alita-sdk 0.3.205__py3-none-any.whl → 0.3.207__py3-none-any.whl

alita_sdk/community/analysis/github_analyse/api_wrapper.py

@@ -1,166 +0,0 @@
-import logging
-from typing import Optional, Any
-from langchain_core.callbacks import dispatch_custom_event
-from pydantic import BaseModel, Field
-
-from elitea_analyse.github.github_org import GitHubGetOrgLvl
-from elitea_analyse.github.main_github import (
-   extract_commits_from_multiple_repos,
-   extract_pull_requests_from_multiple_repos,
-   extract_repositories_list,
-   extract_repositories_extended_data,
-)
-
-from alita_sdk.tools.elitea_base import BaseToolApiWrapper
-from alita_sdk.runtime.utils.save_dataframe import save_dataframe_to_artifact
-from alita_sdk.runtime.tools.artifact import ArtifactWrapper
-from alita_sdk.runtime.utils.logging import with_streamlit_logs
-
-
-logger = logging.getLogger(__name__)
-
-
-class GetGithubCommitsFromReposArgs(BaseModel):
-    since_after: str = Field( description="Date to filter commits from, in 'YYYY-MM-DD' format." )
-    repos: Optional[str] = Field(
-        description="Comma-separated list of repositories to extract commits from.",
-        default="",
-    )
-
-
-class GetGithubRepositoriesListArgs(BaseModel):
-    pushed_after: str = Field( description="Date to filter repositories by, in 'YYYY-MM-DD' format." )
-
-
-class GitHubAnalyseWrapper(BaseToolApiWrapper):
-    artifacts_wrapper: ArtifactWrapper
-    repos: str  # Comma-separated list of GitHub repository names e.g. 'repo1,repo2'
-    git: GitHubGetOrgLvl  # GitHub client
-
-    class Config:
-        arbitrary_types_allowed = True
-
-    def get_commits_from_repos(self, since_after: str, repos: Optional[str] = None) -> str:
-        """
-        Extracts commit data from multiple GitHub repositories since the specified date. Saves the result to a CSV file.
-
-        repos : str
-            The string containing repositories names to extract data from, separated by commas.
-        since_date : str
-            The date to start extracting commits from, in 'YYYY-MM-DD' format.
-        """
-        repos = repos or self.repos
-        df_commits = extract_commits_from_multiple_repos(repos, since_after, git=self.git)
-
-        if df_commits is None or df_commits.empty:
-            return f"No commits found for repositories: {repos} since {since_after}"
-
-        output_filename = f"commits_{repos.replace(',', '_')}.csv"
-        save_dataframe_to_artifact( self.artifacts_wrapper, df_commits, output_filename, {"index": False} )
-
-        return f"GitHub commits data for {repos} saved to {output_filename}"
-
-    def get_pull_requests_from_repos(self, since_after: str, repos: Optional[str] = None) -> str:
-        """
-        Extracts pull request data from multiple GitHub repositories since the specified date. 
-        Saves the result to a CSV file.
-
-        repos: str
-            The string containing repositories names to extract data from, separated by commas.
-        since_date: str
-            The date to start extracting pull requests from, in 'YYYY-MM-DD' format.
-        """
-        repos = repos or self.repos
-        df_pull_requests = extract_pull_requests_from_multiple_repos(repos, since_after, git=self.git)
-
-        output_filename = f"pull_requests_details_{repos.replace(',', '_')}.csv"
-        save_dataframe_to_artifact( self.artifacts_wrapper, df_pull_requests, output_filename, {"index": False} )
-
-        return f"GitHub pull requests data saved to {output_filename}"
-
-    def get_repositories_list(self, pushed_after: str) -> str:
-        """
-        Extracts a list of GitHub repositories that were pushed after the specified date. 
-        Saves the result to a CSV file.
-
-        pushed_after : str
-            The date to filter repositories by, in 'YYYY-MM-DD' format.
