langroid 0.43.1__py3-none-any.whl → 0.44.0__py3-none-any.whl

langroid/agent/callbacks/chainlit.py

@@ -5,7 +5,16 @@ Callbacks for Chainlit integration.
 import json
 import logging
 import textwrap
-from typing import Any, Callable, Dict, List, Literal, Optional, no_type_check
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Callable,
+    Dict,
+    List,
+    Literal,
+    Optional,
+    no_type_check,
+)
 
 from langroid.exceptions import LangroidImportError
 from langroid.pydantic_v1 import BaseSettings
@@ -18,7 +27,8 @@ except ImportError:
 from chainlit import run_sync
 from chainlit.logger import logger
 
-import langroid as lr
+if TYPE_CHECKING:
+    from langroid import Agent, Task
 import langroid.language_models as lm
 from langroid.language_models import StreamEventType
 from langroid.utils.configuration import settings
@@ -222,11 +232,11 @@ class ChainlitAgentCallbacks:
     last_step: Optional[cl.Step] = None  # used to display sub-steps under this
     curr_step: Optional[cl.Step] = None  # used to update an initiated step
     stream: Optional[cl.Step] = None  # pushed into openai_gpt.py to stream tokens
-    parent_agent: Optional[lr.Agent] = None  # used to get parent id, for step nesting
+    parent_agent: Optional["Agent"] = None  # used to get parent id, for step nesting
 
     def __init__(
         self,
-        agent: lr.Agent,
+        agent: "Agent",
         config: ChainlitCallbackConfig = ChainlitCallbackConfig(),
     ):
         """Add callbacks to the agent, and save the initial message,
@@ -245,7 +255,7 @@ class ChainlitAgentCallbacks:
         agent.callbacks.show_error_message = self.show_error_message
         agent.callbacks.show_start_response = self.show_start_response
         self.config = config
-        self.agent: lr.Agent = agent
+        self.agent: "Agent" = agent
         if self.agent.llm is not None:
             # We don't want to suppress LLM output in async + streaming,
             # since we often use chainlit async callbacks to display LLM output
@@ -271,7 +281,7 @@ class ChainlitAgentCallbacks:
         )
         return last_step.id  # type: ignore
 
-    def set_parent_agent(self, parent: lr.Agent) -> None:
+    def set_parent_agent(self, parent: "Agent") -> None:
         self.parent_agent = parent
 
     def get_last_step(self) -> Optional[cl.Step]:
@@ -559,7 +569,7 @@ class ChainlitTaskCallbacks(ChainlitAgentCallbacks):
 
     def __init__(
         self,
-        task: lr.Task,
+        task: "Task",
         config: ChainlitCallbackConfig = ChainlitCallbackConfig(),
     ):
         """Inject callbacks recursively, ensuring msg is passed to the
@@ -573,7 +583,7 @@ class ChainlitTaskCallbacks(ChainlitAgentCallbacks):
 
     @classmethod
     def _inject_callbacks(
-        cls, task: lr.Task, config: ChainlitCallbackConfig = ChainlitCallbackConfig()
+        cls, task: "Task", config: ChainlitCallbackConfig = ChainlitCallbackConfig()
     ) -> None:
         # recursively apply ChainlitAgentCallbacks to agents of sub-tasks
         for t in task.sub_tasks:
@@ -581,7 +591,7 @@ class ChainlitTaskCallbacks(ChainlitAgentCallbacks):
             # ChainlitTaskCallbacks(t, config=config)
 
     def show_subtask_response(
-        self, task: lr.Task, content: str, is_tool: bool = False
+        self, task: "Task", content: str, is_tool: bool = False
     ) -> None:
         """Show sub-task response as a step, nested at the right level."""
 

langroid/agent/special/doc_chat_agent.py

@@ -14,6 +14,7 @@ pip install "langroid[hf-embeddings]"
 
 """
 
+import importlib
 import logging
 from collections import OrderedDict
 from functools import cache
@@ -82,14 +83,13 @@ about them, or summarize them into coherent answers.
 """
 
 CHUNK_ENRICHMENT_DELIMITER = "\n<##-##-##>\n"
-
-has_sentence_transformers = False
 try:
-    from sentence_transformers import SentenceTransformer  # noqa: F401
-
-    has_sentence_transformers = True
-except ImportError:
-    pass
+    # Check if  module exists in sys.path
+    spec = importlib.util.find_spec("sentence_transformers")
+    has_sentence_transformers = spec is not None
+except Exception as e:
+    logger.warning(f"Error checking sentence_transformers: {e}")
+    has_sentence_transformers = False
 
 
 hf_embed_config = SentenceTransformerEmbeddingsConfig(
@@ -236,6 +236,7 @@ class DocChatAgent(ChatAgent):
         self.chunked_docs: List[Document] = []
         self.chunked_docs_clean: List[Document] = []
         self.response: None | Document = None
+
         if len(config.doc_paths) > 0:
             self.ingest()
 

langroid/parsing/document_parser.py

@@ -16,28 +16,11 @@ from dotenv import load_dotenv
 from langroid.exceptions import LangroidImportError
 from langroid.utils.object_registry import ObjectRegistry
 
