alita-sdk 0.3.353__tar.gz → 0.3.355__tar.gz

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.353
+Version: 0.3.355
 Summary: SDK for building langchain agents using resources from Alita
 Author-email: Artem Rozumenko <artyom.rozumenko@gmail.com>, Mikalai Biazruchka <mikalai_biazruchka@epam.com>, Roman Mitusov <roman_mitusov@epam.com>, Ivan Krakhmaliuk <lifedj27@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/runtime/langchain/document_loaders/AlitaTableLoader.py

@@ -63,7 +63,7 @@ class AlitaTableLoader(BaseLoader):
                 "source": f'{self.file_path}:{idx+1}',
                 "table_source": self.file_path,
             }
-            if len(docs) == 0:
+            if len(docs) == 0 and not self.raw_content:
                 header_metadata = metadata.copy()
                 header_metadata["header"] = "true"
                 header = "\t".join([str(value) for value in row.keys()])

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/runtime/tools/router.py

@@ -1,4 +1,5 @@
 import logging
+import re
 from typing import Any, Optional, Union, List
 from langchain_core.runnables import RunnableConfig
 from langchain_core.tools import BaseTool
@@ -7,6 +8,10 @@ from ..utils.utils import clean_string
 
 logger = logging.getLogger(__name__)
 
+def clean_node_str(s: str)-> str:
+        cleaned_string = re.sub(r'[^\w\s]', '', s)
+        return cleaned_string
+
 class RouterNode(BaseTool):
     name: str = 'RouterNode'
     description: str = 'A router node that evaluates a condition and routes accordingly.'
@@ -22,7 +27,7 @@ class RouterNode(BaseTool):
         template = EvaluateTemplate(self.condition, input_data)
         result = template.evaluate()
         logger.info(f"RouterNode evaluated condition '{self.condition}' with input {input_data} => {result}")
-        result = clean_string(str(result))
+        result = clean_node_str(str(result))
         if result in self.routes:
             # If the result is one of the routes, return it
             return {"router_output": result}

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/runtime/tools/vectorstore_base.py

@@ -187,12 +187,12 @@ class VectorStoreWrapperBase(BaseToolApiWrapper):
         """
         Clean the vectorstore collection by deleting all indexed data.
         """
-        self._log_data(
+        self._log_tool_event(
             f"Cleaning collection '{self.dataset}'",
             tool_name="_clean_collection"
         )
         self.vector_adapter.clean_collection(self, collection_suffix)
-        self._log_data(
+        self._log_tool_event(
             f"Collection '{self.dataset}' has been cleaned. ",
             tool_name="_clean_collection"
         )
@@ -212,10 +212,10 @@ class VectorStoreWrapperBase(BaseToolApiWrapper):
 
     def _clean_index(self, collection_suffix: str):
         logger.info("Cleaning index before re-indexing all documents.")
-        self._log_data("Cleaning index before re-indexing all documents. Previous index will be removed", tool_name="index_documents")
+        self._log_tool_event("Cleaning index before re-indexing all documents. Previous index will be removed", tool_name="index_documents")
         try:
             self._clean_collection(collection_suffix)
-            self._log_data("Previous index has been removed",
+            self._log_tool_event("Previous index has been removed",
                            tool_name="index_documents")
         except Exception as e:
             logger.warning(f"Failed to clean index: {str(e)}. Continuing with re-indexing.")
@@ -261,7 +261,7 @@ class VectorStoreWrapperBase(BaseToolApiWrapper):
                 if percent >= next_progress_point:
                     msg = f"Indexing progress: {percent}%. Processed {documents_count} of {total_docs} documents."
                     logger.debug(msg)
-                    self._log_data(msg)
+                    self._log_tool_event(msg)
                     next_progress_point += progress_step
             except Exception:
                 from traceback import format_exc
@@ -569,21 +569,6 @@ class VectorStoreWrapperBase(BaseToolApiWrapper):
         ])
         return result.content
 
