ag2 0.4.1__py3-none-any.whl → 0.5.0__py3-none-any.whl

autogen/agentchat/contrib/text_analyzer_agent.py

@@ -1,76 +0,0 @@
-# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
-#
-# SPDX-License-Identifier: Apache-2.0
-#
-# Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
-# SPDX-License-Identifier: MIT
-from typing import Any, Dict, List, Literal, Optional, Tuple, Union
-
-from autogen.agentchat.agent import Agent
-from autogen.agentchat.assistant_agent import ConversableAgent
-
-system_message = """You are an expert in text analysis.
-The user will give you TEXT to analyze.
-The user will give you analysis INSTRUCTIONS copied twice, at both the beginning and the end.
-You will follow these INSTRUCTIONS in analyzing the TEXT, then give the results of your expert analysis in the format requested."""
-
-
-class TextAnalyzerAgent(ConversableAgent):
-    """(Experimental) Text Analysis agent, a subclass of ConversableAgent designed to analyze text as instructed."""
-
-    def __init__(
-        self,
-        name="analyzer",
-        system_message: Optional[str] = system_message,
-        human_input_mode: Literal["ALWAYS", "NEVER", "TERMINATE"] = "NEVER",
-        llm_config: Optional[Union[Dict, bool]] = None,
-        **kwargs,
-    ):
-        """
-        Args:
-            name (str): name of the agent.
-            system_message (str): system message for the ChatCompletion inference.
-            human_input_mode (str): This agent should NEVER prompt the human for input.
-            llm_config (dict or False): llm inference configuration.
-                Please refer to [OpenAIWrapper.create](/docs/reference/oai/client#create)
-                for available options.
-                To disable llm-based auto reply, set to False.
-            **kwargs (dict): other kwargs in [ConversableAgent](../conversable_agent#__init__).
-        """
-        super().__init__(
-            name=name,
-            system_message=system_message,
-            human_input_mode=human_input_mode,
-            llm_config=llm_config,
-            **kwargs,
-        )
-        self.register_reply(Agent, TextAnalyzerAgent._analyze_in_reply, position=2)
-
-    def _analyze_in_reply(
-        self,
-        messages: Optional[List[Dict]] = None,
-        sender: Optional[Agent] = None,
-        config: Optional[Any] = None,
-    ) -> Tuple[bool, Union[str, Dict, None]]:
-        """Analyzes the given text as instructed, and returns the analysis as a message.
-        Assumes exactly two messages containing the text to analyze and the analysis instructions.
-        See Teachability.analyze for an example of how to use this method."""
-        if self.llm_config is False:
-            raise ValueError("TextAnalyzerAgent requires self.llm_config to be set in its base class.")
-        if messages is None:
-            messages = self._oai_messages[sender]  # In case of a direct call.
-        assert len(messages) == 2
-
-        # Delegate to the analysis method.
-        return True, self.analyze_text(messages[0]["content"], messages[1]["content"])
-
-    def analyze_text(self, text_to_analyze, analysis_instructions):
-        """Analyzes the given text as instructed, and returns the analysis."""
-        # Assemble the message.
-        text_to_analyze = "# TEXT\n" + text_to_analyze + "\n"
-        analysis_instructions = "# INSTRUCTIONS\n" + analysis_instructions + "\n"
-        msg_text = "\n".join(
-            [analysis_instructions, text_to_analyze, analysis_instructions]
-        )  # Repeat the instructions.
-        # Generate and return the analysis string.
-        return self.generate_oai_reply([{"role": "user", "content": msg_text}], None, None)[1]

autogen/agentchat/contrib/tool_retriever.py

@@ -1,120 +0,0 @@
-# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
-#
-# SPDX-License-Identifier: Apache-2.0
-#
-# Portions derived from https://github.com/microsoft/autogen are under the MIT License.
-# SPDX-License-Identifier: MIT
-import importlib.util
-import inspect
-import os
-from textwrap import dedent, indent
-
-import pandas as pd
-from sentence_transformers import SentenceTransformer, util
-
-from autogen import AssistantAgent, UserProxyAgent
-from autogen.coding import LocalCommandLineCodeExecutor
-
-
-class ToolBuilder:
-    TOOL_USING_PROMPT = """# Functions
-    You have access to the following functions. They can be accessed from the module called 'functions' by their function names.
