lionagi 0.3.8__py3-none-any.whl → 0.5.0__py3-none-any.whl

lionagi/integrations/bridge/langchain_/langchain_bridge.py

@@ -1,68 +0,0 @@
-class LangchainBridge:
-
-    @staticmethod
-    def to_langchain_document(*args, **kwargs):
-        """
-        Converts a generic data node into a Langchain Document.
-
-        This function transforms a node, typically from another data schema, into a Langchain Document format.
-        It requires the source node to have a `to_dict` method to convert it into a dictionary, then it renames specific keys
-        to match the Langchain Document schema before creating a Langchain Document object.
-
-        Args:
-                datanode (T): The data node to convert. Must have a `to_dict` method.
-                **kwargs: Additional keyword arguments to be passed to the Langchain Document constructor.
-
-        Returns:
-                Any: An instance of `LangchainDocument` populated with data from the input node.
-        """
-        from .documents import to_langchain_document
-
-        return to_langchain_document(*args, **kwargs)
-
-    @staticmethod
-    def langchain_loader(*args, **kwargs):
-        """
-        Initializes and uses a specified loader to load data within the Langchain ecosystem.
-
-        This function supports dynamically selecting a loader by name or directly using a loader function.
-        It passes specified arguments and keyword arguments to the loader for data retrieval or processing.
-
-        Args:
-                loader (Union[str, Callable]): A string representing the loader's name or a callable loader function.
-                loader_args (List[Any], optional): A list of positional arguments for the loader.
-                loader_kwargs (Dict[str, Any], optional): A dictionary of keyword arguments for the loader.
-
-        Returns:
-                Any: The result returned by the loader function, typically data loaded into a specified format.
-
-        Raises:
-                ValueError: If the loader cannot be initialized or fails to load data.
-        """
-        from .documents import langchain_loader
-
-        return langchain_loader(*args, **kwargs)
-
-    @staticmethod
-    def langchain_text_splitter(*args, **kwargs):
-        """
-        Splits text or a list of texts using a specified Langchain text splitter.
-
-        This function allows for dynamic selection of a text splitter, either by name or as a function, to split text
-        or documents into chunks. The splitter can be configured with additional arguments and keyword arguments.
-
-        Args:
-                data (Union[str, List]): The text or list of texts to be split.
-                splitter (Union[str, Callable]): The name of the splitter function or the splitter function itself.
-                splitter_args (List[Any], optional): Positional arguments to pass to the splitter function.
-                splitter_kwargs (Dict[str, Any], optional): Keyword arguments to pass to the splitter function.
-
-        Returns:
-                List[str]: A list of text chunks produced by the text splitter.
-
-        Raises:
-                ValueError: If the splitter is invalid or fails during the split operation.
-        """
-        from .documents import langchain_text_splitter
-
-        return langchain_text_splitter(*args, **kwargs)

lionagi/integrations/bridge/llamaindex_/index.py

@@ -1,36 +0,0 @@
-from lionfuncs import check_import
-
-
-class LlamaIndex:
-
-    llama_index = check_import("llama_index", pip_name="llama-index")
-
-    @classmethod
-    def index(
-        cls,
-        nodes,
-        llm_obj=None,
-        llm_class=None,
-        llm_kwargs=None,
-        index_type=None,
-        **kwargs,
-    ):
-        Settings = check_import("llama_index.core", import_name="Settings")
-        OpenAI = check_import("llama_index.llms.openai", import_name="OpenAI")
-
-        if not llm_obj:
-            llm_class = llm_class or OpenAI
-            llm_kwargs = llm_kwargs or {}
-            if "model" not in llm_kwargs:
-                llm_kwargs["model"] = "gpt-4o"
-            llm_obj = llm_class(**llm_kwargs)
-
-        Settings.llm = llm_obj
-
-        if not index_type:
-            VectorStoreIndex = check_import(
-                "llama_index.core", import_name="VectorStoreIndex"
-            )
-            index_type = VectorStoreIndex
-
-        return index_type(nodes, **kwargs)