-    def _log_data(self, message: str, tool_name: str = "index_data"):
-        """Log data and dispatch custom event for indexing progress"""
-
-        try:
-            dispatch_custom_event(
-                name="thinking_step",
-                data={
-                    "message": message,
-                    "tool_name": tool_name,
-                    "toolkit": "vectorstore",
-                },
-            )
-        except Exception as e:
-            logger.warning(f"Failed to dispatch progress event: {str(e)}")
-
     def get_available_tools(self):
         return [
             {

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/tools/ado/repos/repos_wrapper.py

@@ -24,7 +24,8 @@ from msrest.authentication import BasicAuthentication
 from pydantic import Field, PrivateAttr, create_model, model_validator, SecretStr
 
 from ..utils import extract_old_new_pairs, generate_diff, get_content_from_generator
-from ...elitea_base import BaseCodeToolApiWrapper
+from ...code_indexer_toolkit import CodeIndexerToolkit
+from ...utils.available_tools_decorator import extend_with_parent_available_tools
 
 logger = logging.getLogger(__name__)
 
@@ -242,7 +243,7 @@ class ArgsSchema(Enum):
     )
 
 
-class ReposApiWrapper(BaseCodeToolApiWrapper):
+class ReposApiWrapper(CodeIndexerToolkit):
     # TODO use ado_repos_configuration fields
     organization_url: Optional[str]
     project: Optional[str]
@@ -293,7 +294,7 @@ class ReposApiWrapper(BaseCodeToolApiWrapper):
             if not branch_exists(active_branch):
                 raise ToolException(f"The active branch '{active_branch}' does not exist.")
 
-        return values
+        return super().validate_toolkit(values)
 
     def _get_commits(self, file_path: str, branch: str, top: int = None) -> List[GitCommitRef]:
         """
@@ -1174,9 +1175,10 @@ class ReposApiWrapper(BaseCodeToolApiWrapper):
         except Exception as e:
             return ToolException(f"Unable to retrieve commits due to error:\n{str(e)}")
 
+    @extend_with_parent_available_tools
     def get_available_tools(self):
         """Return a list of available tools."""
-        tools = [
+        return [
             {
                 "ref": self.list_branches_in_repo,
                 "name": "list_branches_in_repo",
@@ -1267,8 +1269,4 @@ class ReposApiWrapper(BaseCodeToolApiWrapper):
                 "description": self.get_commits.__doc__,
                 "args_schema": ArgsSchema.GetCommits.value,
             },
-        ]        # Add vector search tools from base class (includes index_data + search tools)
-        vector_search_tools = self._get_vector_search_tools()
-        tools.extend(vector_search_tools)
-
-        return tools
+        ]

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/tools/base_indexer_toolkit.py