-try:
+if TYPE_CHECKING:
+    import docling  # noqa
     import fitz
-except ImportError:
-    if not TYPE_CHECKING:
-        fitz = None
-try:
-    import pymupdf4llm
-except ImportError:
-    if not TYPE_CHECKING:
-        pymupdf4llm = None
-
-try:
-    import docling
-except ImportError:
-    if not TYPE_CHECKING:
-        docling = None
-
-try:
+    import pymupdf4llm  # noqa
     import pypdf
-except ImportError:
-    if not TYPE_CHECKING:
-        pypdf = None
 
 
 import requests
@@ -469,8 +452,10 @@ class FitzPDFParser(DocumentParser):
         Returns:
             Generator[fitz.Page]: Generator yielding each page.
         """
-        if fitz is None:
-            raise LangroidImportError("fitz", "pdf-parsers")
+        try:
+            import fitz
+        except ImportError:
+            LangroidImportError("fitz", "doc-chat")
         doc = fitz.open(stream=self.doc_bytes, filetype="pdf")
         for i, page in enumerate(doc):
             yield i, page
@@ -504,7 +489,10 @@ class PyMuPDF4LLMParser(DocumentParser):
         Returns:
             Generator[fitz.Page]: Generator yielding each page.
         """
-        if fitz is None:
+        try:
+            import pymupdf4llm  # noqa
+            import fitz
+        except ImportError:
             raise LangroidImportError(
                 "pymupdf4llm", ["pymupdf4llm", "all", "pdf-parsers", "doc-chat"]
             )
@@ -548,7 +536,9 @@ class DoclingParser(DocumentParser):
         Returns:
             Generator[docling.Page]: Generator yielding each page.
         """
-        if docling is None:
+        try:
+            import docling  # noqa
+        except ImportError:
             raise LangroidImportError(
                 "docling", ["docling", "pdf-parsers", "all", "doc-chat"]
             )
@@ -637,7 +627,9 @@ class PyPDFParser(DocumentParser):
         Returns:
             Generator[pypdf.pdf.PageObject]: Generator yielding each page.
         """
-        if pypdf is None:
+        try:
+            import pypdf
+        except ImportError:
             raise LangroidImportError("pypdf", "pdf-parsers")
         reader = pypdf.PdfReader(self.doc_bytes)
         for i, page in enumerate(reader.pages):

langroid/parsing/repo_loader.py

@@ -7,14 +7,16 @@ import tempfile
 import time
 from collections import deque
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
 from urllib.parse import urlparse
 
 from dotenv import load_dotenv
-from github import Github
-from github.ContentFile import ContentFile
-from github.Label import Label
-from github.Repository import Repository
+
+if TYPE_CHECKING:
+    from github import Github
+    from github.ContentFile import ContentFile
+    from github.Label import Label
+    from github.Repository import Repository
 
 from langroid.mytypes import DocMetaData, Document
 from langroid.parsing.document_parser import DocumentParser, DocumentType
@@ -24,7 +26,7 @@ from langroid.pydantic_v1 import BaseModel, BaseSettings, Field
 logger = logging.getLogger(__name__)
 
 
-def _get_decoded_content(content_file: ContentFile) -> str:
+def _get_decoded_content(content_file: "ContentFile") -> str:
     if content_file.encoding == "base64":
         return content_file.decoded_content.decode("utf-8") or ""
     elif content_file.encoding == "none":
@@ -54,7 +56,7 @@ class IssueData(BaseModel):
     text: str = Field(..., description="Text of issue, i.e. description body")
 
 
-def get_issue_size(labels: List[Label]) -> str | None:
+def get_issue_size(labels: List["Label"]) -> str | None:
     sizes = ["XS", "S", "M", "L", "XL", "XXL"]
     return next((label.name for label in labels if label.name in sizes), None)
 
@@ -117,6 +119,8 @@ class RepoLoader:
         self.config = config
         self.clone_path: Optional[str] = None
         self.log_file = ".logs/repo_loader/download_log.json"
+        self.repo: Optional["Repository"] = None  # Initialize repo as Optional
+
         os.makedirs(os.path.dirname(self.log_file), exist_ok=True)
         if not os.path.exists(self.log_file):
             with open(self.log_file, "w") as f:
@@ -127,20 +131,25 @@ class RepoLoader:
             logger.info(f"Repo Already downloaded in {log[self.url]}")
             self.clone_path = log[self.url]
 
