings
+        self, encoded_files: dict[str, str], embeddings: OpenAIEmbeddings
     ) -> FAISS:
         """Decode base64 files back to FAISS vector store (compatible with web_scraper)."""
         import base64
@@ -125,11 +131,11 @@ class FirecrawlVectorStoreManager:
             logger.error(f"Error decoding vector store: {e}")
             raise
 
-    async def load_vector_store(self, agent_id: str) -> Optional[FAISS]:
+    async def load_vector_store(self, agent_id: str) -> FAISS | None:
         """Load existing vector store for an agent."""
         try:
             vector_store_key = f"vector_store_{agent_id}"
-            stored_data = await self.skill_store.get_agent_skill_data(
+            stored_data = await AgentSkillData.get(
                 agent_id, "web_scraper", vector_store_key
             )
 
@@ -162,9 +168,13 @@ class FirecrawlVectorStoreManager:
                 "chunk_overlap": chunk_overlap,
             }
 
-            await self.skill_store.save_agent_skill_data(
-                agent_id, "web_scraper", vector_store_key, storage_data
+            skill_data = AgentSkillDataCreate(
+                agent_id=agent_id,
+                skill="web_scraper",
+                key=vector_store_key,
+                data=storage_data,
             )
+            await skill_data.save()
 
         except Exception as e:
             logger.error(f"Error saving vector store for agent {agent_id}: {e}")
@@ -174,12 +184,10 @@ class FirecrawlVectorStoreManager:
 class FirecrawlMetadataManager:
     """Manages metadata for Firecrawl indexed content."""
 
-    def __init__(self, skill_store: SkillStoreABC):
-        self.skill_store = skill_store
-
+    @staticmethod
     def create_url_metadata(
-        self, urls: List[str], documents: List[Document], source_type: str
-    ) -> Dict[str, Any]:
+        urls: list[str], documents: list[Document], source_type: str
+    ) -> dict[str, Any]:
         """Create metadata for indexed URLs."""
         return {
             "urls": urls,
@@ -188,34 +196,38 @@ class FirecrawlMetadataManager:
             "indexed_at": str(len(urls)),  # Simple counter
         }
 
-    async def update_metadata(
-        self, agent_id: str, new_metadata: Dict[str, Any]
-    ) -> None:
+    @staticmethod
+    @staticmethod
+    async def update_metadata(agent_id: str, new_metadata: dict[str, Any]) -> None:
         """Update metadata for an agent."""
         try:
             metadata_key = f"indexed_urls_{agent_id}"
-            await self.skill_store.save_agent_skill_data(
-                agent_id, "web_scraper", metadata_key, new_metadata
+            skill_data = AgentSkillDataCreate(
+                agent_id=agent_id,
+                skill="web_scraper",
+                key=metadata_key,
+                data=new_metadata,
             )
+            await skill_data.save()
         except Exception as e:
             logger.error(f"Error updating metadata for agent {agent_id}: {e}")
             raise
 
 
 async def index_documents(
-    documents: List[Document],
+    documents: list[Document],
     agent_id: str,
-    skill_store: SkillStoreABC,
+    vector_manager: FirecrawlVectorStoreManager,
     chunk_size: int = 1000,
     chunk_overlap: int = 200,
-) -> Tuple[int, bool]:
+) -> tuple[int, bool]:
     """
     Index documents into the Firecrawl vector store.
 
     Args:
         documents: List of documents to index
         agent_id: Agent ID for storage
-        skill_store: Skill store for persistence
+        vector_manager: Vector store manager
         chunk_size: Size of text chunks
         chunk_overlap: Overlap between chunks
 
@@ -224,8 +236,6 @@ async def index_documents(
     """
     try:
         # Initialize managers
-        vs_manager = FirecrawlVectorStoreManager(skill_store)
-
         # Split documents into chunks
         split_docs = FirecrawlDocumentProcessor.split_documents(
             documents, chunk_size, chunk_overlap
@@ -236,10 +246,10 @@ async def index_documents(
             return 0, False
 