@@ -155,24 +155,77 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
         #
         if clean_index:
             self._clean_index(collection_suffix)
-        #
+        # 
         self._log_tool_event(f"Indexing data into collection with suffix '{collection_suffix}'. It can take some time...")
         self._log_tool_event(f"Loading the documents to index...{kwargs}")
         documents = self._base_loader(**kwargs)
+        documents = list(documents) # consume/exhaust generator to count items
+        documents_count = len(documents)
+        documents = (doc for doc in documents)
         self._log_tool_event(f"Base documents were pre-loaded. "
                              f"Search for possible document duplicates and remove them from the indexing list...")
-        documents = self._reduce_duplicates(documents, collection_suffix)
+        # documents = self._reduce_duplicates(documents, collection_suffix)
         self._log_tool_event(f"Duplicates were removed. "
                              f"Processing documents to collect dependencies and prepare them for indexing...")
-        documents = self._extend_data(documents) # update content of not-reduced base document if needed (for sharepoint and similar)
-        documents = self._collect_dependencies(documents) # collect dependencies for base documents
-        self._log_tool_event(f"Documents were processed. "
-                             f"Applying chunking tool '{chunking_tool}' if specified and preparing documents for indexing...")
-        documents = self._apply_loaders_chunkers(documents, chunking_tool, chunking_config)
-        list_documents = list(documents)
-        self._clean_metadata(list_documents)
-        self._log_tool_event(f"Documents are ready for indexing. Total documents to index: {len(list_documents)}")
-        return self._save_index(list_documents, collection_suffix=collection_suffix, progress_step=progress_step)
+        return self._save_index_generator(documents, documents_count, chunking_tool, chunking_config, collection_suffix=collection_suffix, progress_step=progress_step)
+
+    def _save_index_generator(self, base_documents: Generator[Document, None, None], base_total: int, chunking_tool, chunking_config, collection_suffix: Optional[str] = None, progress_step: int = 20):
+        self._log_tool_event(f"Base documents are ready for indexing. {base_total} base documents in total to index.")
+        from ..runtime.langchain.interfaces.llm_processor import add_documents
+        #
+        base_doc_counter = 0
+        total_counter = 0
+        pg_vector_add_docs_chunk = []
+        for base_doc in base_documents:
+            base_doc_counter += 1
+            self._log_tool_event(f"Processing dependent documents for base documents #{base_doc_counter}.")
+
+            # (base_doc for _ in range(1)) - wrap single base_doc to Generator in order to reuse existing code
+            documents = self._extend_data((base_doc for _ in range(1)))  # update content of not-reduced base document if needed (for sharepoint and similar)
+            documents = self._collect_dependencies(documents)  # collect dependencies for base documents
+            self._log_tool_event(f"Dependent documents were processed. "
+                                 f"Applying chunking tool '{chunking_tool}' if specified and preparing documents for indexing...")
+            documents = self._apply_loaders_chunkers(documents, chunking_tool, chunking_config)
+            self._clean_metadata(documents)
+
+            logger.debug(f"Indexing base document #{base_doc_counter}: {base_doc} and all dependent documents: {documents}")
+
+            dependent_docs_counter = 0
+            # 
+            for doc in documents:
+                if not doc.page_content:
+                    # To avoid case when all documents have empty content
+                    # See llm_processor.add_documents which exclude metadata of docs with empty content
+                    continue
+                #
+                if 'id' not in doc.metadata or 'updated_on' not in doc.metadata:
+                    logger.warning(f"Document is missing required metadata field 'id' or 'updated_on': {doc.metadata}")
+                #
+                # if collection_suffix is provided, add it to metadata of each document
+                if collection_suffix:
+                    if not doc.metadata.get('collection'):
+                        doc.metadata['collection'] = collection_suffix
+                    else:
+                        doc.metadata['collection'] += f";{collection_suffix}"
+                #
+                try:
+                    pg_vector_add_docs_chunk.append(doc)
+                    dependent_docs_counter += 1
+                    if len(pg_vector_add_docs_chunk) >= self.max_docs_per_add:
+                        add_documents(vectorstore=self.vectorstore, documents=pg_vector_add_docs_chunk)
+                        self._log_tool_event(f"{len(pg_vector_add_docs_chunk)} documents have been indexed. Continuing...")
+                        pg_vector_add_docs_chunk = []
+                except Exception:
+                    from traceback import format_exc
+                    logger.error(f"Error: {format_exc()}")
+                    return {"status": "error", "message": f"Error: {format_exc()}"}
+            msg = f"Indexed base document #{base_doc_counter} out of {base_total} (with {dependent_docs_counter} dependencies)."
+            logger.debug(msg)
+            self._log_tool_event(msg)
+            total_counter += dependent_docs_counter
+        if pg_vector_add_docs_chunk:
+            add_documents(vectorstore=self.vectorstore, documents=pg_vector_add_docs_chunk)
+        return {"status": "ok", "message": f"successfully indexed {total_counter} documents"}
 
     def _apply_loaders_chunkers(self, documents: Generator[Document, None, None], chunking_tool: str=None, chunking_config=None) -> Generator[Document, None, None]:
         from ..tools.chunkers import __all__ as chunkers
@@ -222,11 +275,12 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
                 dep.metadata[IndexerKeywords.PARENT.value] = document.metadata.get('id', None)
                 yield dep
 
