agno 0.1.2__py3-none-any.whl → 2.3.13__py3-none-any.whl

agno/infra/resources.py

@@ -1,55 +0,0 @@
-from typing import Any, List, Optional, Tuple
-
-from agno.infra.base import InfraBase
-
-
-class InfraResources(InfraBase):
-    """InfraResources is a group of InfraResource and InfraApp objects
-    that are managed together.
-    """
-
-    apps: Optional[List[Any]] = None
-    resources: Optional[List[Any]] = None
-
-    def create_resources(
-        self,
-        group_filter: Optional[str] = None,
-        name_filter: Optional[str] = None,
-        type_filter: Optional[str] = None,
-        dry_run: Optional[bool] = False,
-        auto_confirm: Optional[bool] = False,
-        force: Optional[bool] = None,
-        pull: Optional[bool] = None,
-    ) -> Tuple[int, int]:
-        raise NotImplementedError
-
-    def delete_resources(
-        self,
-        group_filter: Optional[str] = None,
-        name_filter: Optional[str] = None,
-        type_filter: Optional[str] = None,
-        dry_run: Optional[bool] = False,
-        auto_confirm: Optional[bool] = False,
-        force: Optional[bool] = None,
-    ) -> Tuple[int, int]:
-        raise NotImplementedError
-
-    def update_resources(
-        self,
-        group_filter: Optional[str] = None,
-        name_filter: Optional[str] = None,
-        type_filter: Optional[str] = None,
-        dry_run: Optional[bool] = False,
-        auto_confirm: Optional[bool] = False,
-        force: Optional[bool] = None,
-        pull: Optional[bool] = None,
-    ) -> Tuple[int, int]:
-        raise NotImplementedError
-
-    def save_resources(
-        self,
-        group_filter: Optional[str] = None,
-        name_filter: Optional[str] = None,
-        type_filter: Optional[str] = None,
-    ) -> Tuple[int, int]:
-        raise NotImplementedError