+        # it's a core dependency, so we don't need to enclose in try/except
+        from github import Github  # Late import
+
+        load_dotenv()
+        # authenticated calls to github api have higher rate limit
+        token = os.getenv("GITHUB_ACCESS_TOKEN")
+
         if "github.com" in self.url:
             repo_name = self.url.split("github.com/")[1]
         else:
             repo_name = self.url
-        load_dotenv()
-        # authenticated calls to github api have higher rate limit
-        token = os.getenv("GITHUB_ACCESS_TOKEN")
+
         g = Github(token)
         self.repo = self._get_repo_with_retry(g, repo_name)
 
     @staticmethod
     def _get_repo_with_retry(
-        g: Github, repo_name: str, max_retries: int = 5
-    ) -> Repository:
+        g: "Github", repo_name: str, max_retries: int = 5
+    ) -> "Repository":
         """
         Get a repo from the GitHub API, retrying if the request fails,
         with exponential backoff.
@@ -173,6 +182,10 @@ class RepoLoader:
 
     def get_issues(self, k: int | None = 100) -> List[IssueData]:
         """Get up to k issues from the GitHub repo."""
+        if self.repo is None:
+            logger.warning("No repo found. Ensure the URL is correct.")
+            return []  # Return an empty list rather than raise an error in this case
+
         if k is None:
             issues = self.repo.get_issues(state="all")
         else:
@@ -224,7 +237,7 @@ class RepoLoader:
         """
         return file_type not in self.config.non_code_types
 
-    def _is_allowed(self, content: ContentFile) -> bool:
+    def _is_allowed(self, content: "ContentFile") -> bool:
         """
         Check if a file or directory content is allowed to be included.
 
@@ -301,6 +314,10 @@ class RepoLoader:
             Dict[str, Union[str, List[Dict]]]:
             A dictionary containing file and directory names, with file contents.
         """
+        if self.repo is None:
+            logger.warning("No repo found. Ensure the URL is correct.")
+            return {}  # Return an empty dict rather than raise an error in this case
+
         root_contents = self.repo.get_contents("")
         if not isinstance(root_contents, list):
             root_contents = [root_contents]
@@ -519,8 +536,7 @@ class RepoLoader:
                 which includes all depths.
             lines (int, optional): Number of lines to read from each file.
                 Defaults to None, which reads all lines.
-            doc_type (str|DocumentType, optional): The type of document to parse.
-
+            doc_type (str|DocumentType | None, optional): The type of document to parse.
         Returns:
             List[Document]: List of Document objects representing files.
 
@@ -584,6 +600,10 @@ class RepoLoader:
             list of Document objects, each has fields `content` and `metadata`,
             and `metadata` has fields `url`, `filename`, `extension`, `language`
         """
+        if self.repo is None:
+            logger.warning("No repo found. Ensure the URL is correct.")
+            return []  # Return an empty list rather than raise an error
+
         contents = self.repo.get_contents("")
         if not isinstance(contents, list):
             contents = [contents]

langroid/parsing/search.py

@@ -10,9 +10,6 @@ import difflib
 import re
 from typing import List, Tuple
 
-from nltk.corpus import stopwords
-from nltk.stem import WordNetLemmatizer
-from nltk.tokenize import RegexpTokenizer
 from rank_bm25 import BM25Okapi
 from thefuzz import fuzz, process
 
@@ -120,6 +117,9 @@ def preprocess_text(text: str) -> str:
     # Ensure the NLTK resources are available
     for resource in ["tokenizers/punkt", "corpora/wordnet", "corpora/stopwords"]:
         download_nltk_resource(resource)
+    from nltk.corpus import stopwords
+    from nltk.stem import WordNetLemmatizer
+    from nltk.tokenize import RegexpTokenizer
 
     # Lowercase the text
     text = text.lower()

langroid/parsing/url_loader.py

@@ -4,12 +4,6 @@ from tempfile import NamedTemporaryFile
 from typing import List, no_type_check
 
 import requests
-import trafilatura
-from trafilatura.downloads import (
-    add_to_compressed_dict,
-    buffered_downloads,
-    load_download_buffer,
-)
 
 from langroid.mytypes import DocMetaData, Document
 from langroid.parsing.document_parser import DocumentParser, ImagePdfParser
@@ -36,6 +30,13 @@ class URLLoader:
 
     @no_type_check
     def load(self) -> List[Document]:
+        import trafilatura
+        from trafilatura.downloads import (
+            add_to_compressed_dict,
+            buffered_downloads,
+            load_download_buffer,
+        )
+
         docs = []
         threads = 4
         # converted the input list to an internal format

langroid/parsing/urls.py

@@ -11,7 +11,6 @@ import requests
 from bs4 import BeautifulSoup
 from rich import print
 from rich.prompt import Prompt
-from trafilatura.spider import focused_crawler
 
 from langroid.pydantic_v1 import BaseModel, HttpUrl, ValidationError, parse_obj_as
 
@@ -150,6 +149,8 @@ def crawl_url(url: str, max_urls: int = 1) -> List[str]:
     up to a maximum of `max_urls`.
     This has not been tested to work as intended. Ignore.
     """
+    from trafilatura.spider import focused_crawler
+
     if max_urls == 1:
         # no need to crawl, just return the original list
         return [url]

langroid/parsing/utils.py

@@ -6,7 +6,6 @@ from functools import cache
 from itertools import islice
 from typing import Iterable, List, Sequence, TypeVar
 
