alita-sdk 0.3.257__py3-none-any.whl → 0.3.562__py3-none-any.whl

alita_sdk/tools/bitbucket/__init__.py

@@ -3,11 +3,13 @@ from typing import Dict, List, Literal, Optional
 from requests.auth import HTTPBasicAuth
 
 from .api_wrapper import BitbucketAPIWrapper
-from .tools import __all__
 from langchain_core.tools import BaseToolkit
 from langchain_core.tools import BaseTool
 from pydantic import BaseModel, Field, ConfigDict, create_model
-from ..utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length, check_connection_response
+
+from ..base.tool import BaseAction
+from ..elitea_base import filter_missconfigured_index_tools
+from ..utils import clean_string, get_max_toolkit_length, check_connection_response
 from ...configurations.bitbucket import BitbucketConfiguration
 from ...configurations.pgvector import PgVectorConfiguration
 import requests
@@ -16,10 +18,9 @@ import requests
 name = "bitbucket"
 
 
-def get_tools(tool):
+def get_toolkit(tool):
     return AlitaBitbucketToolkit.get_toolkit(
         selected_tools=tool['settings'].get('selected_tools', []),
-        url=tool['settings']['url'],
         project=tool['settings']['project'],
         repository=tool['settings']['repository'],
         bitbucket_configuration=tool['settings']['bitbucket_configuration'],
@@ -32,27 +33,26 @@ def get_tools(tool):
         doctype='code',
         embedding_model=tool['settings'].get('embedding_model'),
         toolkit_name=tool.get('toolkit_name')
-    ).get_tools()
+    )
+
+def get_tools(tool):
+    return get_toolkit(tool).get_tools()
 
 
 class AlitaBitbucketToolkit(BaseToolkit):
     tools: List[BaseTool] = []
-    toolkit_max_length: int = 0
 
     @staticmethod
     def toolkit_config_schema() -> BaseModel:
-        selected_tools = {}
-        for t in __all__:
-            default = t['tool'].__pydantic_fields__['args_schema'].default
-            selected_tools[t['name']] = default.schema() if default else default
-        AlitaBitbucketToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
+        selected_tools = {x['name']: x['args_schema'].schema() for x in
+                          BitbucketAPIWrapper.model_construct().get_available_tools()}
         m = create_model(
             name,
-            project=(str, Field(description="Project/Workspace", json_schema_extra={'configuration': True})),
-            repository=(str, Field(description="Repository", json_schema_extra={'max_toolkit_length': AlitaBitbucketToolkit.toolkit_max_length, 'configuration': True})),
+            project=(str, Field(description="Project/Workspace")),
+            repository=(str, Field(description="Repository")),
             branch=(str, Field(description="Main branch", default="main")),
             cloud=(Optional[bool], Field(description="Hosting Option", default=None)),
-            bitbucket_configuration=(Optional[BitbucketConfiguration], Field(description="Bitbucket Configuration", json_schema_extra={'configuration_types': ['bitbucket']})),
+            bitbucket_configuration=(BitbucketConfiguration, Field(description="Bitbucket Configuration", json_schema_extra={'configuration_types': ['bitbucket']})),
             pgvector_configuration=(Optional[PgVectorConfiguration], Field(default=None, description="PgVector Configuration", json_schema_extra={'configuration_types': ['pgvector']})),
             # embedder settings
             embedding_model=(Optional[str], Field(default=None, description="Embedding configuration.", json_schema_extra={'configuration_model': 'embedding'})),
@@ -86,6 +86,7 @@ class AlitaBitbucketToolkit(BaseToolkit):
         return m
 