-        """
-        df_repos = extract_repositories_list(pushed_after, git=self.git)
-
-        output_filename = "github_repos_list.csv"
-        save_dataframe_to_artifact( self.artifacts_wrapper, df_repos, output_filename, {"index": False} )
-        dispatch_custom_event(
-            "thinking_step",
-            data={
-                "message": f"Extracted {len(df_repos)} repositories pushed after {pushed_after}.",
-                "tool_name": "github_repositories_list_extraction",
-                "toolkit": "analyse_github",
-            },
-        )
-
-        return f"GitHub repositories list saved to {output_filename}"
-
-    @with_streamlit_logs(tool_name="get_github_repositories_extended_data")
-    def get_repositories_extended_data(self, pushed_after: str) -> str:
-        """
-        Extracts extended information about GitHub repositories that were pushed after the specified date. 
-        Saves the result to a CSV file.
-
-        pushed_after : str
-            The date to filter repositories by, in 'YYYY-MM-DD' format.
-        """
-        df_repos_extended = extract_repositories_extended_data(pushed_after, git=self.git)
-
-        output_filename = "github_repos_extended_info.csv"
-        save_dataframe_to_artifact( self.artifacts_wrapper, df_repos_extended, output_filename, {"index": False} )
-
-        dispatch_custom_event(
-            "thinking_step",
-            data={
-                "message": (
-                    f"Extracted extended data for {len(df_repos_extended)} repositories "
-                    f"pushed after {pushed_after}."
-                ),
-                "tool_name": "github_repositories_extended_data_extraction",
-                "toolkit": "analyse_github",
-            },
-        )
-
-        return f"Extended repository info that you have access saved to {output_filename}"
-
-    def get_available_tools(self):
-        """Get a list of available tools."""
-        return [
-            {
-                "name": "get_commits_from_repos",
-                "description": self.get_commits_from_repos.__doc__,
-                "args_schema": GetGithubCommitsFromReposArgs,
-                "ref": self.get_commits_from_repos,
-            },
-            {
-                "name": "get_pull_requests_from_repos",
-                "description": self.get_pull_requests_from_repos.__doc__,
-                "args_schema": GetGithubCommitsFromReposArgs,
-                "ref": self.get_pull_requests_from_repos,
-            },
-            {
-                "name": "get_repositories_list",
-                "description": self.get_repositories_list.__doc__,
-                "args_schema": GetGithubRepositoriesListArgs,
-                "ref": self.get_repositories_list,
-            },
-            {
-                "name": "get_repositories_extended_data",
-                "description": self.get_repositories_extended_data.__doc__,
-                "args_schema": GetGithubRepositoriesListArgs,
-                "ref": self.get_repositories_extended_data,
-            },
-        ]
-
-    def run(self, mode: str, *args: Any, **kwargs: Any):
-        for tool in self.get_available_tools():
-            if tool["name"] == mode:
-                return tool["ref"](*args, **kwargs)
-
-        raise ValueError(f"Unknown mode: {mode}")

alita_sdk/community/analysis/gitlab_analyse/__init__.py

@@ -1,110 +0,0 @@
-from typing import List, Optional, Literal
-from elitea_analyse.git.git_search import GitLabV4Search
-from pydantic import SecretStr, create_model, BaseModel, ConfigDict, Field
-
-from langchain_core.tools import BaseTool, BaseToolkit
-
-from alita_sdk.tools.utils import get_max_toolkit_length
-from alita_sdk.tools.base.tool import BaseAction
-from alita_sdk.runtime.clients.client import AlitaClient 
-from alita_sdk.runtime.tools.artifact import ArtifactWrapper
-from .api_wrapper import GitLabAnalyseWrapper
-
-from ...utils import check_schema
-
-
-name = "Analyse_GitLab"
-
-
-class AnalyseGitLab(BaseToolkit):
-    tools: List[BaseTool] = []
-    toolkit_max_length: int = 0
-
-    @staticmethod
-    def toolkit_config_schema() -> type[BaseModel]:
-        selected_tools = {
-            x["name"]: x["args_schema"].schema()