-    def _clean_metadata(self, documents: list[Document]):
+    def _clean_metadata(self, documents: Generator[Document, None, None]):
         for document in documents:
             remove_keys = self._remove_metadata_keys()
             for key in remove_keys:
                 document.metadata.pop(key, None)
+            yield document
 
     def _reduce_duplicates(
             self,
@@ -235,11 +289,11 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
             log_msg: str = "Verification of documents to index started"
     ) -> Generator[Document, None, None]:
         """Generic duplicate reduction logic for documents."""
-        self._log_data(log_msg, tool_name="index_documents")
+        self._log_tool_event(log_msg, tool_name="index_documents")
         indexed_data = self._get_indexed_data(collection_suffix)
         indexed_keys = set(indexed_data.keys())
         if not indexed_keys:
-            self._log_data("Vectorstore is empty, indexing all incoming documents", tool_name="index_documents")
+            self._log_tool_event("Vectorstore is empty, indexing all incoming documents", tool_name="index_documents")
             yield from documents
             return
 
@@ -257,7 +311,7 @@ class BaseIndexerToolkit(VectorStoreWrapperBase):
                 yield document
 
         if docs_to_remove:
-            self._log_data(
+            self._log_tool_event(
                 f"Removing {len(docs_to_remove)} documents from vectorstore that are already indexed with different updated_on.",
                 tool_name="index_documents"
             )

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/tools/bitbucket/api_wrapper.py

@@ -11,7 +11,8 @@ 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
 
 logger = logging.getLogger(__name__)
 
@@ -117,7 +118,7 @@ CommentOnIssueModel = create_model(
 )
 
 
-class BitbucketAPIWrapper(BaseCodeToolApiWrapper):
+class BitbucketAPIWrapper(CodeIndexerToolkit):
     """Wrapper for Bitbucket API."""
 
     _bitbucket: Any = PrivateAttr()
@@ -167,7 +168,7 @@ 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_name: str) -> str:
         """Set the active branch for the bot."""
@@ -399,6 +400,7 @@ class BitbucketAPIWrapper(BaseCodeToolApiWrapper):
         except Exception as e:
             return f"Failed to read file {file_path}: {str(e)}"
 
+    @extend_with_parent_available_tools
     def get_available_tools(self):
         return [
             {
@@ -473,4 +475,4 @@ class BitbucketAPIWrapper(BaseCodeToolApiWrapper):
                 "description": self.add_pull_request_comment.__doc__ or "Add a comment to a pull request in the repository.",
                 "args_schema": AddPullRequestCommentModel,
             }
-        ] + self._get_vector_search_tools()
+        ]