     @classmethod
+    @filter_missconfigured_index_tools
     def get_toolkit(cls, selected_tools: list[str] | None = None, toolkit_name: Optional[str] = None, **kwargs):
         if selected_tools is None:
             selected_tools = []
@@ -98,16 +99,23 @@ class AlitaBitbucketToolkit(BaseToolkit):
             **(kwargs.get('pgvector_configuration') or {}),
         }
         bitbucket_api_wrapper = BitbucketAPIWrapper(**wrapper_payload)
-        available_tools: List[Dict] = __all__
-        prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''
+        available_tools: List[Dict] = bitbucket_api_wrapper.get_available_tools()
         tools = []
         for tool in available_tools:
             if selected_tools:
                 if tool['name'] not in selected_tools:
                     continue
-            initiated_tool = tool['tool'](api_wrapper=bitbucket_api_wrapper)
-            initiated_tool.name = prefix + tool['name']
-            tools.append(initiated_tool)
+            description = tool["description"] + f"\nrepo: {bitbucket_api_wrapper.repository}"
+            if toolkit_name:
+                description = f"{description}\nToolkit: {toolkit_name}"
+            description = description[:1000]
+            tools.append(BaseAction(
+                api_wrapper=bitbucket_api_wrapper,
+                name=tool["name"],
+                description=description,
+                args_schema=tool["args_schema"],
+                metadata={"toolkit_name": toolkit_name} if toolkit_name else {}
+            ))
         return cls(tools=tools)
 
     def get_tools(self):

alita_sdk/tools/bitbucket/api_wrapper.py

@@ -2,28 +2,134 @@
 from __future__ import annotations
 
 import logging
-from typing import TYPE_CHECKING, Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional
+import fnmatch
 
 from langchain_core.tools import ToolException
-from pydantic import model_validator, SecretStr
+from pydantic import model_validator, SecretStr, create_model, Field
 from .bitbucket_constants import create_pr_data
 from .cloud_api_wrapper import BitbucketCloudApi, BitbucketServerApi
 from pydantic.fields import PrivateAttr
 
-from ..elitea_base import BaseCodeToolApiWrapper
+from ..code_indexer_toolkit import CodeIndexerToolkit
+from ..utils.available_tools_decorator import extend_with_parent_available_tools
+from ..elitea_base import extend_with_file_operations, BaseCodeToolApiWrapper
 
 logger = logging.getLogger(__name__)
 
+# Pydantic model definitions for tool arguments
+CreateBranchModel = create_model(
+    "CreateBranchModel",
+    branch_name=(str, Field(description="The name of the branch, e.g. `my_branch`.")),
+)
 
-if TYPE_CHECKING:
-    pass
+CreatePullRequestModel = create_model(
+    "CreatePullRequestModel",
+    pr_json_data=(str, Field(description=create_pr_data)),
+)
 
+CreateFileModel = create_model(
+    "CreateFileModel",
+    file_path=(str, Field(description="The path of the file")),
+    file_contents=(str, Field(description="The contents of the file")),
+    branch=(str, Field(description="The branch to create the file in")),
+)
 