-import nltk
 from faker import Faker
 
 from langroid.mytypes import Document
@@ -22,19 +21,19 @@ random.seed(43)
 logger = logging.getLogger(__name__)
 
 
-# Ensures the NLTK resource is available
-@cache
 def download_nltk_resource(resource: str) -> None:
-    try:
-        nltk.data.find(resource)
-    except LookupError:
-        model = resource.split("/")[-1]
-        nltk.download(model, quiet=True)
+    import nltk
+
+    @cache
+    def _download() -> None:
+        try:
+            nltk.data.find(resource)
+        except LookupError:
+            model = resource.split("/")[-1]
+            nltk.download(model, quiet=True)
 
+    _download()
 
-# Download punkt_tab resource at module import
-download_nltk_resource("tokenizers/punkt_tab")
-download_nltk_resource("corpora/gutenberg")
 
 T = TypeVar("T")
 
@@ -51,9 +50,12 @@ def batched(iterable: Iterable[T], n: int) -> Iterable[Sequence[T]]:
 
 def generate_random_sentences(k: int) -> str:
     # Load the sample text
-
+    import nltk
     from nltk.corpus import gutenberg
 
+    download_nltk_resource("corpora/gutenberg")
+    download_nltk_resource("tokenizers/punkt")
+
     text = gutenberg.raw("austen-emma.txt")
 
     # Split the text into sentences
@@ -155,6 +157,8 @@ def number_segments(s: str, granularity: int = 1) -> str:
         >>> number_segments("Hello world! How are you? Have a good day.")
         '<#1#> Hello world! <#2#> How are you? <#3#> Have a good day.'
     """
+    import nltk
+
     if granularity < 0:
         return "<#1#> " + s
     numbered_text = []

langroid/vector_store/postgres.py

@@ -27,7 +27,6 @@ try:
     )
     from sqlalchemy.dialects.postgresql import JSONB
     from sqlalchemy.engine import Connection, Engine
-    from sqlalchemy.orm import sessionmaker
     from sqlalchemy.sql.expression import insert
 except ImportError:
     Engine = Any  # type: ignore
@@ -56,6 +55,11 @@ class PostgresDB(VectorStore):
         super().__init__(config)
         if not has_postgres:
             raise LangroidImportError("pgvector", "postgres")
+        try:
+            from sqlalchemy.orm import sessionmaker
+        except ImportError:
+            raise LangroidImportError("sqlalchemy", "postgres")
+
         self.config: PostgresDBConfig = config
         self.engine = self._create_engine()
         PostgresDB._create_vector_extension(self.engine)

langroid/vector_store/qdrantdb.py

@@ -4,24 +4,9 @@ import logging
 import os
 import time
 import uuid
-from typing import Dict, List, Optional, Sequence, Tuple, TypeVar
+from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Tuple, TypeVar
 
 from dotenv import load_dotenv
-from qdrant_client import QdrantClient
-from qdrant_client.conversions.common_types import ScoredPoint
-from qdrant_client.http.models import (
-    Batch,
-    CollectionStatus,
-    Distance,
-    Filter,
-    NamedSparseVector,
-    NamedVector,
-    SearchRequest,
-    SparseIndexParams,
-    SparseVector,
-    SparseVectorParams,
-    VectorParams,
-)
 
 from langroid.embedding_models.base import (
     EmbeddingModelsConfig,
@@ -32,6 +17,8 @@ from langroid.utils.configuration import settings
 from langroid.vector_store.base import VectorStore, VectorStoreConfig
 
 logger = logging.getLogger(__name__)
+if TYPE_CHECKING:
+    from qdrant_client.http.models import SparseVector
 
 
 T = TypeVar("T")
@@ -67,16 +54,18 @@ class QdrantDBConfig(VectorStoreConfig):
     collection_name: str | None = "temp"
     storage_path: str = ".qdrant/data"
     embedding: EmbeddingModelsConfig = OpenAIEmbeddingsConfig()
-    distance: str = Distance.COSINE
     use_sparse_embeddings: bool = False
     sparse_embedding_model: str = "naver/splade-v3-distilbert"
     sparse_limit: int = 3
+    distance: str = "cosine"
 
 
 class QdrantDB(VectorStore):
     def __init__(self, config: QdrantDBConfig = QdrantDBConfig()):
         super().__init__(config)
         self.config: QdrantDBConfig = config
+        from qdrant_client import QdrantClient
+
         if self.config.use_sparse_embeddings:
             try:
                 from transformers import AutoModelForMaskedLM, AutoTokenizer
@@ -166,6 +155,7 @@ class QdrantDB(VectorStore):
 