-For example, if there is a function called `foo` you could import it by writing `from functions import foo`
-{functions}
-"""
-
-    def __init__(self, corpus_path, retriever="all-mpnet-base-v2"):
-
-        self.df = pd.read_csv(corpus_path, sep="\t")
-        document_list = self.df["document_content"].tolist()
-
-        self.model = SentenceTransformer(retriever)
-        self.embeddings = self.model.encode(document_list)
-
-    def retrieve(self, query, top_k=3):
-        # Encode the query using the Sentence Transformer model
-        query_embedding = self.model.encode([query])
-
-        hits = util.semantic_search(query_embedding, self.embeddings, top_k=top_k)
-
-        results = []
-        for hit in hits[0]:
-            results.append(self.df.iloc[hit["corpus_id"], 1])
-        return results
-
-    def bind(self, agent: AssistantAgent, functions: str):
-        """Binds the function to the agent so that agent is aware of it."""
-        sys_message = agent.system_message
-        sys_message += self.TOOL_USING_PROMPT.format(functions=functions)
-        agent.update_system_message(sys_message)
-        return
-
-    def bind_user_proxy(self, agent: UserProxyAgent, tool_root: str):
-        """
-        Updates user proxy agent with a executor so that code executor can successfully execute function-related code.
-        Returns an updated user proxy.
-        """
-        # Find all the functions in the tool root
-        functions = find_callables(tool_root)
-
-        code_execution_config = agent._code_execution_config
-        executor = LocalCommandLineCodeExecutor(
-            timeout=code_execution_config.get("timeout", 180),
-            work_dir=code_execution_config.get("work_dir", "coding"),
-            functions=functions,
-        )
-        code_execution_config = {
-            "executor": executor,
-            "last_n_messages": code_execution_config.get("last_n_messages", 1),
-        }
-        updated_user_proxy = UserProxyAgent(
-            name=agent.name,
-            is_termination_msg=agent._is_termination_msg,
-            code_execution_config=code_execution_config,
-            human_input_mode="NEVER",
-            default_auto_reply=agent._default_auto_reply,
-        )
-        return updated_user_proxy
-
-
-def get_full_tool_description(py_file):
-    """
-    Retrieves the function signature for a given Python file.
-    """
-    with open(py_file, "r") as f:
-        code = f.read()
-        exec(code)
-        function_name = os.path.splitext(os.path.basename(py_file))[0]
-        if function_name in locals():
-            func = locals()[function_name]
-            content = f"def {func.__name__}{inspect.signature(func)}:\n"
-            docstring = func.__doc__
-
-            if docstring:
-                docstring = dedent(docstring)
-                docstring = '"""' + docstring + '"""'
-                docstring = indent(docstring, "    ")
-                content += docstring + "\n"
-            return content
-        else:
-            raise ValueError(f"Function {function_name} not found in {py_file}")
-
-
-def find_callables(directory):
-    """
-    Find all callable objects defined in Python files within the specified directory.
-    """
-    callables = []
-    for root, dirs, files in os.walk(directory):
-        for file in files:
-            if file.endswith(".py"):
-                module_name = os.path.splitext(file)[0]
-                module_path = os.path.join(root, file)
-                spec = importlib.util.spec_from_file_location(module_name, module_path)
-                module = importlib.util.module_from_spec(spec)
-                spec.loader.exec_module(module)
-                for name, value in module.__dict__.items():
-                    if callable(value) and name == module_name:
-                        callables.append(value)
-                        break
-    return callables

autogen/agentchat/contrib/vectordb/base.py

@@ -1,243 +0,0 @@
-# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
-#
-# SPDX-License-Identifier: Apache-2.0
-#
-# Portions derived from  https://github.com/microsoft/autogen are under the MIT License.