         # Create embeddings
-        embeddings = vs_manager.create_embeddings()
+        embeddings = vector_manager.create_embeddings()
 
         # Try to load existing vector store
-        existing_vector_store = await vs_manager.load_vector_store(agent_id)
+        existing_vector_store = await vector_manager.load_vector_store(agent_id)
 
         if existing_vector_store:
             # Add to existing vector store
@@ -252,7 +262,7 @@ async def index_documents(
             was_merged = False
 
         # Save the vector store
-        await vs_manager.save_vector_store(
+        await vector_manager.save_vector_store(
             agent_id, vector_store, chunk_size, chunk_overlap
         )
 
@@ -269,16 +279,16 @@ async def index_documents(
 async def query_indexed_content(
     query: str,
     agent_id: str,
-    skill_store: SkillStoreABC,
+    vector_manager: FirecrawlVectorStoreManager,
     max_results: int = 4,
-) -> List[Document]:
+) -> list[Document]:
     """
     Query the Firecrawl indexed content.
 
     Args:
         query: Search query
         agent_id: Agent ID
-        skill_store: Skill store for persistence
+        vector_manager: Manager for vector store persistence
         max_results: Maximum number of results to return
 
     Returns:
@@ -286,10 +296,8 @@ async def query_indexed_content(
     """
     try:
         # Initialize vector store manager
-        vs_manager = FirecrawlVectorStoreManager(skill_store)
-
         # Load vector store
-        vector_store = await vs_manager.load_vector_store(agent_id)
+        vector_store = await vector_manager.load_vector_store(agent_id)
 
         if not vector_store:
             logger.warning(f"No vector store found for agent {agent_id}")

intentkit/skills/github/__init__.py

@@ -1,6 +1,5 @@
 from typing import TypedDict
 
-from intentkit.abstracts.skill import SkillStoreABC
 from intentkit.skills.base import SkillConfig, SkillState
 from intentkit.skills.github.base import GitHubBaseTool
 from intentkit.skills.github.github_search import GitHubSearch
@@ -22,7 +21,6 @@ class Config(SkillConfig):
 async def get_skills(
     config: "Config",
     is_private: bool,
-    store: SkillStoreABC,
     **_,
 ) -> list[GitHubBaseTool]:
     """Get all GitHub skills."""
@@ -36,19 +34,16 @@ async def get_skills(
             available_skills.append(skill_name)
 
     # Get each skill using the cached getter
-    return [get_github_skill(name, store) for name in available_skills]
+    return [get_github_skill(name) for name in available_skills]
 
 
 def get_github_skill(
     name: str,
-    store: SkillStoreABC,
 ) -> GitHubBaseTool:
     """Get a GitHub skill by name."""
     if name == "github_search":
         if name not in _cache:
-            _cache[name] = GitHubSearch(
-                skill_store=store,
-            )
+            _cache[name] = GitHubSearch()
         return _cache[name]
     else:
         raise ValueError(f"Unknown GitHub skill: {name}")

intentkit/skills/github/base.py

@@ -1,8 +1,5 @@
-from typing import Type
-
 from pydantic import BaseModel, Field
 
-from intentkit.abstracts.skill import SkillStoreABC
 from intentkit.skills.base import IntentKitSkill
 
 
@@ -11,10 +8,7 @@ class GitHubBaseTool(IntentKitSkill):
 
     name: str = Field(description="The name of the tool")
     description: str = Field(description="A description of what the tool does")
-    args_schema: Type[BaseModel]
-    skill_store: SkillStoreABC = Field(
-        description="The skill store for persisting data"
-    )
+    args_schema: type[BaseModel]
 