     def clear_all_collections(self, really: bool = False, prefix: str = "") -> int:
         """Clear all collections with the given prefix."""
+
         if not really:
             logger.warning("Not deleting all collections, set really=True to confirm")
             return 0
@@ -200,6 +190,7 @@ class QdrantDB(VectorStore):
         Args:
             empty (bool, optional): Whether to include empty collections.
         """
+
         colls = list(self.client.get_collections())[0][1]
         if empty:
             return [coll.name for coll in colls]
@@ -228,6 +219,14 @@ class QdrantDB(VectorStore):
             replace (bool): Whether to replace an existing collection
                 with the same name. Defaults to False.
         """
+        from qdrant_client.http.models import (
+            CollectionStatus,
+            Distance,
+            SparseIndexParams,
+            SparseVectorParams,
+            VectorParams,
+        )
+
         self.config.collection_name = collection_name
         if self.client.collection_exists(collection_name=collection_name):
             coll = self.client.get_collection(collection_name=collection_name)
@@ -268,7 +267,9 @@ class QdrantDB(VectorStore):
             logger.info(collection_info)
             logger.setLevel(level)
 
-    def get_sparse_embeddings(self, inputs: List[str]) -> List[SparseVector]:
+    def get_sparse_embeddings(self, inputs: List[str]) -> List["SparseVector"]:
+        from qdrant_client.http.models import SparseVector
+
         if not self.config.use_sparse_embeddings:
             return []
         import torch
@@ -295,6 +296,12 @@ class QdrantDB(VectorStore):
         return sparse_embeddings
 
     def add_documents(self, documents: Sequence[Document]) -> None:
+        from qdrant_client.http.models import (
+            Batch,
+            CollectionStatus,
+            SparseVector,
+        )
+
         # Add id to metadata if not already present
         super().maybe_add_ids(documents)
         # Fix the ids due to qdrant finickiness
@@ -383,6 +390,10 @@ class QdrantDB(VectorStore):
         return str(formatted_uuid)
 
     def get_all_documents(self, where: str = "") -> List[Document]:
+        from qdrant_client.http.models import (
+            Filter,
+        )
+
         if self.config.collection_name is None:
             raise ValueError("No collection name set, cannot retrieve docs")
         docs = []
@@ -431,6 +442,14 @@ class QdrantDB(VectorStore):
         where: Optional[str] = None,
         neighbors: int = 0,
     ) -> List[Tuple[Document, float]]:
+        from qdrant_client.conversions.common_types import ScoredPoint
+        from qdrant_client.http.models import (
+            Filter,
+            NamedSparseVector,
+            NamedVector,
+            SearchRequest,
+        )
+
         embedding = self.embedding_fn([text])[0]
         # TODO filter may not work yet
         if where is None or where == "":

langroid/vector_store/weaviatedb.py

@@ -1,7 +1,7 @@
 import logging
 import os
 import re
-from typing import TYPE_CHECKING, Any, List, Optional, Sequence, Tuple
+from typing import Any, List, Optional, Sequence, Tuple
 
 from dotenv import load_dotenv
 
@@ -15,29 +15,16 @@ from langroid.utils.configuration import settings
 from langroid.vector_store.base import VectorStore, VectorStoreConfig
 
 logger = logging.getLogger(__name__)
-has_weaviate: bool = True
-try:
-    import weaviate
-    from weaviate.classes.config import (
-        Configure,
-        VectorDistances,
-    )
-    from weaviate.classes.init import Auth
-    from weaviate.classes.query import Filter, MetadataQuery
-    from weaviate.util import generate_uuid5, get_valid_uuid
-except ImportError:
-    has_weaviate = False
-
-    if not TYPE_CHECKING:
-
-        class VectorDistances:
-            """
-            Fallback class when weaviate is not installed, to avoid import errors.
-            """
 
-            COSINE: str = "cosine"
-            DOTPRODUCT: str = "dot"
-            L2: str = "l2"
+
+class VectorDistances:
+    """
+    Fallback class when weaviate is not installed, to avoid import errors.
+    """
+
+    COSINE: str = "cosine"
+    DOTPRODUCT: str = "dot"
+    L2: str = "l2"
 
 
 class WeaviateDBConfig(VectorStoreConfig):
@@ -54,8 +41,12 @@ class WeaviateDBConfig(VectorStoreConfig):
 class WeaviateDB(VectorStore):
     def __init__(self, config: WeaviateDBConfig = WeaviateDBConfig()):
         super().__init__(config)
-        if not has_weaviate:
+        try:
+            import weaviate
+            from weaviate.classes.init import Auth
+        except ImportError:
             raise LangroidImportError("weaviate", "weaviate")
+
         self.config: WeaviateDBConfig = config
         load_dotenv()
         if self.config.docker:
@@ -141,6 +132,13 @@ class WeaviateDB(VectorStore):
         self.client.collections.delete(name=collection_name)
 
     def create_collection(self, collection_name: str, replace: bool = False) -> None:
+        try:
+            from weaviate.classes.config import (
+                Configure,
+                VectorDistances,
+            )
+        except ImportError:
+            raise LangroidImportError("weaviate", "weaviate")
         collection_name = WeaviateDB.validate_and_format_collection_name(
             collection_name
         )
@@ -207,6 +205,8 @@ class WeaviateDB(VectorStore):
         return [self.weaviate_obj_to_doc(item) for item in coll.iterator()]
 
     def get_documents_by_ids(self, ids: List[str]) -> List[Document]:
+        from weaviate.classes.query import Filter
+
         if self.config.collection_name is None:
             raise ValueError("No collection name set, cannot retrieve docs")
 