agno/knowledge/agent.py

@@ -1,230 +0,0 @@
-from typing import Any, Dict, Iterator, List, Optional
-
-from pydantic import BaseModel, ConfigDict, Field, model_validator
-
-from agno.document import Document
-from agno.document.chunking.fixed import FixedSizeChunking
-from agno.document.chunking.strategy import ChunkingStrategy
-from agno.document.reader.base import Reader
-from agno.utils.log import logger
-from agno.vectordb import VectorDb
-
-
-class AgentKnowledge(BaseModel):
-    """Base class for Agent knowledge"""
-
-    # Reader for reading documents from files, pdfs, urls, etc.
-    reader: Optional[Reader] = None
-    # Vector db for storing knowledge
-    vector_db: Optional[VectorDb] = None
-    # Number of relevant documents to return on search
-    num_documents: int = 5
-    # Number of documents to optimize the vector db on
-    optimize_on: Optional[int] = 1000
-
-    chunking_strategy: ChunkingStrategy = Field(default_factory=FixedSizeChunking)
-
-    model_config = ConfigDict(arbitrary_types_allowed=True)
-
-    @model_validator(mode="after")
-    def update_reader(self) -> "AgentKnowledge":
-        if self.reader is not None:
-            self.reader.chunking_strategy = self.chunking_strategy
-        return self
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterator that yields lists of documents in the knowledge base
-        Each object yielded by the iterator is a list of documents.
-        """
-        raise NotImplementedError
-
-    def search(
-        self, query: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = None
-    ) -> List[Document]:
-        """Returns relevant documents matching a query"""
-        try:
-            if self.vector_db is None:
-                logger.warning("No vector db provided")
-                return []
-
-            _num_documents = num_documents or self.num_documents
-            logger.debug(f"Getting {_num_documents} relevant documents for query: {query}")
-            return self.vector_db.search(query=query, limit=_num_documents, filters=filters)
-        except Exception as e:
-            logger.error(f"Error searching for documents: {e}")
-            return []
-
-    def load(
-        self,
-        recreate: bool = False,
-        upsert: bool = False,
-        skip_existing: bool = True,
-        filters: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        """Load the knowledge base to the vector db
-
-        Args:
-            recreate (bool): If True, recreates the collection in the vector db. Defaults to False.
-            upsert (bool): If True, upserts documents to the vector db. Defaults to False.
-            skip_existing (bool): If True, skips documents which already exist in the vector db when inserting. Defaults to True.
-            filters (Optional[Dict[str, Any]]): Filters to add to each row that can be used to limit results during querying. Defaults to None.
-        """
-
-        if self.vector_db is None:
-            logger.warning("No vector db provided")
-            return
-
-        if recreate:
-            logger.info("Dropping collection")
-            self.vector_db.drop()
-
-        logger.info("Creating collection")
-        self.vector_db.create()
-
-        logger.info("Loading knowledge base")
-        num_documents = 0
-        for document_list in self.document_lists:
-            documents_to_load = document_list
-            # Upsert documents if upsert is True and vector db supports upsert
-            if upsert and self.vector_db.upsert_available():
-                self.vector_db.upsert(documents=documents_to_load, filters=filters)
-            # Insert documents
-            else:
-                # Filter out documents which already exist in the vector db
-                if skip_existing:
-                    # Use set for O(1) lookups
-                    seen_content = set()
-                    documents_to_load = []
-                    for doc in document_list:
-                        if doc.content not in seen_content and not self.vector_db.doc_exists(doc):
-                            seen_content.add(doc.content)
-                            documents_to_load.append(doc)
-                self.vector_db.insert(documents=documents_to_load, filters=filters)
-            num_documents += len(documents_to_load)
-            logger.info(f"Added {len(documents_to_load)} documents to knowledge base")
-
-    def load_documents(
-        self,
-        documents: List[Document],
-        upsert: bool = False,
-        skip_existing: bool = True,
-        filters: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        """Load documents to the knowledge base
-
-        Args:
-            documents (List[Document]): List of documents to load
-            upsert (bool): If True, upserts documents to the vector db. Defaults to False.
-            skip_existing (bool): If True, skips documents which already exist in the vector db when inserting. Defaults to True.
-            filters (Optional[Dict[str, Any]]): Filters to add to each row that can be used to limit results during querying. Defaults to None.
-        """
-
-        logger.info("Loading knowledge base")
-        if self.vector_db is None:
-            logger.warning("No vector db provided")
-            return
-
-        logger.debug("Creating collection")
-        self.vector_db.create()
-
-        # Upsert documents if upsert is True
-        if upsert and self.vector_db.upsert_available():
-            self.vector_db.upsert(documents=documents, filters=filters)
-            logger.info(f"Loaded {len(documents)} documents to knowledge base")
-            return
-
-        # Filter out documents which already exist in the vector db
-        documents_to_load = (
-            [document for document in documents if not self.vector_db.doc_exists(document)]
-            if skip_existing
-            else documents
-        )
-
-        # Insert documents
-        if len(documents_to_load) > 0:
-            self.vector_db.insert(documents=documents_to_load, filters=filters)
-            logger.info(f"Loaded {len(documents_to_load)} documents to knowledge base")
-        else:
-            logger.info("No new documents to load")
-
-    def load_document(
-        self,
-        document: Document,
-        upsert: bool = False,
-        skip_existing: bool = True,
-        filters: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        """Load a document to the knowledge base
-
-        Args:
-            document (Document): Document to load
-            upsert (bool): If True, upserts documents to the vector db. Defaults to False.
-            skip_existing (bool): If True, skips documents which already exist in the vector db. Defaults to True.
-            filters (Optional[Dict[str, Any]]): Filters to add to each row that can be used to limit results during querying. Defaults to None.
-        """
-        self.load_documents(documents=[document], upsert=upsert, skip_existing=skip_existing, filters=filters)
-
-    def load_dict(
-        self,
-        document: Dict[str, Any],
-        upsert: bool = False,
-        skip_existing: bool = True,
-        filters: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        """Load a dictionary representation of a document to the knowledge base
-
-        Args:
-            document (Dict[str, Any]): Dictionary representation of a document
-            upsert (bool): If True, upserts documents to the vector db. Defaults to False.
-            skip_existing (bool): If True, skips documents which already exist in the vector db. Defaults to True.
-            filters (Optional[Dict[str, Any]]): Filters to add to each row that can be used to limit results during querying. Defaults to None.
-        """
-        self.load_documents(
-            documents=[Document.from_dict(document)], upsert=upsert, skip_existing=skip_existing, filters=filters
-        )
-
-    def load_json(
-        self, document: str, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None
-    ) -> None:
-        """Load a json representation of a document to the knowledge base
-
-        Args:
-            document (str): Json representation of a document
-            upsert (bool): If True, upserts documents to the vector db. Defaults to False.
-            skip_existing (bool): If True, skips documents which already exist in the vector db. Defaults to True.
-            filters (Optional[Dict[str, Any]]): Filters to add to each row that can be used to limit results during querying. Defaults to None.
-        """
-        self.load_documents(
-            documents=[Document.from_json(document)], upsert=upsert, skip_existing=skip_existing, filters=filters
-        )
-
-    def load_text(
-        self, text: str, upsert: bool = False, skip_existing: bool = True, filters: Optional[Dict[str, Any]] = None
-    ) -> None:
-        """Load a text to the knowledge base
-
-        Args:
-            text (str): Text to load to the knowledge base
-            upsert (bool): If True, upserts documents to the vector db. Defaults to False.
-            skip_existing (bool): If True, skips documents which already exist in the vector db. Defaults to True.
-            filters (Optional[Dict[str, Any]]): Filters to add to each row that can be used to limit results during querying. Defaults to None.
-        """
-        self.load_documents(
-            documents=[Document(content=text)], upsert=upsert, skip_existing=skip_existing, filters=filters
-        )
-
-    def exists(self) -> bool:
-        """Returns True if the knowledge base exists"""
-        if self.vector_db is None:
-            logger.warning("No vector db provided")
-            return False
-        return self.vector_db.exists()
-
-    def delete(self) -> bool:
-        """Clear the knowledge base"""
-        if self.vector_db is None:
-            logger.warning("No vector db available")
-            return True
-
-        return self.vector_db.delete()