     @property
     def category(self) -> str:

intentkit/skills/github/github_search.py

@@ -1,6 +1,5 @@
 import logging
 from enum import Enum
-from typing import Type
 
 import httpx
 from pydantic import BaseModel, Field
@@ -54,7 +53,7 @@ class GitHubSearch(GitHubBaseTool):
         "- Code snippets across GitHub repositories\n"
         "You must call this tool whenever the user asks about finding something on GitHub."
     )
-    args_schema: Type[BaseModel] = GitHubSearchInput
+    args_schema: type[BaseModel] = GitHubSearchInput
 
     async def _arun(
         self,

intentkit/skills/heurist/__init__.py

@@ -3,7 +3,6 @@
 import logging
 from typing import NotRequired, TypedDict
 
-from intentkit.abstracts.skill import SkillStoreABC
 from intentkit.skills.base import SkillConfig, SkillState
 from intentkit.skills.heurist.base import HeuristBaseTool
 from intentkit.skills.heurist.image_generation_animagine_xl import (
@@ -52,7 +51,6 @@ class Config(SkillConfig):
 async def get_skills(
     config: "Config",
     is_private: bool,
-    store: SkillStoreABC,
     **_,
 ) -> list[HeuristBaseTool]:
     """Get all Heurist AI skills.
@@ -60,7 +58,6 @@ async def get_skills(
     Args:
         config: The configuration for Heurist AI skills.
         is_private: Whether to include private skills.
-        store: The skill store for persisting data.
 
     Returns:
         A list of Heurist AI skills.
@@ -77,7 +74,7 @@ async def get_skills(
     # Get each skill using the cached getter
     result = []
     for name in available_skills:
-        skill = get_heurist_skill(name, store)
+        skill = get_heurist_skill(name)
         if skill:
             result.append(skill)
     return result
@@ -85,58 +82,42 @@ async def get_skills(
 
 def get_heurist_skill(
     name: str,
-    store: SkillStoreABC,
 ) -> HeuristBaseTool:
     """Get a Heurist AI skill by name.
 
     Args:
         name: The name of the skill to get
-        store: The skill store for persisting data
 
     Returns:
         The requested Heurist AI skill
     """
     if name == "image_generation_animagine_xl":
         if name not in _cache:
-            _cache[name] = ImageGenerationAnimagineXL(
-                skill_store=store,
-            )
+            _cache[name] = ImageGenerationAnimagineXL()
         return _cache[name]
     elif name == "image_generation_arthemy_comics":
         if name not in _cache:
-            _cache[name] = ImageGenerationArthemyComics(
-                skill_store=store,
-            )
+            _cache[name] = ImageGenerationArthemyComics()
         return _cache[name]
     elif name == "image_generation_arthemy_real":
         if name not in _cache:
-            _cache[name] = ImageGenerationArthemyReal(
-                skill_store=store,
-            )
+            _cache[name] = ImageGenerationArthemyReal()
         return _cache[name]
     elif name == "image_generation_braindance":
         if name not in _cache:
-            _cache[name] = ImageGenerationBrainDance(
-                skill_store=store,
-            )
+            _cache[name] = ImageGenerationBrainDance()
         return _cache[name]
     elif name == "image_generation_cyber_realistic_xl":
         if name not in _cache:
-            _cache[name] = ImageGenerationCyberRealisticXL(
-                skill_store=store,
-            )
+            _cache[name] = ImageGenerationCyberRealisticXL()
         return _cache[name]
     elif name == "image_generation_flux_1_dev":
         if name not in _cache:
-            _cache[name] = ImageGenerationFlux1Dev(
-                skill_store=store,
-            )
+            _cache[name] = ImageGenerationFlux1Dev()
         return _cache[name]
     elif name == "image_generation_sdxl":
         if name not in _cache:
-            _cache[name] = ImageGenerationSDXL(
-                skill_store=store,
-            )
+            _cache[name] = ImageGenerationSDXL()
         return _cache[name]
     else:
         logger.warning(f"Unknown Heurist skill: {name}")

intentkit/skills/heurist/base.py

@@ -1,11 +1,9 @@
 """Base class for Heurist AI skills."""
 
