langroid 0.1.73__py3-none-any.whl → 0.1.77__py3-none-any.whl

langroid/agent/special/doc_chat_agent.py

@@ -81,6 +81,7 @@ class DocChatAgentConfig(ChatAgentConfig):
     # and use the embed(A) to find similar chunks in vecdb.
     # Referred to as HyDE in the paper:
     # https://arxiv.org/pdf/2212.10496.pdf
+    # It is False by default; its benefits depends on the context.
     hypothetical_answer: bool = False
     n_query_rephrases: int = 0
     use_fuzzy_match: bool = True
@@ -391,13 +392,14 @@ class DocChatAgent(ChatAgent):
         if self.config.hypothetical_answer:
             with console.status("[cyan]LLM generating hypothetical answer..."):
                 with StreamingIfAllowed(self.llm, False):
+                    # TODO: provide an easy way to
+                    # Adjust this prompt depending on context.
                     answer = self.llm_response_forget(
                         f"""
-                        Give a sample answer to the following query, 
+                        Give an ideal answer to the following query, 
                         in up to 3 sentences. Do not explain yourself, 
                         and do not apologize, just show 
-                        a possible answer. Guess a hypothetical answer 
-                        even if you do not have any information.
+                        a good possible answer, even if you do not have any information.
                         Preface your answer with "HYPOTHETICAL ANSWER: "
                         
                         QUERY: {query}
@@ -504,7 +506,7 @@ class DocChatAgent(ChatAgent):
 
         with console.status("[cyan]LLM Extracting verbatim passages..."):
             with StreamingIfAllowed(self.llm, False):
-                # these are async calls, one per passage
+                # these are async calls, one per passage; turn off streaming
                 extracts = self.llm.get_verbatim_extracts(query, passages)
                 extracts = [e for e in extracts if e.content != NO_ANSWER]
 

langroid/agent/tools/generator_tool.py

@@ -0,0 +1,25 @@
+"""
+A tool to generate a message from the current pending message.
+The idea is that when an LLM is generating text that is a deterministic transformation
+of known text, then specifying the transformation can be much cheaper than actually
+generating the transformation.
+"""
+
+from langroid.agent.tool_message import ToolMessage
+
+class GeneratorTool(ToolMessage):
+    request: str = "generate"
+    purpose: str = """
+            To generate a message where the parts within curly braces  
+            are derived from previous previous messages in the conversation,
+            using  
+            message are 
+            obtained from a previous message numbered <n>, 
+            using the <rules>.
+            """
+    rules: str
+
+
+    def handle(self) -> str:
+        pass
+

langroid/embedding_models/models.py

@@ -19,7 +19,7 @@ class OpenAIEmbeddingsConfig(EmbeddingModelsConfig):
 class SentenceTransformerEmbeddingsConfig(EmbeddingModelsConfig):
     model_type: str = "sentence-transformer"
     model_name: str = "BAAI/bge-large-en-v1.5"
-    dims: int = 384
+    dims: int = 1024 # should correspond to the model's embedding dims
 
 
 class OpenAIEmbeddings(EmbeddingModel):

langroid/parsing/{pdf_parser.py → document_parser.py}

@@ -1,5 +1,6 @@
 import re
 from abc import abstractmethod
+from enum import Enum
 from io import BytesIO
 from typing import Any, Generator, List, Tuple
 
@@ -12,35 +13,56 @@ from langroid.mytypes import DocMetaData, Document
 from langroid.parsing.parser import Parser, ParsingConfig
 
 
-class PdfParser(Parser):
+class DocumentType(str, Enum):
+    PDF = "pdf"
+    DOCX = "docx"
+
+
+class DocumentParser(Parser):
     """
-    Abstract base class for extracting text from PDFs.
+    Abstract base class for extracting text from special types of docs
+    such as PDFs or Docx.
 
     Attributes:
-        source (str): The PDF source, either a URL or a file path.
-        pdf_bytes (BytesIO): BytesIO object containing the PDF data.
+        source (str): The source, either a URL or a file path.
+        doc_bytes (BytesIO): BytesIO object containing the doc data.
     """
 
     @classmethod
-    def create(cls, source: str, config: ParsingConfig) -> "PdfParser":
+    def create(cls, source: str, config: ParsingConfig) -> "DocumentParser":
         """
-        Create a PDF Parser instance based on config.library specified.
+        Create a DocumentParser instance based on source type
+            and config.<source_type>.library specified.
 