-class BitbucketAPIWrapper(BaseCodeToolApiWrapper):
+UpdateFileModel = create_model(
+    "UpdateFileModel",
+    file_path=(str, Field(description="The path of the file")),
+    update_query=(str, Field(description="Contains the file contents required to be updated. "
+                                       "The old file contents is wrapped in OLD <<<< and >>>> OLD. "
+                                       "The new file contents is wrapped in NEW <<<< and >>>> NEW")),
+    branch=(str, Field(description="The branch to update the file in")),
+)
+
+ReadFileModel = create_model(
+    "ReadFileModel",
+    file_path=(str, Field(description="The path of the file")),
+    branch=(str, Field(description="The branch to read the file from")),
+)
+
+SetActiveBranchModel = create_model(
+    "SetActiveBranchModel",
+    branch_name=(str, Field(description="The name of the branch, e.g. `my_branch`.")),
+)
+
+ListBranchesInRepoModel = create_model(
+    "ListBranchesInRepoModel",
+    limit=(Optional[int], Field(default=20, description="Maximum number of branches to return. If not provided, all branches will be returned.")),
+    branch_wildcard=(Optional[str], Field(default=None, description="Wildcard pattern to filter branches by name. If not provided, all branches will be returned."))
+)
+
+ListFilesModel = create_model(
+    "ListFilesModel",
+    path=(Optional[str], Field(description="The path to list files from", default=None)),
+    recursive=(bool, Field(description="Whether to list files recursively", default=True)),
+    branch=(Optional[str], Field(description="The branch to list files from")),
+)
+
+GetPullRequestsCommitsModel = create_model(
+    "GetPullRequestsCommitsModel",
+    pr_id=(str, Field(description="The ID of the pull request to get commits from")),
+)
+
+GetPullRequestModel = create_model(
+    "GetPullRequestModel",
+    pr_id=(str, Field(description="The ID of the pull request to get details from")),
+)
+
+GetPullRequestsChangesModel = create_model(
+    "GetPullRequestsChangesModel",
+    pr_id=(str, Field(description="The ID of the pull request to get changes from")),
+)
+
+AddPullRequestCommentModel = create_model(
+    "AddPullRequestCommentModel",
+    pr_id=(str, Field(description="The ID of the pull request to add a comment to")),
+    content=(str, Field(description="The comment content")),
+    inline=(Optional[dict], Field(default=None, description="Inline comment details. Example: {'from': 57, 'to': 122, 'path': '<string>'}"))
+)
+
+DeleteFileModel = create_model(
+    "DeleteFileModel",
+    file_path=(str, Field(description="The path of the file")),
+    branch=(str, Field(description="The branch to delete the file from")),
+    commit_message=(str, Field(default=None, description="Commit message for deleting the file. Optional.")),
+)
+
+AppendFileModel = create_model(
+    "AppendFileModel",
+    file_path=(str, Field(description="The path of the file")),
+    content=(str, Field(description="The content to append to the file")),
+    branch=(str, Field(description="The branch to append the file in")),
+)
+
+GetIssuesModel = create_model(
+    "GetIssuesModel",
+)
+
+GetIssueModel = create_model(
+    "GetIssueModel",
+    issue_number=(int, Field(description="The number of the issue")),
+)
+
+CommentOnIssueModel = create_model(
+    "CommentOnIssueModel",
+    comment_query=(str, Field(description="The comment query string")),
+)
+
+
+class BitbucketAPIWrapper(CodeIndexerToolkit):
     """Wrapper for Bitbucket API."""
 
     _bitbucket: Any = PrivateAttr()
     _active_branch: Any = PrivateAttr()
+    
+    # Import file operation methods from BaseCodeToolApiWrapper
+    read_file_chunk = BaseCodeToolApiWrapper.read_file_chunk
+    read_multiple_files = BaseCodeToolApiWrapper.read_multiple_files
+    search_file = BaseCodeToolApiWrapper.search_file
+    edit_file = BaseCodeToolApiWrapper.edit_file
     url: str = ''
     project: str = ''
     """The key of the project this repo belongs to"""
@@ -41,18 +147,6 @@ class BitbucketAPIWrapper(BaseCodeToolApiWrapper):
     """Bitbucket installation type: true for cloud, false for server.
     """
 
-    llm: Optional[Any] = None
-    # Alita instance
-    alita: Optional[Any] = None
-
-    # Vector store configuration
-    connection_string: Optional[SecretStr] = None
-    collection_name: Optional[str] = None
-    doctype: Optional[str] = 'code'
-    embedding_model: Optional[str] = "HuggingFaceEmbeddings"
-    embedding_model_params: Optional[Dict[str, Any]] = {"model_name": "sentence-transformers/all-MiniLM-L6-v2"}
-    vectorstore_type: Optional[str] = "PGVector"
-
     @model_validator(mode='before')
     @classmethod
     def validate_env(cls, values: Dict) -> Dict:
@@ -81,16 +175,36 @@ class BitbucketAPIWrapper(BaseCodeToolApiWrapper):
             repository=values['repository']
         )
         cls._active_branch = values.get('branch')
-        return values
+        return super().validate_toolkit(values)
 