agno/knowledge/arxiv.py

@@ -1,22 +0,0 @@
-from typing import Iterator, List
-
-from agno.document import Document
-from agno.document.reader.arxiv_reader import ArxivReader
-from agno.knowledge.agent import AgentKnowledge
-
-
-class ArxivKnowledgeBase(AgentKnowledge):
-    queries: List[str] = []
-    reader: ArxivReader = ArxivReader()
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterate over urls and yield lists of documents.
-        Each object yielded by the iterator is a list of documents.
-
-        Returns:
-            Iterator[List[Document]]: Iterator yielding list of documents
-        """
-
-        for _query in self.queries:
-            yield self.reader.read(query=_query)

agno/knowledge/combined.py

@@ -1,22 +0,0 @@
-from typing import Iterator, List
-
-from agno.document import Document
-from agno.knowledge.agent import AgentKnowledge
-from agno.utils.log import logger
-
-
-class CombinedKnowledgeBase(AgentKnowledge):
-    sources: List[AgentKnowledge] = []
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterate over knowledge bases and yield lists of documents.
-        Each object yielded by the iterator is a list of documents.
-
-        Returns:
-            Iterator[List[Document]]: Iterator yielding list of documents
-        """
-
-        for kb in self.sources:
-            logger.debug(f"Loading documents from {kb.__class__.__name__}")
-            yield from kb.document_lists

agno/knowledge/csv.py

@@ -1,28 +0,0 @@
-from pathlib import Path
-from typing import Iterator, List, Union
-
-from agno.document import Document
-from agno.document.reader.csv_reader import CSVReader
-from agno.knowledge.agent import AgentKnowledge
-
-
-class CSVKnowledgeBase(AgentKnowledge):
-    path: Union[str, Path]
-    reader: CSVReader = CSVReader()
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterate over CSVs and yield lists of documents.
-        Each object yielded by the iterator is a list of documents.
-
-        Returns:
-            Iterator[List[Document]]: Iterator yielding list of documents
-        """
-
-        _csv_path: Path = Path(self.path) if isinstance(self.path, str) else self.path
-
-        if _csv_path.exists() and _csv_path.is_dir():
-            for _csv in _csv_path.glob("**/*.csv"):
-                yield self.reader.read(file=_csv)
-        elif _csv_path.exists() and _csv_path.is_file() and _csv_path.suffix == ".csv":
-            yield self.reader.read(file=_csv_path)

agno/knowledge/csv_url.py

@@ -1,19 +0,0 @@
-from typing import Iterator, List
-
-from agno.document import Document
-from agno.document.reader.csv_reader import CSVUrlReader
-from agno.knowledge.agent import AgentKnowledge
-from agno.utils.log import logger
-
-
-class CSVUrlKnowledgeBase(AgentKnowledge):
-    urls: List[str]
-    reader: CSVUrlReader = CSVUrlReader()
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        for url in self.urls:
-            if url.endswith(".csv"):
-                yield self.reader.read(url=url)
-            else:
-                logger.error(f"Unsupported URL: {url}")

agno/knowledge/document.py

@@ -1,20 +0,0 @@
-from typing import Iterator, List
-
-from agno.document import Document
-from agno.knowledge.agent import AgentKnowledge
-
-
-class DocumentKnowledgeBase(AgentKnowledge):
-    documents: List[Document]
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterate over documents and yield lists of documents.
-        Each object yielded by the iterator is a list of documents.
-
-        Returns:
-            Iterator[List[Document]]: Iterator yielding list of documents
-        """
-
-        for _document in self.documents:
-            yield [_document]