-# SPDX-License-Identifier: MIT
-from typing import (
-    Any,
-    Callable,
-    List,
-    Mapping,
-    Optional,
-    Protocol,
-    Sequence,
-    Tuple,
-    TypedDict,
-    Union,
-    runtime_checkable,
-)
-
-Metadata = Union[Mapping[str, Any], None]
-Vector = Union[Sequence[float], Sequence[int]]
-ItemID = Union[str, int]  # chromadb doesn't support int ids, VikingDB does
-
-
-class Document(TypedDict):
-    """A Document is a record in the vector database.
-
-    id: ItemID | the unique identifier of the document.
-    content: str | the text content of the chunk.
-    metadata: Metadata, Optional | contains additional information about the document such as source, date, etc.
-    embedding: Vector, Optional | the vector representation of the content.
-    """
-
-    id: ItemID
-    content: str
-    metadata: Optional[Metadata]
-    embedding: Optional[Vector]
-
-
-"""QueryResults is the response from the vector database for a query/queries.
-A query is a list containing one string while queries is a list containing multiple strings.
-The response is a list of query results, each query result is a list of tuples containing the document and the distance.
-"""
-QueryResults = List[List[Tuple[Document, float]]]
-
-
-@runtime_checkable
-class VectorDB(Protocol):
-    """
-    Abstract class for vector database. A vector database is responsible for storing and retrieving documents.
-
-    Attributes:
-        active_collection: Any | The active collection in the vector database. Make get_collection faster. Default is None.
-        type: str | The type of the vector database, chroma, pgvector, etc. Default is "".
-
-    Methods:
-        create_collection: Callable[[str, bool, bool], Any] | Create a collection in the vector database.
-        get_collection: Callable[[str], Any] | Get the collection from the vector database.
-        delete_collection: Callable[[str], Any] | Delete the collection from the vector database.
-        insert_docs: Callable[[List[Document], str, bool], None] | Insert documents into the collection of the vector database.
-        update_docs: Callable[[List[Document], str], None] | Update documents in the collection of the vector database.
-        delete_docs: Callable[[List[ItemID], str], None] | Delete documents from the collection of the vector database.
-        retrieve_docs: Callable[[List[str], str, int, float], QueryResults] | Retrieve documents from the collection of the vector database based on the queries.
-        get_docs_by_ids: Callable[[List[ItemID], str], List[Document]] | Retrieve documents from the collection of the vector database based on the ids.
-    """
-
-    active_collection: Any = None
-    type: str = ""
-    embedding_function: Optional[Callable[[List[str]], List[List[float]]]] = (
-        None  # embeddings = embedding_function(sentences)
-    )
-
-    def create_collection(self, collection_name: str, overwrite: bool = False, get_or_create: bool = True) -> Any:
-        """
-        Create a collection in the vector database.
-        Case 1. if the collection does not exist, create the collection.
-        Case 2. the collection exists, if overwrite is True, it will overwrite the collection.
-        Case 3. the collection exists and overwrite is False, if get_or_create is True, it will get the collection,
-            otherwise it raise a ValueError.
-
-        Args:
-            collection_name: str | The name of the collection.
-            overwrite: bool | Whether to overwrite the collection if it exists. Default is False.
-            get_or_create: bool | Whether to get the collection if it exists. Default is True.
-
-        Returns:
-            Any | The collection object.
-        """
-        ...
-
-    def get_collection(self, collection_name: str = None) -> Any:
-        """
-        Get the collection from the vector database.
-
-        Args:
-            collection_name: str | The name of the collection. Default is None. If None, return the
-                current active collection.
-
-        Returns:
-            Any | The collection object.
-        """
-        ...
-
-    def delete_collection(self, collection_name: str) -> Any:
-        """
-        Delete the collection from the vector database.
-
-        Args:
-            collection_name: str | The name of the collection.
-
-        Returns:
-            Any
-        """
-        ...
-
-    def insert_docs(self, docs: List[Document], collection_name: str = None, upsert: bool = False, **kwargs) -> None:
-        """
-        Insert documents into the collection of the vector database.
-
-        Args:
-            docs: List[Document] | A list of documents. Each document is a TypedDict `Document`.