-            for x in GitLabAnalyseWrapper.model_construct().get_available_tools()
-        }
-        AnalyseGitLab.toolkit_max_length = get_max_toolkit_length(selected_tools)
-
-        return create_model(
-            "analyse_gitlab",
-            url=(
-                str,
-                Field(
-                    description="GitLab URL (e.g., git.epam.com)",
-                    json_schema_extra={"toolkit_name": True, "max_toolkit_length": AnalyseGitLab.toolkit_max_length}
-                )
-            ),
-            project_ids=(Optional[str], Field(description="GitLab project ids separated by comma", default=None)),
-            jira_project_keys=(Optional[str],
-                               Field(description="GitLab project Jira keys separated by comma", default=None)),
-            token=(SecretStr, Field(description="GitLab Personal Access Token", json_schema_extra={"secret": True})),
-            default_branch_name=(Optional[str], Field(description="Default branch name", default="master")),
-            artifact_bucket_path=(Optional[str], Field(description="Artifact Bucket Path", default="analyse-gitlab")),
-            selected_tools=(
-                List[Literal[tuple(selected_tools)]],
-                Field(default=[], json_schema_extra={"args_schemas": selected_tools})
-            ),
-            __config__=ConfigDict(json_schema_extra={"metadata": {
-                "label": "Analyse_GitLab",
-                "icon_url": "gitlab-icon.svg", # if exists
-                "hidden": True,
-                "sections": {
-                    "auth": {
-                        "required": True,
-                        "subsections": [{"name": "Token", "fields": ["token"]}],
-                    }
-                },
-            }})
-        )
-
-    @classmethod
-    def get_toolkit(cls, client: "AlitaClient", selected_tools: list[str], **kwargs):
-        bucket_path = kwargs.get("artifact_bucket_path") or "analyse-gitlab"
-        artifact_wrapper = ArtifactWrapper(client=client, bucket=bucket_path)
-        check_schema(artifact_wrapper)
-
-        jira_project_keys = kwargs.get("jira_project_keys") or ""
-        project_ids = kwargs.get("project_ids")  or ""
-        url = kwargs.get("url")
-        token = kwargs.get("token")
-
-        if not url or not token:
-            raise ValueError("GitLab URL and token are required.")
-
-        gitlab_search = GitLabV4Search(
-            url=url,
-            default_branch_name=kwargs.get("default_branch_name", "master"),
-            token=token,
-        )
-
-        gitlab_analyse_wrapper = GitLabAnalyseWrapper(
-            artifacts_wrapper=artifact_wrapper,
-            project_ids=project_ids,
-            jira_project_keys=jira_project_keys,
-            gitlab_search=gitlab_search,
-        )
-
-        selected_tools = selected_tools or []
-        available_tools = gitlab_analyse_wrapper.get_available_tools()
-
-        tools = []
-        for tool in available_tools:
-            if selected_tools:
-                if tool["name"] not in selected_tools:
-                    continue
-            tools.append(
-                BaseAction(
-                    api_wrapper=gitlab_analyse_wrapper,
-                    name=tool["name"],
-                    description=tool["description"],
-                    args_schema=tool["args_schema"],
-                )
-            )
-
-        return cls(tools=tools)
-
-    def get_tools(self):
-        return self.tools

alita_sdk/community/analysis/gitlab_analyse/api_wrapper.py

@@ -1,172 +0,0 @@
-import logging
-from typing import Any
-from pydantic import BaseModel, Field
-from typing import Optional
-
-from elitea_analyse.git.main import (
-    get_git_projects_list,
-    get_git_projects_that_in_jira,
-    get_git_commits,
-    get_git_merge_requests,
-)
-from elitea_analyse.git.git_search import GitLabV4Search
-
-
-from alita_sdk.tools.elitea_base import BaseToolApiWrapper
-from alita_sdk.runtime.utils.save_dataframe import save_dataframe_to_artifact
-from alita_sdk.runtime.tools.artifact import ArtifactWrapper
-
-
-logger = logging.getLogger(__name__)
-
-
-class GitLabProjectsListArgs(BaseModel):
-    date: str = Field(
-        description="Filter projects by last activity date in 'YYYY-MM-DD' format."