agno/knowledge/docx.py

@@ -1,30 +0,0 @@
-from pathlib import Path
-from typing import Iterator, List, Union
-
-from agno.document import Document
-from agno.document.reader.docx_reader import DocxReader
-from agno.knowledge.agent import AgentKnowledge
-
-
-class DocxKnowledgeBase(AgentKnowledge):
-    path: Union[str, Path]
-    formats: List[str] = [".doc", ".docx"]
-    reader: DocxReader = DocxReader()
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterate over doc/docx files and yield lists of documents.
-        Each object yielded by the iterator is a list of documents.
-
-        Returns:
-            Iterator[List[Document]]: Iterator yielding list of documents
-        """
-
-        _file_path: Path = Path(self.path) if isinstance(self.path, str) else self.path
-
-        if _file_path.exists() and _file_path.is_dir():
-            for _file in _file_path.glob("**/*"):
-                if _file.suffix in self.formats:
-                    yield self.reader.read(file=_file)
-        elif _file_path.exists() and _file_path.is_file() and _file_path.suffix in self.formats:
-            yield self.reader.read(file=_file_path)

agno/knowledge/json.py

@@ -1,28 +0,0 @@
-from pathlib import Path
-from typing import Iterator, List, Union
-
-from agno.document import Document
-from agno.document.reader.json_reader import JSONReader
-from agno.knowledge.agent import AgentKnowledge
-
-
-class JSONKnowledgeBase(AgentKnowledge):
-    path: Union[str, Path]
-    reader: JSONReader = JSONReader()
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterate over Json files and yield lists of documents.
-        Each object yielded by the iterator is a list of documents.
-
-        Returns:
-            Iterator[List[Document]]: Iterator yielding list of documents
-        """
-
-        _json_path: Path = Path(self.path) if isinstance(self.path, str) else self.path
-
-        if _json_path.exists() and _json_path.is_dir():
-            for _pdf in _json_path.glob("*.json"):
-                yield self.reader.read(path=_pdf)
-        elif _json_path.exists() and _json_path.is_file() and _json_path.suffix == ".json":
-            yield self.reader.read(path=_json_path)

agno/knowledge/langchain.py

@@ -1,71 +0,0 @@
-from typing import Any, Callable, Dict, List, Optional
-
-from agno.document import Document
-from agno.knowledge.agent import AgentKnowledge
-from agno.utils.log import logger
-
-
-class LangChainKnowledgeBase(AgentKnowledge):
-    loader: Optional[Callable] = None
-
-    vectorstore: Optional[Any] = None
-    search_kwargs: Optional[dict] = None
-
-    retriever: Optional[Any] = None
-
-    def search(
-        self, query: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = None
-    ) -> List[Document]:
-        """Returns relevant documents matching the query"""
-
-        try:
-            from langchain_core.documents import Document as LangChainDocument
-            from langchain_core.retrievers import BaseRetriever
-        except ImportError:
-            raise ImportError(
-                "The `langchain` package is not installed. Please install it via `pip install langchain`."
-            )
-
-        if self.vectorstore is not None and self.retriever is None:
-            logger.debug("Creating retriever")
-            if self.search_kwargs is None:
-                self.search_kwargs = {"k": self.num_documents}
-            if filters is not None:
-                self.search_kwargs.update(filters)
-            self.retriever = self.vectorstore.as_retriever(search_kwargs=self.search_kwargs)
-
-        if self.retriever is None:
-            logger.error("No retriever provided")
-            return []
-
-        if not isinstance(self.retriever, BaseRetriever):
-            raise ValueError(f"Retriever is not of type BaseRetriever: {self.retriever}")
-
-        _num_documents = num_documents or self.num_documents
-        logger.debug(f"Getting {_num_documents} relevant documents for query: {query}")
-        lc_documents: List[LangChainDocument] = self.retriever.invoke(input=query)
-        documents = []
-        for lc_doc in lc_documents:
-            documents.append(
-                Document(
-                    content=lc_doc.page_content,
-                    meta_data=lc_doc.metadata,
-                )
-            )
-        return documents
-
-    def load(
-        self,
-        recreate: bool = False,
-        upsert: bool = True,
-        skip_existing: bool = True,
-        filters: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        if self.loader is None:
-            logger.error("No loader provided for LangChainKnowledgeBase")
-            return
-        self.loader()
-
-    def exists(self) -> bool:
-        logger.warning("LangChainKnowledgeBase.exists() not supported - please check the vectorstore manually.")
-        return True