-    def set_active_branch(self, branch: str) -> None:
+    def set_active_branch(self, branch_name: str) -> str:
         """Set the active branch for the bot."""
-        self._active_branch = branch
-        return f"Active branch set to `{branch}`"
+        self._active_branch = branch_name
+        return f"Active branch set to `{branch_name}`"
+
+    def list_branches_in_repo(self, limit: Optional[int] = 20, branch_wildcard: Optional[str] = None) -> List[str]:
+        """
+        Lists branches in the repository with optional limit and wildcard filtering.
+
+        Parameters:
+            limit (Optional[int]): Maximum number of branches to return
+            branch_wildcard (Optional[str]): Wildcard pattern to filter branches (e.g., '*dev')
+
+        Returns:
+            List[str]: List containing names of branches
+        """
+        try:
+            branches = self._bitbucket.list_branches()
+
+            if branch_wildcard:
+                branches = [branch for branch in branches if fnmatch.fnmatch(branch, branch_wildcard)]
 
-    def list_branches_in_repo(self) -> List[str]:
-        """List all branches in the repository."""
-        return self._bitbucket.list_branches()
+            if limit is not None:
+                branches = branches[:limit]
+
+            return "Found branches: " + ", ".join(branches)
+        except Exception as e:
+            return f"Failed to list branches: {str(e)}"
 
     def create_branch(self, branch_name: str) -> None:
         """Create a new branch in the repository."""
@@ -253,12 +367,15 @@ class BitbucketAPIWrapper(BaseCodeToolApiWrapper):
     #     except Exception as e:
     #         raise ToolException(f"Can't extract file commit hash (`{file_path}`) due to error:\n{str(e)}")
 