alita_sdk-0.3.355/alita_sdk/tools/code_indexer_toolkit.py

@@ -0,0 +1,156 @@
+import ast
+import fnmatch
+import logging
+from typing import Optional, List, Generator
+
+from langchain_core.documents import Document
+from langchain_core.tools import ToolException
+from pydantic import Field
+
+from alita_sdk.tools.base_indexer_toolkit import BaseIndexerToolkit
+from .chunkers.code.codeparser import parse_code_files_for_db
+
+logger = logging.getLogger(__name__)
+
+
+class CodeIndexerToolkit(BaseIndexerToolkit):
+    def _get_indexed_data(self, collection_suffix: str):
+        if not self.vector_adapter:
+            raise ToolException("Vector adapter is not initialized. "
+                             "Check your configuration: embedding_model and vectorstore_type.")
+        return self.vector_adapter.get_code_indexed_data(self, collection_suffix)
+
+    def key_fn(self, document: Document):
+        return document.metadata.get('id')
+
+    def compare_fn(self, document: Document, idx_data):
+        return (document.metadata.get('commit_hash') and
+            idx_data.get('commit_hashes') and
+            document.metadata.get('commit_hash') in idx_data.get('commit_hashes')
+        )
+
+    def remove_ids_fn(self, idx_data, key: str):
+        return idx_data[key]['ids']
+
+    def _base_loader(
+            self,
+            branch: Optional[str] = None,
+            whitelist: Optional[List[str]] = None,
+            blacklist: Optional[List[str]] = None,
+            **kwargs) -> Generator[Document, None, None]:
+        """Index repository files in the vector store using code parsing."""
+        yield from self.loader(
+            branch=branch,
+            whitelist=whitelist,
+            blacklist=blacklist
+        )
+
+    def _extend_data(self, documents: Generator[Document, None, None]):
+        yield from parse_code_files_for_db(documents)
+
+    def _index_tool_params(self):
+        """Return the parameters for indexing data."""
+        return {
+            "branch": (Optional[str], Field(
+                description="Branch to index files from. Defaults to active branch if None.",
+                default=None)),
+            "whitelist": (Optional[List[str]], Field(
+                description='File extensions or paths to include. Defaults to all files if None. Example: ["*.md", "*.java"]',
+                default=None)),
+            "blacklist": (Optional[List[str]], Field(
+                description='File extensions or paths to exclude. Defaults to no exclusions if None. Example: ["*.md", "*.java"]',
+                default=None)),
+        }
+
+    def loader(self,
+               branch: Optional[str] = None,
+               whitelist: Optional[List[str]] = None,
+               blacklist: Optional[List[str]] = None) -> Generator[Document, None, None]:
+        """
+        Generates file content from a branch, respecting whitelist and blacklist patterns.
+    
+        Parameters:
+        - branch (Optional[str]): Branch for listing files. Defaults to the current branch if None.
+        - whitelist (Optional[List[str]]): File extensions or paths to include. Defaults to all files if None.
+        - blacklist (Optional[List[str]]): File extensions or paths to exclude. Defaults to no exclusions if None.
+    
+        Returns:
+        - generator: Yields content from files matching the whitelist but not the blacklist.
+    
+        Example:
+        # Use 'feature-branch', include '.py' files, exclude 'test_' files
+        file_generator = loader(branch='feature-branch', whitelist=['*.py'], blacklist=['*test_*'])
+    
+        Notes:
+        - Whitelist and blacklist use Unix shell-style wildcards.
+        - Files must match the whitelist and not the blacklist to be included.
+        """
+    
+        _files = self.__handle_get_files("", self.__get_branch(branch))
+        self._log_tool_event(message="Listing files in branch", tool_name="loader")
+        logger.info(f"Files in branch: {_files}")
+    
+        def is_whitelisted(file_path: str) -> bool:
+            if whitelist:
+                return (any(fnmatch.fnmatch(file_path, pattern) for pattern in whitelist)
+                        or any(file_path.endswith(f'.{pattern}') for pattern in whitelist))
+            return True
+    
+        def is_blacklisted(file_path: str) -> bool:
+            if blacklist:
+                return (any(fnmatch.fnmatch(file_path, pattern) for pattern in blacklist)
+                        or any(file_path.endswith(f'.{pattern}') for pattern in blacklist))
+            return False
+    
+        def file_content_generator():
+            self._log_tool_event(message="Reading the files", tool_name="loader")
+            # log the progress of file reading
+            total_files = len(_files)
+            for idx, file in enumerate(_files, 1):
+                if is_whitelisted(file) and not is_blacklisted(file):
+                    # read file ONLY if it matches whitelist and does not match blacklist
+                    try:
+                        file_content = self._read_file(file, self.__get_branch(branch))
+                    except Exception as e:
+                        logger.error(f"Failed to read file {file}: {e}")
+                        file_content = ""
+                    if not file_content:
+                        # empty file, skip
+                        continue
+                    # hash the file content to ensure uniqueness
+                    import hashlib
+                    file_hash = hashlib.sha256(file_content.encode("utf-8")).hexdigest()
+                    yield {"file_name": file,
+                           "file_content": file_content,
+                           "commit_hash": file_hash}
+                if idx % 10 == 0 or idx == total_files:
+                    self._log_tool_event(message=f"{idx} out of {total_files} files have been read", tool_name="loader")
+            self._log_tool_event(message=f"{len(_files)} have been read", tool_name="loader")
+    
+        return file_content_generator()
+
+    def __handle_get_files(self, path: str, branch: str):
+        """
+        Handles the retrieval of files from a specific path and branch.
+        This method should be implemented in subclasses to provide the actual file retrieval logic.
+        """
+        _files = self._get_files(path=path, branch=branch)
+        if isinstance(_files, str):
+            try:
+                # Attempt to convert the string to a list using ast.literal_eval
+                _files = ast.literal_eval(_files)
+                # Ensure that the result is actually a list of strings
+                if not isinstance(_files, list) or not all(isinstance(item, str) for item in _files):
+                    raise ValueError("The evaluated result is not a list of strings")
+            except (SyntaxError, ValueError):
+                # Handle the case where the string cannot be converted to a list
+                raise ValueError("Expected a list of strings, but got a string that cannot be converted")
+
+            # Ensure _files is a list of strings
+        if not isinstance(_files, list) or not all(isinstance(item, str) for item in _files):
+            raise ValueError("Expected a list of strings")
+        return _files
+
+    def __get_branch(self, branch):
+       return (branch or getattr(self, 'active_branch', None)
+               or getattr(self, '_active_branch', None) or getattr(self, 'branch', None))