lionagi/integrations/bridge/llamaindex_/llama_index_bridge.py

@@ -1,108 +0,0 @@
-class LlamaIndexBridge:
-
-    @staticmethod
-    def to_llama_index_node(*args, **kwargs):
-        """
-        Converts a Lion node to a Llama Index node of a specified type.
-
-        This function takes a node from the Lion framework, converts it to a dictionary, modifies keys to match
-        the expected Llama Index node schema, and then creates a Llama Index node object of the specified type.
-
-        Args:
-                lion_node: The Lion node to convert. Must have a `to_dict` method.
-                node_type (Any, optional): The type of Llama Index node to create. Can be a string name of a node class
-                        within the Llama Index schema or a class that inherits from `BaseNode`. Defaults to 'TextNode'.
-                **kwargs: Additional keyword arguments to be included in the Llama Index node's initialization.
-
-        Returns:
-                Any: A new instance of the specified Llama Index node type populated with data from the Lion node.
-
-        Raises:
-                TypeError: If `node_type` is neither a string nor a subclass of `BaseNode`.
-                AttributeError: If an error occurs due to an invalid node type or during the creation of the node object.
-        """
-        from .textnode import to_llama_index_node
-
-        return to_llama_index_node(*args, **kwargs)
-
-    @staticmethod
-    def llama_index_read_data(*args, **kwargs):
-        """
-        Reads data using a specified llama index reader and its arguments.
-
-        This function initializes a llama index reader with the given arguments and keyword arguments,
-        then loads data using the reader's `load_data` method with the provided loader arguments and keyword arguments.
-
-        Args:
-                reader (Union[None, str, Any], optional): The reader to use. This can be a class, a string identifier,
-                        or None. If None, a default reader is used.
-                reader_args (List[Any], optional): Positional arguments to initialize the reader.
-                reader_kwargs (Dict[str, Any], optional): Keyword arguments to initialize the reader.
-                loader_args (List[Any], optional): Positional arguments for the reader's `load_data` method.
-                loader_kwargs (Dict[str, Any], optional): Keyword arguments for the reader's `load_data` method.
-
-        Returns:
-                Any: The documents or data loaded by the reader.
-
-        Raises:
-                ValueError: If there is an error initializing the reader or loading the data.
-        """
-        from .reader import llama_index_read_data
-
-        return llama_index_read_data(*args, **kwargs)
-
-    @staticmethod
-    def llama_index_parse_node(*args, **kwargs):
-        """
-        Parses documents using a specified llama index node parser and its arguments.
-
-        This function initializes a llama index node parser with the given arguments and keyword arguments,
-        then parses documents using the node parser's `get_nodes_from_documents` method.
-
-        Args:
-                documents (Any): The documents to be parsed by the node parser.
-                node_parser (Any): The node parser to use. This can be a class, a string identifier, or None.
-                parser_args (Optional[List[Any]], optional): Positional arguments to initialize the node parser.
-                parser_kwargs (Optional[Dict[str, Any]], optional): Keyword arguments to initialize the node parser.
-
-        Returns:
-                Any: The nodes extracted from the documents by the node parser.
-
-        Raises:
-                ValueError: If there is an error initializing the node parser or parsing the documents.
-        """
-        from .node_parser import llama_index_parse_node
-
-        return llama_index_parse_node(*args, **kwargs)
-
-    @staticmethod
-    def get_llama_index_reader(*args, **kwargs):
-        """
-        Retrieves a llama index reader object based on the specified reader name or class.
-
-        This function checks if the specified reader is a recognized type or name and returns the appropriate
-        llama index reader class. If a string is provided, it attempts to match it with known reader names and import
-        the corresponding reader class dynamically. If a reader class is provided, it validates that the class is a
-        subclass of BasePydanticReader.
-
-        Args:
-          reader (Union[Any, str], optional): The reader identifier, which can be a reader class, a string alias
-                  for a reader class, or None. If None, returns the SimpleDirectoryReader class.
-
-        Returns:
-          Any: The llama index reader class corresponding to the specified reader.
-
-        Raises:
-          TypeError: If the reader is neither a string nor a subclass of BasePydanticReader.
-          ValueError: If the specified reader string does not correspond to a known reader.
-          AttributeError: If there is an issue importing the specified reader.
-        """
-        from .reader import get_llama_index_reader
-
-        return get_llama_index_reader(*args, **kwargs)
-
-    @staticmethod
-    def index(nodes, **kwargs):
-        from .index import LlamaIndex
-
-        return LlamaIndex.index(nodes, **kwargs)