-from typing import Type
-
-from langchain.tools.base import ToolException
+from langchain_core.tools.base import ToolException
 from pydantic import BaseModel, Field
 
-from intentkit.abstracts.skill import SkillStoreABC
+from intentkit.config.config import config
 from intentkit.skills.base import IntentKitSkill
 
 
@@ -17,17 +15,14 @@ class HeuristBaseTool(IntentKitSkill):
 
     name: str = Field(description="The name of the tool")
     description: str = Field(description="A description of what the tool does")
-    args_schema: Type[BaseModel]
-    skill_store: SkillStoreABC = Field(
-        description="The skill store for persisting data"
-    )
+    args_schema: type[BaseModel]
 
     def get_api_key(self) -> str:
         context = self.get_context()
         skill_config = context.agent.skill_config(self.category)
         api_key_provider = skill_config.get("api_key_provider")
         if api_key_provider == "platform":
-            return self.skill_store.get_system_config("heurist_api_key")
+            return config.heurist_api_key
         # for backward compatibility, may only have api_key in skill_config
         elif skill_config.get("api_key"):
             return skill_config.get("api_key")

intentkit/skills/heurist/image_generation_animagine_xl.py

@@ -1,10 +1,10 @@
 import logging
-from typing import Optional, Type
 
 import httpx
 from epyxid import XID
 from pydantic import BaseModel, Field
 
+from intentkit.config.config import config
 from intentkit.skills.heurist.base import HeuristBaseTool
 from intentkit.utils.s3 import store_image
 
@@ -17,16 +17,16 @@ class ImageGenerationAnimagineXLInput(BaseModel):
     prompt: str = Field(
         description="Text prompt describing the image to generate.",
     )
-    neg_prompt: Optional[str] = Field(
+    neg_prompt: str | None = Field(
         default="(worst quality: 1.4), bad quality, nsfw",
         description="Negative prompt describing what to avoid in the generated image.",
     )
-    width: Optional[int] = Field(
+    width: int | None = Field(
         default=1024,
         le=1024,
         description="Width of the generated image.",
     )
-    height: Optional[int] = Field(
+    height: int | None = Field(
         default=680,
         le=1024,
         description="Height of the generated image.",
@@ -52,14 +52,14 @@ class ImageGenerationAnimagineXL(HeuristBaseTool):
         "AnimagineXL specializes in creating high-quality Japanese anime-style illustrations.\n"
         "If you have height and width, remember to specify them.\n"
     )
-    args_schema: Type[BaseModel] = ImageGenerationAnimagineXLInput
+    args_schema: type[BaseModel] = ImageGenerationAnimagineXLInput
 
     async def _arun(
         self,
         prompt: str,
-        neg_prompt: Optional[str] = "(worst quality: 1.4), bad quality, nsfw",
-        width: Optional[int] = 1024,
-        height: Optional[int] = 680,
+        neg_prompt: str | None = "(worst quality: 1.4), bad quality, nsfw",
+        width: int | None = 1024,
+        height: int | None = 680,
         **kwargs,
     ) -> str:
         """Implementation of the tool to generate Japanese anime-style images using Heurist AI's AnimagineXL model.
@@ -79,20 +79,19 @@ class ImageGenerationAnimagineXL(HeuristBaseTool):
         skill_config = context.agent.skill_config(self.category)
         skill_config = skill_config
 
-        # Get the Heurist API key from the skill store
+        # Get the Heurist API key from configuration
         if "api_key" in skill_config and skill_config["api_key"]:
             api_key = skill_config["api_key"]
             if skill_config.get("rate_limit_number") and skill_config.get(
                 "rate_limit_minutes"
             ):
                 await self.user_rate_limit_by_category(
-                    context.user_id,
                     skill_config["rate_limit_number"],
-                    skill_config["rate_limit_minutes"],
+                    skill_config["rate_limit_minutes"] * 60,
                 )
         else:
-            api_key = self.skill_store.get_system_config("heurist_api_key")
-            await self.user_rate_limit_by_category(context.user_id, 10, 1440)
+            api_key = config.heurist_api_key
+            await self.user_rate_limit_by_category(10, 1440 * 60)
 
         # Generate a unique job ID
         job_id = str(XID())