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/tools/github/api_wrapper.py

@@ -1,9 +1,7 @@
-from typing import Any, Dict, List, Optional, Union, Tuple
 import logging
-import traceback
-import json
-import re
-from pydantic import BaseModel, model_validator, Field, SecretStr
+from typing import Any, Dict, Optional
+
+from pydantic import model_validator, Field, SecretStr
 
 from .github_client import GitHubClient
 from .graphql_client_wrapper import GraphQLClientWrapper
@@ -11,28 +9,17 @@ from .schemas import (
     GitHubAuthConfig,
     GitHubRepoConfig
 )
-
-from ..elitea_base import BaseCodeToolApiWrapper
-
-from langchain_core.callbacks import dispatch_custom_event
+from ..code_indexer_toolkit import CodeIndexerToolkit
+from ..utils.available_tools_decorator import extend_with_parent_available_tools
 
 logger = logging.getLogger(__name__)
 
 # Import prompts for tools
-from .tool_prompts import (
-    UPDATE_FILE_PROMPT,
-    CREATE_ISSUE_PROMPT,
-    UPDATE_ISSUE_PROMPT,
-    CREATE_ISSUE_ON_PROJECT_PROMPT,
-    UPDATE_ISSUE_ON_PROJECT_PROMPT
-)
 
 # Create schema models for the new indexing functionality
-from pydantic import create_model
-from typing import Literal
 
 
-class AlitaGitHubAPIWrapper(BaseCodeToolApiWrapper):
+class AlitaGitHubAPIWrapper(CodeIndexerToolkit):
     """
     Wrapper for GitHub API that integrates both REST and GraphQL functionality.
     """
@@ -117,7 +104,7 @@ class AlitaGitHubAPIWrapper(BaseCodeToolApiWrapper):
         if "llm" not in values:
             values["llm"] = None
 
-        return values
+        return super().validate_toolkit(values)
 
     # Expose GitHub REST client methods directly via property
     @property
@@ -131,7 +118,7 @@ class AlitaGitHubAPIWrapper(BaseCodeToolApiWrapper):
         """Access to GitHub GraphQL client methods"""
         return self.graphql_client_instance
 
-
+    @extend_with_parent_available_tools
     def get_available_tools(self):
         # this is horrible, I need to think on something better
         if not self.github_client_instance:
@@ -142,12 +129,8 @@ class AlitaGitHubAPIWrapper(BaseCodeToolApiWrapper):
             graphql_tools = GraphQLClientWrapper.model_construct().get_available_tools()
         else:
             graphql_tools = self.graphql_client_instance.get_available_tools()
-            
-        # Add vector search tools from base class (includes index_data + search tools)
-        vector_search_tools = self._get_vector_search_tools()
         
-        tools = github_tools + graphql_tools + vector_search_tools
-        return tools
+        return github_tools + graphql_tools
 
     def _get_files(self, path: str = "", branch: str = None):
         """Get list of files from GitHub repository."""