-    def _read_file(self, file_path: str, branch: str) -> str:
+    def _read_file(self, file_path: str, branch: str, **kwargs) -> str:
         """
-        Reads a file from the gitlab repo
+        Reads a file from the bitbucket repo with optional partial read support.
+        
         Parameters:
             file_path(str): the file path
             branch(str): branch name (by default: active_branch)
+            **kwargs: Additional parameters (offset, limit, head, tail) - currently ignored,
+                     partial read handled client-side by base class methods
         Returns:
             str: The file decoded as a string
         """
@@ -266,3 +383,144 @@ class BitbucketAPIWrapper(BaseCodeToolApiWrapper):
             return self._bitbucket.get_file(file_path=file_path, branch=branch)
         except Exception as e:
             raise ToolException(f"Can't extract file content (`{file_path}`) due to error:\n{str(e)}")
+
+    def list_files(self, path: str = None, recursive: bool = True, branch: str = None) -> List[str]:
+        """List files in the repository with optional path, recursive search, and branch."""
+        branch = branch if branch else self._active_branch
+        try:
+            files_str = self._get_files(path, branch)
+            # Parse the string response to extract file paths
+            # This is a simplified implementation - might need adjustment based on actual response format
+            import ast
+            try:
+                files_list = ast.literal_eval(files_str)
+                if isinstance(files_list, list):
+                    return files_list
+                else:
+                    return [str(files_list)]
+            except:
+                return [files_str] if files_str else []
+        except Exception as e:
+            return f"Failed to list files: {str(e)}"
+
+    def read_file(self, file_path: str, branch: str) -> str:
+        """Read the contents of a file in the repository."""
+        try:
+            return self._read_file(file_path, branch)
+        except Exception as e:
+            return f"Failed to read file {file_path}: {str(e)}"
+    
+    def _write_file(
+        self,
+        file_path: str,
+        content: str,
+        branch: str = None,
+        commit_message: str = None
+    ) -> str:
+        """
+        Write content to a file (create or update).
+        
+        Parameters:
+            file_path: Path to the file
+            content: New file content
+            branch: Branch name (uses active branch if None)
+            commit_message: Commit message (not used by Bitbucket API)
+            
+        Returns:
+            Success message
+        """
+        try:
+            branch = branch or self._active_branch
+            
+            # Check if file exists by attempting to read it
+            try:
+                self._read_file(file_path, branch)
+                # File exists, update it using OLD/NEW format
+                old_content = self._read_file(file_path, branch)
+                update_query = f"OLD <<<<\n{old_content}\n>>>> OLD\nNEW <<<<\n{content}\n>>>> NEW"
+                self._bitbucket.update_file(file_path=file_path, update_query=update_query, branch=branch)
+                return f"Updated file {file_path}"
+            except:
+                # File doesn't exist, create it
+                self._bitbucket.create_file(file_path=file_path, file_contents=content, branch=branch)
+                return f"Created file {file_path}"
+        except Exception as e:
+            raise ToolException(f"Unable to write file {file_path}: {str(e)}")
+
+    @extend_with_parent_available_tools
+    @extend_with_file_operations
+    def get_available_tools(self):
+        return [
+            {
+                "name": "create_branch",
+                "ref": self.create_branch,
+                "description": self.create_branch.__doc__ or "Create a new branch in the repository.",
+                "args_schema": CreateBranchModel,
+            },
+            {
+                "name": "list_branches_in_repo",
+                "ref": self.list_branches_in_repo,
+                "description": self.list_branches_in_repo.__doc__ or "List branches in the repository with optional limit and wildcard filtering.",
+                "args_schema": ListBranchesInRepoModel,
+            },
+            {
+                "name": "list_files",
+                "ref": self.list_files,
+                "description": self.list_files.__doc__ or "List files in the repository with optional path, recursive search, and branch.",
+                "args_schema": ListFilesModel,
+            },
+            {
+                "name": "create_pull_request",
+                "ref": self.create_pull_request,
+                "description": self.create_pull_request.__doc__ or "Create a pull request in the repository.",
+                "args_schema": CreatePullRequestModel,
+            },
+            {
+                "name": "create_file",
+                "ref": self.create_file,
+                "description": self.create_file.__doc__ or "Create a new file in the repository.",
+                "args_schema": CreateFileModel,
+            },
+            {
+                "name": "read_file",
+                "ref": self.read_file,
+                "description": self.read_file.__doc__ or "Read the contents of a file in the repository.",
+                "args_schema": ReadFileModel,
+            },
+            {
+                "name": "update_file",
+                "ref": self.update_file,
+                "description": self.update_file.__doc__ or "Update the contents of a file in the repository.",
+                "args_schema": UpdateFileModel,
+            },
+            {
+                "name": "set_active_branch",
+                "ref": self.set_active_branch,
+                "description": self.set_active_branch.__doc__ or "Set the active branch in the repository.",
+                "args_schema": SetActiveBranchModel,
+            },
+            {
+                "name": "get_pull_requests_commits",
+                "ref": self.get_pull_requests_commits,
+                "description": self.get_pull_requests_commits.__doc__ or "Get commits from a pull request in the repository.",
+                "args_schema": GetPullRequestsCommitsModel,
+            },
+            {
+                "name": "get_pull_request",
+                "ref": self.get_pull_request,
+                "description": self.get_pull_request.__doc__ or "Get details of a pull request in the repository.",
+                "args_schema": GetPullRequestModel,
+            },
+            {
+                "name": "get_pull_requests_changes",
+                "ref": self.get_pull_requests_changes,
+                "description": self.get_pull_requests_changes.__doc__ or "Get changes from a pull request in the repository.",
+                "args_schema": GetPullRequestsChangesModel,
+            },
+            {
+                "name": "add_pull_request_comment",
+                "ref": self.add_pull_request_comment,
+                "description": self.add_pull_request_comment.__doc__ or "Add a comment to a pull request in the repository.",
+                "args_schema": AddPullRequestCommentModel,
+            }
+        ]

alita_sdk/tools/bitbucket/cloud_api_wrapper.py

@@ -35,7 +35,7 @@ def normalize_response(response) -> Dict[str, Any]:
 class BitbucketApiAbstract(ABC):
 
     @abstractmethod
-    def list_branches(self) -> str:
+    def list_branches(self) -> List[str]:
         pass
 
     @abstractmethod
@@ -86,9 +86,9 @@ class BitbucketServerApi(BitbucketApiAbstract):
         self.password = password
         self.api_client = Bitbucket(url=url, username=username, password=password)
 