-            collection_name: str | The name of the collection. Default is None.
-            upsert: bool | Whether to update the document if it exists. Default is False.
-            kwargs: Dict | Additional keyword arguments.
-
-        Returns:
-            None
-        """
-        ...
-
-    def update_docs(self, docs: List[Document], collection_name: str = None, **kwargs) -> None:
-        """
-        Update documents in the collection of the vector database.
-
-        Args:
-            docs: List[Document] | A list of documents.
-            collection_name: str | The name of the collection. Default is None.
-            kwargs: Dict | Additional keyword arguments.
-
-        Returns:
-            None
-        """
-        ...
-
-    def delete_docs(self, ids: List[ItemID], collection_name: str = None, **kwargs) -> None:
-        """
-        Delete documents from the collection of the vector database.
-
-        Args:
-            ids: List[ItemID] | A list of document ids. Each id is a typed `ItemID`.
-            collection_name: str | The name of the collection. Default is None.
-            kwargs: Dict | Additional keyword arguments.
-
-        Returns:
-            None
-        """
-        ...
-
-    def retrieve_docs(
-        self,
-        queries: List[str],
-        collection_name: str = None,
-        n_results: int = 10,
-        distance_threshold: float = -1,
-        **kwargs,
-    ) -> QueryResults:
-        """
-        Retrieve documents from the collection of the vector database based on the queries.
-
-        Args:
-            queries: List[str] | A list of queries. Each query is a string.
-            collection_name: str | The name of the collection. Default is None.
-            n_results: int | The number of relevant documents to return. Default is 10.
-            distance_threshold: float | The threshold for the distance score, only distance smaller than it will be
-                returned. Don't filter with it if < 0. Default is -1.
-            kwargs: Dict | Additional keyword arguments.
-
-        Returns:
-            QueryResults | The query results. Each query result is a list of list of tuples containing the document and
-                the distance.
-        """
-        ...
-
-    def get_docs_by_ids(
-        self, ids: List[ItemID] = None, collection_name: str = None, include=None, **kwargs
-    ) -> List[Document]:
-        """
-        Retrieve documents from the collection of the vector database based on the ids.
-
-        Args:
-            ids: List[ItemID] | A list of document ids. If None, will return all the documents. Default is None.
-            collection_name: str | The name of the collection. Default is None.
-            include: List[str] | The fields to include. Default is None.
-                If None, will include ["metadatas", "documents"], ids will always be included. This may differ
-                depending on the implementation.
-            kwargs: dict | Additional keyword arguments.
-
-        Returns:
-            List[Document] | The results.
-        """
-        ...
-
-
-class VectorDBFactory:
-    """
-    Factory class for creating vector databases.
-    """
-
-    PREDEFINED_VECTOR_DB = ["chroma", "pgvector", "mongodb", "qdrant"]
-
-    @staticmethod
-    def create_vector_db(db_type: str, **kwargs) -> VectorDB:
-        """
-        Create a vector database.
-
-        Args:
-            db_type: str | The type of the vector database.
-            kwargs: Dict | The keyword arguments for initializing the vector database.
-
-        Returns:
-            VectorDB | The vector database.
-        """
-        if db_type.lower() in ["chroma", "chromadb"]:
-            from .chromadb import ChromaVectorDB
-
-            return ChromaVectorDB(**kwargs)
-        if db_type.lower() in ["pgvector", "pgvectordb"]:
-            from .pgvectordb import PGVectorDB
-
-            return PGVectorDB(**kwargs)
-        if db_type.lower() in ["mdb", "mongodb", "atlas"]:
-            from .mongodb import MongoDBAtlasVectorDB
-
-            return MongoDBAtlasVectorDB(**kwargs)
-        if db_type.lower() in ["qdrant", "qdrantdb"]:
-            from .qdrant import QdrantVectorDB
-
-            return QdrantVectorDB(**kwargs)
-        else:
-            raise ValueError(
-                f"Unsupported vector database type: {db_type}. Valid types are {VectorDBFactory.PREDEFINED_VECTOR_DB}."
-            )