lionagi/integrations/bridge/llamaindex_/llama_pack.py

@@ -1,256 +0,0 @@
-from lionfuncs import check_import
-
-
-class LlamaPack:
-
-    @staticmethod
-    def download(pack_name, pack_path):
-        try:
-            download_llama_pack = check_import(
-                "llama_index.llama_pack", import_name="download_llama_pack"
-            )
-
-            return download_llama_pack(pack_name, pack_path)
-        except Exception as e:
-            raise ImportError(f"Error in downloading llama pack: {e}")
-
-    @staticmethod
-    def build(pack_name, pack_path, args=[], **kwargs):
-        pack = LlamaPack.download(pack_name, pack_path)
-        return pack(*args, **kwargs)
-
-    @staticmethod
-    def stock_market_pack(
-        pack_path="./stock_market_data_pack", args=[], **kwargs
-    ):
-        name_ = "StockMarketDataQueryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def embedded_table_pack(
-        pack_path="./embedded_tables_unstructured_pack", args=[], **kwargs
-    ):
-        name_ = "RecursiveRetrieverSmallToBigPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def rag_evaluator_pack(
-        pack_path="./rag_evaluator_pack", args=[], **kwargs
-    ):
-        name_ = "RagEvaluatorPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def ollma_pack(pack_path="./ollama_pack", args=[], **kwargs):
-        name_ = "OllamaQueryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def llm_compiler_agent_pack(
-        pack_path="./llm_compiler_agent_pack", args=[], **kwargs
-    ):
-        name_ = "LLMCompilerAgentPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def resume_screener_pack(
-        pack_path="./resume_screener_pack", args=[], **kwargs
-    ):
-        name_ = "ResumeScreenerPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def ragatouille_retriever_pack(
-        pack_path="./ragatouille_pack", args=[], **kwargs
-    ):
-        name_ = "RAGatouilleRetrieverPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def chain_of_table_pack(
-        pack_path="./chain_of_table_pack", args=[], **kwargs
-    ):
-        name_ = "ChainOfTablePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def hybrid_fusion_retriever_pack(
-        pack_path="./hybrid_fusion_pack", args=[], **kwargs
-    ):
-        name_ = "HybridFusionRetrieverPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def neo4j_query_engine_pack(pack_path="./neo4j_pack", args=[], **kwargs):
-        name_ = "Neo4jQueryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def llava_completion_pack(pack_path="./llava_pack", args=[], **kwargs):
-        name_ = "LlavaCompletionPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def sentence_window_retriever_pack(
-        pack_path="./sentence_window_retriever_pack", args=[], **kwargs
-    ):
-        name_ = "SentenceWindowRetrieverPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def dense_x_retrieval_pack(pack_path="./dense_pack", args=[], **kwargs):
-        name_ = "DenseXRetrievalPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def zephyr_query_engine_pack(pack_path="./zephyr_pack", args=[], **kwargs):
-        name_ = "ZephyrQueryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def query_rewriting_retriever_pack(
-        pack_path="./query_rewriting_pack", args=[], **kwargs
-    ):
-        name_ = "QueryRewritingRetrieverPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def fuzzy_citation_engine_pack(
-        pack_path="./fuzzy_citation_pack", args=[], **kwargs
-    ):
-        name_ = "FuzzyCitationEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def multidoc_auto_retriever_pack(
-        pack_path="./multidoc_autoretrieval_pack", args=[], **kwargs
-    ):
-        name_ = "MultiDocAutoRetrieverPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def auto_merging_retriever_pack(
-        pack_path="./auto_merging_retriever_pack", args=[], **kwargs
-    ):
-        name_ = "AutoMergingRetrieverPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def voyage_query_engine_pack(pack_path="./voyage_pack", args=[], **kwargs):
-        name_ = "VoyageQueryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def mix_self_consistency_pack(
-        pack_path="./mix_self_consistency_pack", args=[], **kwargs
-    ):
-        name_ = "MixSelfConsistencyPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def rag_fusion_pipeline_pack(
-        pack_path="./rag_fusion_pipeline_pack", args=[], **kwargs
-    ):
-        name_ = "RAGFusionPipelinePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def multi_document_agents_pack(
-        pack_path="./multi_doc_agents_pack", args=[], **kwargs
-    ):
-        name_ = "MultiDocumentAgentsPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def llama_guard_moderator_pack(
-        pack_path="./llamaguard_pack", args=[], **kwargs
-    ):
-        name_ = "LlamaGuardModeratorPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def evaluator_benchmarker_pack(
-        pack_path="./eval_benchmark_pack", args=[], **kwargs
-    ):
-        name_ = "EvaluatorBenchmarkerPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def amazon_product_extraction_pack(
-        pack_path="./amazon_product_extraction_pack", args=[], **kwargs
-    ):
-        name_ = "AmazonProductExtractionPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def llama_dataset_metadata_pack(
-        pack_path="./llama_dataset_metadata_pack", args=[], **kwargs
-    ):
-        name_ = "LlamaDatasetMetadataPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def multi_tenancy_rag_pack(
-        pack_path="./multitenancy_rag_pack", args=[], **kwargs
-    ):
-        name_ = "MultiTenancyRAGPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def gmail_openai_agent_pack(pack_path="./gmail_pack", args=[], **kwargs):
-        name_ = "GmailOpenAIAgentPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def snowflake_query_engine_pack(
-        pack_path="./snowflake_pack", args=[], **kwargs
-    ):
-        name_ = "SnowflakeQueryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def agent_search_retriever_pack(
-        pack_path="./agent_search_pack", args=[], **kwargs
-    ):
-        name_ = "AgentSearchRetrieverPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def vectara_rag_pack(pack_path="./vectara_rag_pack", args=[], **kwargs):
-        name_ = "VectaraRagPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def chroma_autoretrieval_pack(
-        pack_path="./chroma_pack", args=[], **kwargs
-    ):
-        name_ = "ChromaAutoretrievalPack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def arize_phoenix_query_engine_pack(
-        pack_path="./arize_pack", args=[], **kwargs
-    ):
-        name_ = "ArizePhoenixQueryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def redis_ingestion_pipeline_pack(
-        pack_path="./redis_ingestion_pack", args=[], **kwargs
-    ):
-        name_ = "RedisIngestionPipelinePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def nebula_graph_query_engine_pack(
-        pack_path="./nebulagraph_pack", args=[], **kwargs
-    ):
-        name_ = "NebulaGraphQueryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)
-
-    @staticmethod
-    def weaviate_retry_engine_pack(
-        pack_path="./weaviate_pack", args=[], **kwargs
-    ):
-        name_ = "WeaviateRetryEnginePack"
-        return LlamaPack.build(name_, pack_path, args, **kwargs)