-    def list_branches(self) -> str:
+    def list_branches(self) -> List[str]:
         branches = self.api_client.get_branches(project_key=self.project, repository_slug=self.repository)
-        return json.dumps([branch['displayId'] for branch in branches])
+        return [branch['displayId'] for branch in branches]
 
     def create_branch(self, branch_name: str, branch_from: str) -> Response:
         return self.api_client.create_branch(
@@ -257,10 +257,10 @@ class BitbucketCloudApi(BitbucketApiAbstract):
         except Exception as e:
             raise ToolException(f"Unable to connect to the repository '{self.repository_name}' due to error:\n{str(e)}")
 
-    def list_branches(self) -> str:
+    def list_branches(self) -> List[str]:
         branches = self.repository.branches.each()
         branch_names = [branch.name for branch in branches]
-        return ', '.join(branch_names)
+        return branch_names
 
     def _get_branch(self, branch_name: str) -> Response:
         return self.repository.branches.get(branch_name)

alita_sdk/tools/browser/__init__.py

@@ -1,16 +1,19 @@
 from typing import List, Optional, Literal
 from langchain_core.tools import BaseTool, BaseToolkit
 
-from pydantic import create_model, BaseModel, ConfigDict, Field, SecretStr, model_validator
+from pydantic import create_model, BaseModel, ConfigDict, Field, model_validator
 
 from langchain_community.utilities.google_search import GoogleSearchAPIWrapper
 from langchain_community.utilities.wikipedia import WikipediaAPIWrapper
 from .google_search_rag import GoogleSearchResults
 from .crawler import SingleURLCrawler, MultiURLCrawler, GetHTMLContent, GetPDFContent
 from .wiki import WikipediaQueryRun
-from ..utils import get_max_toolkit_length, clean_string, TOOLKIT_SPLITTER
+from ..utils import get_max_toolkit_length, clean_string
+from ...configurations.browser import BrowserConfiguration
 from logging import getLogger
 
+from ...configurations.pgvector import PgVectorConfiguration
+
 logger = getLogger(__name__)
 
 name = "browser"
@@ -19,8 +22,9 @@ name = "browser"
 def get_tools(tool):
     return BrowserToolkit().get_toolkit(
         selected_tools=tool['settings'].get('selected_tools', []),
-        google_api_key=tool['settings'].get('google_api_key'),
-        google_cse_id=tool['settings'].get("google_cse_id"),
+        browser_configuration=tool['settings']['browser_configuration'],
+        pgvector_configuration=tool['settings'].get('pgvector_configuration', {}),
+        embedding_model=tool['settings'].get('embedding_model'),
         toolkit_name=tool.get('toolkit_name', '')
     ).get_tools()
 
@@ -38,22 +42,29 @@ class BrowserToolkit(BaseToolkit):
             'google': GoogleSearchResults.__pydantic_fields__['args_schema'].default.schema(),
             'wiki': WikipediaQueryRun.__pydantic_fields__['args_schema'].default.schema()
         }
-        BrowserToolkit.toolkit_max_length = get_max_toolkit_length(selected_tools)
 
         def validate_google_fields(cls, values):
             if 'google' in values.get('selected_tools', []):
-                google_cse_id = values.get('google_cse_id') is not None
-                google_api_key = values.get('google_api_key') is not None
+                browser_config = values.get('browser_configuration', {})
+                google_cse_id = browser_config.get('google_cse_id') is not None if browser_config else False
+                google_api_key = browser_config.get('google_api_key') is not None if browser_config else False
                 if not (google_cse_id and google_api_key):
                     raise ValueError("google_cse_id and google_api_key are required when 'google' is in selected_tools")
             return values
 