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/tools/gitlab/api_wrapper.py

@@ -1,9 +1,12 @@
 # api_wrapper.py
 from typing import Any, Dict, List, Optional
 import fnmatch
-from ...tools.elitea_base import BaseCodeToolApiWrapper
+
+from ..code_indexer_toolkit import CodeIndexerToolkit
 from pydantic import create_model, Field, model_validator, SecretStr, PrivateAttr
 
+from ..utils.available_tools_decorator import extend_with_parent_available_tools
+
 AppendFileModel = create_model(
     "AppendFileModel",
     file_path=(str, Field(description="The path of the file")),
@@ -97,7 +100,7 @@ GetCommitsModel = create_model(
     author=(Optional[str], Field(description="Author name", default=None)),
 )
 
-class GitLabAPIWrapper(BaseCodeToolApiWrapper):
+class GitLabAPIWrapper(CodeIndexerToolkit):
     url: str
     repository: str
     private_token: SecretStr
@@ -127,7 +130,7 @@ class GitLabAPIWrapper(BaseCodeToolApiWrapper):
         cls._repo_instance = g.projects.get(values.get('repository'))
         cls._git = g
         cls._active_branch = values.get('branch')
-        return values
+        return super().validate_toolkit(values)
 
     def set_active_branch(self, branch_name: str) -> str:
         self._active_branch = branch_name
@@ -417,6 +420,7 @@ class GitLabAPIWrapper(BaseCodeToolApiWrapper):
             for commit in commits
         ]
 
+    @extend_with_parent_available_tools
     def get_available_tools(self):
         return [
             {
@@ -521,4 +525,4 @@ class GitLabAPIWrapper(BaseCodeToolApiWrapper):
                 "description": "Retrieve a list of commits from the repository.",
                 "args_schema": GetCommitsModel,
             }
-        ] + self._get_vector_search_tools()
+        ]

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/tools/jira/api_wrapper.py

@@ -1330,7 +1330,7 @@ class JiraApiWrapper(NonCodeIndexerToolkit):
 
             # Use provided JQL query or default to all issues
             if not jql:
-                jql_query = "ORDER BY updated DESC"  # Default to get all issues ordered by update time
+                jql_query = "created >= \"1970-01-01\" ORDER BY updated DESC"  # Default to get all issues ordered by update time
             else:
                 jql_query = jql
 

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk/tools/utils/content_parser.py

@@ -297,7 +297,9 @@ def sanitize_for_postgres(text: str, replacement: str = "") -> str:
     return text.replace("\x00", replacement)
 
 
-def file_extension_by_chunker(chunker_name: str) -> str:
+def file_extension_by_chunker(chunker_name: str) -> str | None:
+    if not chunker_name:
+        return None
     name = chunker_name.lower()
     if name == "markdown":
         return ".md"

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: alita_sdk
-Version: 0.3.353
+Version: 0.3.355
 Summary: SDK for building langchain agents using resources from Alita
 Author-email: Artem Rozumenko <artyom.rozumenko@gmail.com>, Mikalai Biazruchka <mikalai_biazruchka@epam.com>, Roman Mitusov <roman_mitusov@epam.com>, Ivan Krakhmaliuk <lifedj27@gmail.com>, Artem Dubrovskiy <ad13box@gmail.com>
 License-Expression: Apache-2.0

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/alita_sdk.egg-info/SOURCES.txt

@@ -143,6 +143,7 @@ alita_sdk/runtime/utils/toolkit_utils.py
 alita_sdk/runtime/utils/utils.py
 alita_sdk/tools/__init__.py
 alita_sdk/tools/base_indexer_toolkit.py
+alita_sdk/tools/code_indexer_toolkit.py
 alita_sdk/tools/elitea_base.py
 alita_sdk/tools/non_code_indexer_toolkit.py
 alita_sdk/tools/ado/__init__.py

{alita_sdk-0.3.353 → alita_sdk-0.3.355}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "alita_sdk"
-version = "0.3.353"
+version = "0.3.355"
 description = "SDK for building langchain agents using resources from Alita"
 readme = "README.md"
 requires-python = ">=3.10"