@@ -230,6 +230,8 @@ class WeaviateDB(VectorStore):
     def similar_texts_with_scores(
         self, text: str, k: int = 1, where: Optional[str] = None
     ) -> List[Tuple[Document, float]]:
+        from weaviate.classes.query import MetadataQuery
+
         embedding = self.embedding_fn([text])[0]
         if self.config.collection_name is None:
             raise ValueError("No collections name set,cannot search")
@@ -246,6 +248,8 @@ class WeaviateDB(VectorStore):
         return list(zip(docs, similarities))
 
     def _create_valid_uuid_id(self, id: str) -> Any:
+        from weaviate.util import generate_uuid5, get_valid_uuid
+
         try:
             id = get_valid_uuid(id)
             return id
@@ -253,6 +257,8 @@ class WeaviateDB(VectorStore):
             return generate_uuid5(id)
 
     def weaviate_obj_to_doc(self, input_object: Any) -> Document:
+        from weaviate.util import get_valid_uuid
+
         content = input_object.properties.get("content", "")
         metadata_dict = input_object.properties.get("metadata", {})
 

{langroid-0.43.1.dist-info → langroid-0.44.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: langroid
-Version: 0.43.1
+Version: 0.44.0
 Summary: Harness LLMs with Multi-Agent Programming
 Author-email: Prasad Chalasani <pchalasani@gmail.com>
 License: MIT
@@ -237,9 +237,11 @@ This Multi-Agent paradigm is inspired by the
 
 `Langroid` is a fresh take on LLM app-development, where considerable thought has gone 
 into simplifying the developer experience; 
-it does not use `Langchain`, or any other LLM framework.
+it does not use `Langchain`, or any other LLM framework, 
+and works with [practically any LLM](https://langroid.github.io/langroid/tutorials/supported-models/).
 
-:fire: Read the (WIP) [overview of the langroid architecture](https://langroid.github.io/langroid/blog/2024/08/15/overview-of-langroids-multi-agent-architecture-prelim/) and a [quick tour of Langroid](https://langroid.github.io/langroid/tutorials/langroid-tour/)
+:fire: Read the (WIP) [overview of the langroid architecture](https://langroid.github.io/langroid/blog/2024/08/15/overview-of-langroids-multi-agent-architecture-prelim/), 
+ and a [quick tour of Langroid](https://langroid.github.io/langroid/tutorials/langroid-tour/).
 
 📢 Companies are using/adapting Langroid in **production**. Here is a quote:
 
@@ -327,6 +329,18 @@ teacher_task.run()
 <details>
 <summary> <b>Click to expand</b></summary>
 
+- **Feb 2025:**
+  - [0.43.0](https://github.com/langroid/langroid/releases/tag/0.43.0): `GeminiPdfParser` for parsing PDF using 
+    Gemini LLMs - Thanks @abab-dev.
+  - [0.42.0](https://github.com/langroid/langroid/releases/tag/0.42.0): `markitdown` parser for `pptx,xlsx,xls` files 
+    Thanks @abab-dev.
+  - [0.41.0](https://github.com/langroid/langroid/releases/tag/0.41.0): `pinecone` vector-db (Thanks @coretado), 
+    `Tavily` web-search (Thanks @Sozhan308), `Exa` web-search (Thanks @MuddyHope).
+  - [0.40.0](https://github.com/langroid/langroid/releases/tag/0.40.0): `pgvector` vector-db. Thanks @abab-dev.
+  - [0.39.0](https://github.com/langroid/langroid/releases/tag/0.39.0): `ChatAgentConfig.handle_llm_no_tool` for 
+    handling LLM "forgetting" to use a tool.
+  - [0.38.0](https://github.com/langroid/langroid/releases/tag/0.38.0): Gemini embeddings - Thanks @abab-dev)
+  - [0.37.0](https://github.com/langroid/langroid/releases/tag/0.37.0): New PDF Parsers: `docling`, `pymupdf4llm`
 - **Jan 2025:**
   - [0.36.0](https://github.com/langroid/langroid/releases/tag/0.36.0): Weaviate vector-db support (thanks @abab-dev).
   - [0.35.0](https://github.com/langroid/langroid/releases/tag/0.35.0): Capture/Stream reasoning content from 
@@ -591,7 +605,8 @@ section above)
   Agents with specific skills, wrap them in Tasks, and combine tasks in a flexible way.
 - **LLM Support**: Langroid supports OpenAI LLMs as well as LLMs from hundreds of 
 providers ([local/open](https://langroid.github.io/langroid/tutorials/local-llm-setup/) or [remote/commercial](https://langroid.github.io/langroid/tutorials/non-openai-llms/)) via proxy libraries and local model servers
-such as [ollama](https://github.com/ollama), [oobabooga](https://github.com/oobabooga/text-generation-webui), [LiteLLM](https://docs.litellm.ai/docs/providers) that in effect mimic the OpenAI API. 
+such as [ollama](https://github.com/ollama), [oobabooga](https://github.com/oobabooga/text-generation-webui), 
+  [LiteLLM](https://docs.litellm.ai/docs/providers) that in effect mimic the OpenAI API. See the [supported LLMs](https://langroid.github.io/langroid/tutorials/supported-models/). 
 - **Caching of LLM responses:** Langroid supports [Redis](https://redis.com/try-free/) and 
   [Momento](https://www.gomomento.com/) to cache LLM responses.
 - **Vector-stores**: [LanceDB](https://github.com/lancedb/lancedb), [Qdrant](https://qdrant.tech/), [Chroma](https://www.trychroma.com/) are currently supported.