agno/knowledge/llamaindex.py

@@ -1,66 +0,0 @@
-from typing import Any, Callable, Dict, List, Optional
-
-from agno.document import Document
-from agno.knowledge.agent import AgentKnowledge
-from agno.utils.log import logger
-
-try:
-    from llama_index.core.retrievers import BaseRetriever
-    from llama_index.core.schema import NodeWithScore
-except ImportError:
-    raise ImportError(
-        "The `llama-index-core` package is not installed. Please install it via `pip install llama-index-core`."
-    )
-
-
-class LlamaIndexKnowledgeBase(AgentKnowledge):
-    retriever: BaseRetriever
-    loader: Optional[Callable] = None
-
-    def search(
-        self, query: str, num_documents: Optional[int] = None, filters: Optional[Dict[str, Any]] = None
-    ) -> List[Document]:
-        """
-        Returns relevant documents matching the query.
-
-        Args:
-            query (str): The query string to search for.
-            num_documents (Optional[int]): The maximum number of documents to return. Defaults to None.
-            filters (Optional[Dict[str, Any]]): Filters to apply to the search. Defaults to None.
-
-        Returns:
-            List[Document]: A list of relevant documents matching the query.
-        Raises:
-            ValueError: If the retriever is not of type BaseRetriever.
-        """
-        if not isinstance(self.retriever, BaseRetriever):
-            raise ValueError(f"Retriever is not of type BaseRetriever: {self.retriever}")
-
-        lc_documents: List[NodeWithScore] = self.retriever.retrieve(query)
-        if num_documents is not None:
-            lc_documents = lc_documents[:num_documents]
-        documents = []
-        for lc_doc in lc_documents:
-            documents.append(
-                Document(
-                    content=lc_doc.text,
-                    meta_data=lc_doc.metadata,
-                )
-            )
-        return documents
-
-    def load(
-        self,
-        recreate: bool = False,
-        upsert: bool = True,
-        skip_existing: bool = True,
-        filters: Optional[Dict[str, Any]] = None,
-    ) -> None:
-        if self.loader is None:
-            logger.error("No loader provided for LlamaIndexKnowledgeBase")
-            return
-        self.loader()
-
-    def exists(self) -> bool:
-        logger.warning("LlamaIndexKnowledgeBase.exists() not supported - please check the vectorstore manually.")
-        return True

agno/knowledge/pdf.py

@@ -1,28 +0,0 @@
-from pathlib import Path
-from typing import Iterator, List, Union
-
-from agno.document import Document
-from agno.document.reader.pdf_reader import PDFImageReader, PDFReader
-from agno.knowledge.agent import AgentKnowledge
-
-
-class PDFKnowledgeBase(AgentKnowledge):
-    path: Union[str, Path]
-    reader: Union[PDFReader, PDFImageReader] = PDFReader()
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterate over PDFs and yield lists of documents.
-        Each object yielded by the iterator is a list of documents.
-
-        Returns:
-            Iterator[List[Document]]: Iterator yielding list of documents
-        """
-
-        _pdf_path: Path = Path(self.path) if isinstance(self.path, str) else self.path
-
-        if _pdf_path.exists() and _pdf_path.is_dir():
-            for _pdf in _pdf_path.glob("**/*.pdf"):
-                yield self.reader.read(pdf=_pdf)
-        elif _pdf_path.exists() and _pdf_path.is_file() and _pdf_path.suffix == ".pdf":
-            yield self.reader.read(pdf=_pdf_path)

agno/knowledge/pdf_url.py

@@ -1,26 +0,0 @@
-from typing import Iterator, List, Union
-
-from agno.document import Document
-from agno.document.reader.pdf_reader import PDFUrlImageReader, PDFUrlReader
-from agno.knowledge.agent import AgentKnowledge
-from agno.utils.log import logger
-
-
-class PDFUrlKnowledgeBase(AgentKnowledge):
-    urls: List[str] = []
-    reader: Union[PDFUrlReader, PDFUrlImageReader] = PDFUrlReader()
-
-    @property
-    def document_lists(self) -> Iterator[List[Document]]:
-        """Iterate over PDF urls and yield lists of documents.
-        Each object yielded by the iterator is a list of documents.
-
-        Returns:
-            Iterator[List[Document]]: Iterator yielding list of documents
-        """
-
-        for url in self.urls:
-            if url.endswith(".pdf"):
-                yield self.reader.read(url=url)
-            else:
-                logger.error(f"Unsupported URL: {url}")