-    )
-
-class GitLabProjectsListInJiraArgs(BaseModel):
-    jira_project_keys: Optional[str] = Field(description="Comma-separated Jira project keys.", default=None)
-
-class GitLabCommitsArgs(BaseModel):
-    project_ids: Optional[str] = Field(description="GitLab project ID.", default=None)
-    since_date:str = Field(description="Date filter in 'YYYY-MM-DD' format.")
-
-
-class GitLabAnalyseWrapper(BaseToolApiWrapper):
-    artifacts_wrapper: ArtifactWrapper
-    project_ids: str  # Comma-separated list of GitLab project IDs
-    jira_project_keys: str  # Comma-separated list of Jira projects' keys
-    gitlab_search: GitLabV4Search  # GitLab search client
-
-    class Config:
-        arbitrary_types_allowed = True
-
-    def get_gitlab_projects_list(self, date: str) -> str:
-        """
-        Get projects list that user has access to in GitLab.
-
-        date: str
-            Filter projects by last activity date.
-            Date in 'YYYY-MM-DD' format.
-        """
-
-        df_project_list = get_git_projects_list(date, git=self.gitlab_search)
-
-        save_dataframe_to_artifact(
-            self.artifacts_wrapper, df_project_list, "gitlab_projects_info.csv", csv_options={"index": False}
-        )
-
-        return (
-            f"You have access to {len(df_project_list)}. "
-            f"Data has been downloaded to the bucket as 'gitlab_projects_info.csv'"
-        )
-
-    def get_gitlab_projects_that_in_jira(self, jira_project_keys: Optional[str] = None) -> str:
-        """
-        Find GitLab projects that correspond to Jira projects by matching names.
-
-        jira_project_keys: str
-            Comma-separated Jira project keys.
-        """
-        jira_project_keys = jira_project_keys or self.jira_project_keys
-        df_projects = get_git_projects_that_in_jira(
-            jira_project_keys, git=self.gitlab_search)
-
-        if df_projects is None or df_projects.empty:
-            return "No GitLab projects found that match the provided Jira project keys."
-
-        save_dataframe_to_artifact(
-            self.artifacts_wrapper, df_projects, "gitlab_projects_that_in_Jira.csv", csv_options={"index": False},
-        )
-
-        return (
-            f"Found {len(df_projects)} GitLab projects that match Jira project names. "
-            f"Data has been downloaded to the bucket as 'gitlab_projects_that_in_Jira.csv'."
-        )
-
-    def get_gitlab_commits(self, since_date: str, project_ids: Optional[str] = None) -> str:
-        """
-        Get commit data for specified GitLab project.
-
-        project_id: str
-            GitLab project ID.
-        since_date: str
-            Date filter in 'YYYY-MM-DD' format.
-        """
-        project_ids = project_ids or self.project_ids
-        df_commits = get_git_commits(
-            project_ids, since_date, git_search=self.gitlab_search
-        )
-
-        if df_commits is None or df_commits.empty:
-            return f'There are no commits in the project {project_ids} created after {since_date}'
-
-        save_dataframe_to_artifact(
-            self.artifacts_wrapper, df_commits, f"commits_details_{project_ids}.csv", csv_options={"index": False},
-        )
-
-        return (
-            f"Commits data for project {project_ids} has been saved. "
-            f"Data has been downloaded to the bucket as 'commits_details_{project_ids}.csv'."
-        )
-
-    def get_gitlab_merge_requests(self, since_date: str, project_ids: Optional[str] = None) -> str:
-        """
-        Get merge requests for specified GitLab project.