{langroid-0.43.1.dist-info → langroid-0.44.0.dist-info}/RECORD

@@ -12,9 +12,9 @@ langroid/agent/task.py,sha256=HB6N-Jn80HFqCf0ZYOC1v3Bn3oO7NLjShHQJJFwW0q4,90557
 langroid/agent/tool_message.py,sha256=BhjP-_TfQ2tgxuY4Yo_JHLOwwt0mJ4BwjPnREvEY4vk,14744
 langroid/agent/xml_tool_message.py,sha256=6SshYZJKIfi4mkE-gIoSwjkEYekQ8GwcSiCv7a5uO9E,15054
 langroid/agent/callbacks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langroid/agent/callbacks/chainlit.py,sha256=RH8qUXaZE5o2WQz3WJQ1SdFtASGlxWCA6_HYz_3meDQ,20822
+langroid/agent/callbacks/chainlit.py,sha256=UHB6P_J40vsVnssosqkpkOVWRf9NK4TOY0_G2g_Arsg,20900
 langroid/agent/special/__init__.py,sha256=gik_Xtm_zV7U9s30Mn8UX3Gyuy4jTjQe9zjiE3HWmEo,1273
-langroid/agent/special/doc_chat_agent.py,sha256=Q16HOg6MXa26szTO29OOIv1kv8QfuUjxLlLOP3eqZvA,64539
+langroid/agent/special/doc_chat_agent.py,sha256=Pnx_gb-3-QUeUoZfYYzU3l6f3PecpHTiymrB4Tu_wEg,64661
 langroid/agent/special/lance_doc_chat_agent.py,sha256=s8xoRs0gGaFtDYFUSIRchsgDVbS5Q3C2b2mr3V1Fd-Q,10419
 langroid/agent/special/lance_tools.py,sha256=qS8x4wi8mrqfbYV2ztFzrcxyhHQ0ZWOc-zkYiH7awj0,2105
 langroid/agent/special/relevance_extractor_agent.py,sha256=zIx8GUdVo1aGW6ASla0NPQjYYIpmriK_TYMijqAx3F8,4796
@@ -81,19 +81,19 @@ langroid/language_models/prompt_formatter/llama2_formatter.py,sha256=YdcO88qyBeu
 langroid/parsing/__init__.py,sha256=2oUWJJAxIavq9Wtw5RGlkXLq3GF3zgXeVLLW4j7yeb8,1138
 langroid/parsing/agent_chats.py,sha256=sbZRV9ujdM5QXvvuHVjIi2ysYSYlap-uqfMMUKulrW0,1068
 langroid/parsing/code_parser.py,sha256=5ze0MBytrGGkU69pA_bJDjRm6QZz_QYfPcIwkagUa7U,3796
-langroid/parsing/document_parser.py,sha256=tov34uYB_2ecq7-G7P7CWSOv5alcfwkrrwfsnCCVdIk,49714
+langroid/parsing/document_parser.py,sha256=QThgCm9iZyRZd1pmANZ3lO20p2TNH0NIU5_a5v8q8Ck,49649
 langroid/parsing/para_sentence_split.py,sha256=AJBzZojP3zpB-_IMiiHismhqcvkrVBQ3ZINoQyx_bE4,2000
 langroid/parsing/parse_json.py,sha256=aADo38bAHQhC8on4aWZZzVzSDy-dK35vRLZsFI2ewh8,4756
 langroid/parsing/parser.py,sha256=8MDoKQO60RGXod9E5jMj-k90QNhdim4blVJB9L0rrSA,13789
 langroid/parsing/pdf_utils.py,sha256=rmNJ9UzuBgXTAYwj1TtRJcD8h53x7cizhgyYHKO88I4,1513
-langroid/parsing/repo_loader.py,sha256=3GjvPJS6Vf5L6gV2zOU8s-Tf1oq_fZm-IB_RL_7CTsY,29373
+langroid/parsing/repo_loader.py,sha256=NpysuyzRHvgL3F4BB_wGo5sCUnZ3FOlVCJmZ7CaUdbs,30202
 langroid/parsing/routing.py,sha256=-FcnlqldzL4ZoxuDwXjQPNHgBe9F9-F4R6q7b_z9CvI,1232
-langroid/parsing/search.py,sha256=YPCwezM0c4PWbNUMEmQ5RrJBtvX4aWZ1CMCJFs4sqFo,9806