         return create_model(
             name,
-            __config__=ConfigDict(json_schema_extra={'metadata': {"label": "Browser", "icon_url": None, "categories": ["testing"], "extra_categories": ["web scraping", "search", "crawler"]}}),
-            google_cse_id=(Optional[str], Field(description="Google CSE id", default=None)),
-            google_api_key=(Optional[SecretStr],
-                            Field(description="Google API key", default=None, json_schema_extra={'secret': True})),
+            __config__=ConfigDict(json_schema_extra={'metadata': {"label": "Browser", "icon_url": None,
+                                                                  "categories": ["testing"],
+                                                                  "extra_categories": [
+                                                                      "web scraping", "search", "crawler"
+                                                                  ]}}),
+            browser_configuration=(Optional[BrowserConfiguration],
+                                   Field(description="Browser Configuration (required for tools and `google`)",
+                                         default=None, json_schema_extra={'configuration_types': ['browser']})),
+            pgvector_configuration=(Optional[PgVectorConfiguration],
+                                    Field(description="PgVector configuration (required for tools `multi_url_crawler`)",
+                                          default=None, json_schema_extra={'configuration_types': ['pgvector']})),
             selected_tools=(List[Literal[tuple(selected_tools)]],
                             Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
             __validators__={
@@ -65,8 +76,19 @@ class BrowserToolkit(BaseToolkit):
     def get_toolkit(cls, selected_tools: list[str] | None = None, toolkit_name: Optional[str] = None, **kwargs):
         if selected_tools is None:
             selected_tools = []
+
+        wrapper_payload_google = {
+            **kwargs,
+            **kwargs.get('browser_configuration', {}),
+            **kwargs.get('pgvector_configuration', {}),
+        }
+
+        wrapper_payload_rag_based = {
+            **kwargs,
+            **kwargs.get('pgvector_configuration', {}),
+        }
+
         tools = []
-        prefix = clean_string(toolkit_name, cls.toolkit_max_length) + TOOLKIT_SPLITTER if toolkit_name else ''
         if not selected_tools:
             selected_tools = [
                 'single_url_crawler',
@@ -80,7 +102,7 @@ class BrowserToolkit(BaseToolkit):
             if tool == 'single_url_crawler':
                 tool_entry = SingleURLCrawler()
             elif tool == 'multi_url_crawler':
-                tool_entry = MultiURLCrawler()
+                tool_entry = MultiURLCrawler(**wrapper_payload_rag_based)
             elif tool == 'get_html_content':
                 tool_entry = GetHTMLContent()
             elif tool == 'get_pdf_content':
@@ -88,8 +110,8 @@ class BrowserToolkit(BaseToolkit):
             elif tool == 'google':
                 try:
                     google_api_wrapper = GoogleSearchAPIWrapper(
-                        google_api_key=kwargs.get("google_api_key"),
-                        google_cse_id=kwargs.get("google_cse_id"),
+                        google_api_key=wrapper_payload_google.get('google_api_key'),
+                        google_cse_id=wrapper_payload_google.get('google_cse_id')
                     )
                     tool_entry = GoogleSearchResults(api_wrapper=google_api_wrapper)
                     # rename the tool to avoid conflicts
@@ -103,7 +125,10 @@ class BrowserToolkit(BaseToolkit):
 
             # Only add the tool if it was successfully created
             if tool_entry is not None:
-                tool_entry.name = f"{prefix}{tool_entry.name}"
+                if toolkit_name:
+                    tool_entry.description = f"{tool_entry.description}\nToolkit: {toolkit_name}"
+                    tool_entry.description = tool_entry.description[:1000]
+                    tool_entry.metadata = {"toolkit_name": toolkit_name}
                 tools.append(tool_entry)
         return cls(tools=tools)
 

alita_sdk/tools/browser/crawler.py

@@ -27,13 +27,15 @@ class MultiURLCrawler(BaseTool):
     max_response_size: int = 3000
     name: str = "multi_url_crawler"
     description: str = "Crawls multiple URLs and returns the content related to query"
+    connection_string: str = None
     args_schema: Type[BaseModel] = create_model("MultiURLCrawlerModel",
                                                 query=(str, Field(description="Query text to search pages")),
                                                 urls=(list[str], Field(description="list of URLs to search like ['url1', 'url2']")))
 
     def _run(self, query: str, urls: list[str], run_manager=None):
         urls = [url.strip() for url in urls]
-        return webRag(urls, self.max_response_size, query)
+        return webRag(urls=urls, max_response_size=self.max_response_size, query=query,
+                      connection_string=self.connection_string)
 
 
 class GetHTMLContent(BaseTool):