-
-        project_ids: str
-            GitLab project ID.
-        since_date: str
-            Date filter in 'YYYY-MM-DD' format.
-        """
-        project_ids = project_ids or self.project_ids
-        df_mrs = get_git_merge_requests(
-            project_ids, since_date, git_search=self.gitlab_search)
-
-        if df_mrs is None or df_mrs.empty:
-            return f'There are no merge requests in the project {project_ids} created after {since_date}'
-
-        save_dataframe_to_artifact(
-            self.artifacts_wrapper, df_mrs, f"merge_requests_details_{project_ids}.csv", csv_options={"index": False},
-        )
-
-        return (
-            f"Merge requests data for project {project_ids} has been saved. "
-            f"Data has been downloaded to the bucket as 'merge_requests_details_{project_ids}.csv'."
-        )
-
-
-    def get_available_tools(self):
-        return [
-            {
-                "name": "get_gitlab_projects_list",
-                "description": self.get_gitlab_projects_list.__doc__,
-                "args_schema": GitLabProjectsListArgs ,
-                "ref": self.get_gitlab_projects_list
-            },
-            {
-                "name": "get_gitlab_projects_that_in_jira",
-                "description": self.get_gitlab_projects_that_in_jira.__doc__,
-                "args_schema": GitLabProjectsListInJiraArgs,
-                "ref": self.get_gitlab_projects_that_in_jira
-            },
-            {
-                "name": "get_gitlab_commits",
-                "description": self.get_gitlab_commits.__doc__,
-                "args_schema": GitLabCommitsArgs,
-                "ref": self.get_gitlab_commits
-            },
-            {
-                "name": "get_gitlab_merge_requests",
-                "description": self.get_gitlab_merge_requests.__doc__,
-                "args_schema": GitLabCommitsArgs,
-                "ref": self.get_gitlab_merge_requests
-            }
-        ]
-
-    def run(self, mode: str, *args: Any, **kwargs: Any):
-        for tool in self.get_available_tools():
-            if tool["name"] == mode:
-                return tool["ref"](*args, **kwargs)
-        raise ValueError(f"Unknown mode: {mode}")

alita_sdk/community/analysis/jira_analyse/__init__.py

@@ -1,141 +0,0 @@
-import json
-from typing import List, Optional, Literal
-from pydantic import create_model, BaseModel, ConfigDict, Field
-
-from langchain_core.tools import BaseTool, BaseToolkit
-
-from elitea_analyse.jira.jira_connect import connect_to_jira
-from alita_sdk.tools.utils import clean_string, TOOLKIT_SPLITTER, get_max_toolkit_length
-from alita_sdk.tools.base.tool import BaseAction
-from alita_sdk.runtime.clients.client import AlitaClient
-from alita_sdk.runtime.tools.artifact import ArtifactWrapper
-from .api_wrapper import JiraAnalyseWrapper
-
-from ...utils import check_schema
-
-name = "Analyse_Jira"
-
-class AnalyseJira(BaseToolkit):
-    tools: List[BaseTool] = []
-    toolkit_max_length: int = 0
-
-    @staticmethod
-    def toolkit_config_schema() -> type[BaseModel]:
-        selected_tools = {x['name']: x['args_schema'].schema() for x in
-                          JiraAnalyseWrapper.model_construct().get_available_tools()}
-        AnalyseJira.toolkit_max_length = get_max_toolkit_length(selected_tools)
-        return create_model(
-            "analyse_jira",
-            jira_base_url=(str, Field(
-                description="Jira URL",
-                json_schema_extra={
-                    'toolkit_name': True,
-                    'max_toolkit_length': AnalyseJira.toolkit_max_length                   
-                })
-            ),
-            jira_cloud=(bool, Field(description="Hosting Option")),
-            jira_username=(str, Field(description="Jira Username")),
-            jira_api_key=(Optional[str], Field(description="API key", json_schema_extra={'secret': True}, default="")),
-            jira_token=(Optional[str], Field(description="Jira token", json_schema_extra={'secret': True}, default="")),
-            # TODO: Add these fields to the schema as custom fields comma-separated if required
-            project_keys=(Optional[str], Field(description="Jira project keys separated by comma", default=None)),