+langroid/parsing/search.py,sha256=0NJ5-Rou_BbrHAD7O9b20bKjZJnbadjObvGm4Zq8Kis,9818
 langroid/parsing/spider.py,sha256=hAVM6wxh1pQ0EN4tI5wMBtAjIk0T-xnpi-ZUzWybhos,3258
 langroid/parsing/table_loader.py,sha256=qNM4obT_0Y4tjrxNBCNUYjKQ9oETCZ7FbolKBTcz-GM,3410
-langroid/parsing/url_loader.py,sha256=MPJFhAdMl4LYVtL9f8r1BOtTkDOg2-hKkANUBUoXCG0,4846
-langroid/parsing/urls.py,sha256=86omykgxo4hg2jyF10Ef-FJa9n6MgXdSXy2mImqgo5c,8076
-langroid/parsing/utils.py,sha256=ZWMS7oG04GUY9EAIwnFN6KKo_ePCKhqk_H8jW6TDT0s,12805
+langroid/parsing/url_loader.py,sha256=obi_kj6ehBkdh5mXNtYCXpm3KCuExoy2D1ODVlFbXbQ,4895
+langroid/parsing/urls.py,sha256=Tjzr64YsCusiYkY0LEGB5-rSuX8T2P_4DVoOFKAeKuI,8081
+langroid/parsing/utils.py,sha256=WwqzOhbQRlorbVvddDIZKv9b1KqZCBDm955lgIHDXRw,12828
 langroid/parsing/web_search.py,sha256=wWSmV0METFTGPhHJIs-M4tog2Aur_75Pxr4a49cKDkU,7042
 langroid/prompts/__init__.py,sha256=RW11vK6jiLPuaUh4GpeFvstti73gkm8_rDMtrbo2YsU,142
 langroid/prompts/dialog.py,sha256=SpfiSyofSgy2pwD1YboHR_yHO3LEEMbv6j2sm874jKo,331
@@ -124,10 +124,10 @@ langroid/vector_store/chromadb.py,sha256=p9mEqJwO2BrL2jSSXfa23kCPlPOwWpF3xJYd5zo
 langroid/vector_store/lancedb.py,sha256=Qd20gKjWozPWfW5-D66J6U8dSrJo1yl-maj6s1lbf1c,14688
 langroid/vector_store/meilisearch.py,sha256=6frB7GFWeWmeKzRfLZIvzRjllniZ1cYj3HmhHQICXLs,11663
 langroid/vector_store/pineconedb.py,sha256=otxXZNaBKb9f_H75HTaU3lMHiaR2NUp5MqwLZXpEY9M,14994
-langroid/vector_store/postgres.py,sha256=DQHd6dt-OcV_QVNm-ymn28rlTfhI6hqgcpLTPCsm0jI,15990
-langroid/vector_store/qdrantdb.py,sha256=v7TAsIoj_vxeKDYS9tpwJLBZA8fuTweTYxHo0X_uawM,17949
-langroid/vector_store/weaviatedb.py,sha256=tjlqEtkwrhykelt-nbr2WIuHWJBuSAGjZuG6gsAMBsc,11753
-langroid-0.43.1.dist-info/METADATA,sha256=AQaUq3J9kszROM1HO3-8s9us3eGpSt9yJy7SI8eznkU,61773
-langroid-0.43.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-langroid-0.43.1.dist-info/licenses/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.43.1.dist-info/RECORD,,
+langroid/vector_store/postgres.py,sha256=wHPtIi2qM4fhO4pMQr95pz1ZCe7dTb2hxl4VYspGZoA,16104
+langroid/vector_store/qdrantdb.py,sha256=O6dSBoDZ0jzfeVBd7LLvsXu083xs2fxXtPa9gGX3JX4,18443
+langroid/vector_store/weaviatedb.py,sha256=Yn8pg139gOy3zkaPfoTbMXEEBCiLiYa1MU5d_3UA1K4,11847
+langroid-0.44.0.dist-info/METADATA,sha256=mKlCCdQQhV31aMCklT9QcRpUs5iHsOeDGAd55axAevU,62973
+langroid-0.44.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+langroid-0.44.0.dist-info/licenses/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.44.0.dist-info/RECORD,,