lionagi/integrations/bridge/llamaindex_/node_parser.py

@@ -1,92 +0,0 @@
-from typing import Any
-
-from lionfuncs import check_import, import_module
-
-from lionagi.libs.sys_util import SysUtil
-
-
-def get_llama_index_node_parser(node_parser: Any):
-    """
-    Retrieves a llama index node parser object based on the specified node parser name or class.
-
-    This function checks if the specified node parser is a recognized type or name and returns the appropriate
-    llama index node parser object. If a string is provided, it attempts to match it with known node parser names
-    and import the corresponding node parser object dynamically. If a node parser class is provided, it validates
-    that the class is a subclass of NodeParser.
-
-    Args:
-            node_parser (Any): The node parser identifier, which can be a node parser class, a string alias
-                    for a node parser class, or None.
-
-    Returns:
-            Any: The llama index node parser object corresponding to the specified node parser.
-
-    Raises:
-            TypeError: If the node_parser is neither a string nor a subclass of NodeParser.
-            AttributeError: If there is an issue importing the specified node parser due to it not being
-            found within the llama_index.core.node_parser module.
-    """
-
-    NodeParser = check_import(
-        "llama_index.core.node_parser.interface",
-        import_name="NodeParser",
-        pip_name="llama-index",
-    )
-
-    if not isinstance(node_parser, str) and not issubclass(
-        node_parser, NodeParser
-    ):
-        raise TypeError("node_parser must be a string or NodeParser.")
-
-    if isinstance(node_parser, str):
-        if node_parser == "CodeSplitter":
-            SysUtil.check_import("tree_sitter_languages")
-
-        try:
-            node_module = import_module(
-                "llama_index.core", module_name="node_parser"
-            )
-            return getattr(node_module, node_parser)
-        except Exception as e:
-            raise AttributeError(
-                f"llama_index_core has no such attribute:"
-                f" {node_parser}, Error: {e}"
-            ) from e
-
-    elif isinstance(node_parser, NodeParser):
-        return node_parser
-
-
-def llama_index_parse_node(
-    documents, node_parser: Any, parser_args=None, parser_kwargs=None
-):
-    """
-    Parses documents using a specified llama index node parser and its arguments.
-
-    This function initializes a llama index node parser with the given arguments and keyword arguments,
-    then parses documents using the node parser's `get_nodes_from_documents` method.
-
-    Args:
-            documents (Any): The documents to be parsed by the node parser.
-            node_parser (Any): The node parser to use. This can be a class, a string identifier, or None.
-            parser_args (Optional[List[Any]], optional): Positional arguments to initialize the node parser.
-            parser_kwargs (Optional[Dict[str, Any]], optional): Keyword arguments to initialize the node parser.
-
-    Returns:
-            Any: The nodes extracted from the documents by the node parser.
-
-    Raises:
-            ValueError: If there is an error initializing the node parser or parsing the documents.
-    """
-
-    try:
-        parser_args = parser_args or []
-        parser_kwargs = parser_kwargs or {}
-        parser = get_llama_index_node_parser(node_parser)
-        try:
-            parser = parser(*parser_args, **parser_kwargs)
-        except Exception:
-            parser = parser.from_defaults(*parser_args, **parser_kwargs)
-        return parser.get_nodes_from_documents(documents)
-    except Exception as e:
-        raise ValueError(f"Failed to parse. Error: {e}") from e