-            team_field=(Optional[str], Field(description="Jira field used as identifier for team", default="")),
-            environment_field=(Optional[str], Field(description="Jira field used as identifier for environment", default="")),
-            defects_name=(Optional[str], Field(description="Jira defects type", default="")),
-            closed_status=(Optional[str], Field(description="Jira closed status", default="")),
-            jira_verify_ssl=(bool, Field(description="Verify SSL")),
-            jira_custom_fields=(Optional[dict], Field(description="Additional fields, split by comma", default={})),
-            artifact_bucket_path=(Optional[str], Field(description="Artifact Bucket Path", default="")),
-            selected_tools=(List[Literal[tuple(selected_tools)]],
-                           Field(default=[], json_schema_extra={'args_schemas': selected_tools})),
-            __config__=ConfigDict(json_schema_extra={'metadata':
-                {
-                    "label": "Analyse_Jira",
-                    "icon_url": "jira-icon.svg",
-                    "hidden": False,
-                    "sections": {
-                        "auth": {
-                            "required": True,
-                            "subsections": [
-                                {
-                                    "name": "Api key",
-                                    "fields": ["jira_api_key"]
-                                },
-                                {
-                                    "name": "Token",
-                                    "fields": ["jira_token"]
-                                }
-                            ]
-                        }
-                    }
-                }
-            })
-        )
-
-    @classmethod
-    def get_toolkit(cls, client: "AlitaClient", selected_tools: list[str], **kwargs):
-        if selected_tools is None:
-            selected_tools = []
-
-        bucket_path = kwargs.get('artifact_bucket_path') or 'analyse-jira'
-        artifact_wrapper = ArtifactWrapper(
-            client=client, bucket=bucket_path
-        )
-        check_schema(artifact_wrapper)
-
-        project_keys = kwargs.get('project_keys') or ''
-
-        jira_base_url = kwargs.get('jira_base_url')
-        jira_verify_ssl = kwargs.get('jira_verify_ssl')
-        jira_username = kwargs.get('jira_username')
-        jira_token = kwargs.get('jira_token')
-        jira_api_key = kwargs.get('jira_api_key')
-       
-        jira_custom_fields = kwargs.get('jira_custom_fields', {})
-        jira_custom_fields['team'] = kwargs.get('team_field', '')
-        jira_custom_fields['environment'] = kwargs.get('environment_field', '')
-        closed_status = kwargs.get('closed_status', '')
-        defects_name = kwargs.get('defects_name', '')
-
-        jira_credentials = {
-            "username": jira_username,
-            "base_url": jira_base_url,
-            "token": jira_token,
-            "api_key": jira_api_key,
-            "verify_ssl": jira_verify_ssl
-        }
-
-        jira = connect_to_jira(credentials=jira_credentials)
-        if not jira:
-            raise ValueError(
-                "Failed to connect to Jira. Please check your credentials."
-            )
-
-        api_wrapper = JiraAnalyseWrapper(
-            artifacts_wrapper=artifact_wrapper,
-            jira=jira,
-            project_keys=project_keys,
-            closed_status=closed_status,
-            defects_name=defects_name,
-            custom_fields=jira_custom_fields,
-        )
-
-        tools = []
-        available_tools = api_wrapper.get_available_tools()
-        for tool in available_tools:
-            if selected_tools:
-                if tool["name"] not in selected_tools:
-                    continue
-            tools.append(
-                BaseAction(
-                    api_wrapper=api_wrapper,
-                    name=tool["name"],
-                    description=tool["description"],
-                    args_schema=tool["args_schema"],
-                )
-            )
-
-        return cls(tools=tools)
-
-    def get_tools(self):
-        return self.tools