         Args:
             source (str): The source of the PDF, either a URL or a file path.
             config (ParserConfig): The parser configuration.
 
         Returns:
-            PdfParser: An instance of a PDF Parser subclass.
-        """
-        if config.pdf.library == "fitz":
-            return FitzPdfParser(source, config)
-        elif config.pdf.library == "pypdf":
-            return PyPdfParser(source, config)
-        elif config.pdf.library == "pdfplumber":
-            return PdfPlumberParser(source, config)
+            DocumentParser: An instance of a DocumentParser subclass.
+        """
+        if DocumentParser._document_type(source) == DocumentType.PDF:
+            if config.pdf.library == "fitz":
+                return FitzPDFParser(source, config)
+            elif config.pdf.library == "pypdf":
+                return PyPDFParser(source, config)
+            elif config.pdf.library == "pdfplumber":
+                return PDFPlumberParser(source, config)
+            elif config.pdf.library == "unstructured":
+                return UnstructuredPDFParser(source, config)
+            else:
+                raise ValueError(
+                    f"Unsupported PDF library specified: {config.pdf.library}"
+                )
+        elif DocumentParser._document_type(source) == DocumentType.DOCX:
+            if config.docx.library == "unstructured":
+                return UnstructuredDocxParser(source, config)
+            else:
+                raise ValueError(
+                    f"Unsupported DOCX library specified: {config.docx.library}"
+                )
         else:
-            raise ValueError(f"Unsupported library specified: {config.pdf.library}")
+            raise ValueError(f"Unsupported document type: {source}")
 
     def __init__(self, source: str, config: ParsingConfig):
         """
@@ -52,14 +74,32 @@ class PdfParser(Parser):
         super().__init__(config)
         self.source = source
         self.config = config
-        self.pdf_bytes = self._load_pdf_as_bytesio()
+        self.doc_bytes = self._load_doc_as_bytesio()
+
+    @staticmethod
+    def _document_type(source: str) -> DocumentType:
+        """
+        Determine the type of document based on the source.
+
+        Args:
+            source (str): The source of the PDF, either a URL or a file path.
+
+        Returns:
+            str: The document type.
+        """
+        if source.lower().endswith(".pdf"):
+            return DocumentType.PDF
+        elif source.lower().endswith(".docx"):
+            return DocumentType.DOCX
+        else:
+            raise ValueError(f"Unsupported document type: {source}")
 
-    def _load_pdf_as_bytesio(self) -> BytesIO:
+    def _load_doc_as_bytesio(self) -> BytesIO:
         """
-        Load the PDF into a BytesIO object.
+        Load the docs into a BytesIO object.
 
         Returns:
-            BytesIO: A BytesIO object containing the PDF data.
+            BytesIO: A BytesIO object containing the doc data.
         """
         if self.source.startswith(("http://", "https://")):
             response = requests.get(self.source)
@@ -159,7 +199,7 @@ class PdfParser(Parser):
         return docs
 
 
-class FitzPdfParser(PdfParser):
+class FitzPDFParser(DocumentParser):
     """
     Parser for processing PDFs using the `fitz` library.
     """
@@ -171,7 +211,7 @@ class FitzPdfParser(PdfParser):
         Returns:
             Generator[fitz.Page]: Generator yielding each page.
         """
-        doc = fitz.open(stream=self.pdf_bytes, filetype="pdf")
+        doc = fitz.open(stream=self.doc_bytes, filetype="pdf")
         for i, page in enumerate(doc):
             yield i, page
         doc.close()
@@ -189,7 +229,7 @@ class FitzPdfParser(PdfParser):
         return self.fix_text(page.get_text())
 
 
-class PyPdfParser(PdfParser):
+class PyPDFParser(DocumentParser):
     """
     Parser for processing PDFs using the `pypdf` library.
     """
@@ -201,7 +241,7 @@ class PyPdfParser(PdfParser):
         Returns:
             Generator[pypdf.pdf.PageObject]: Generator yielding each page.
         """
-        reader = pypdf.PdfReader(self.pdf_bytes)
+        reader = pypdf.PdfReader(self.doc_bytes)
         for i, page in enumerate(reader.pages):
             yield i, page
 
@@ -218,7 +258,7 @@ class PyPdfParser(PdfParser):
         return self.fix_text(page.extract_text())
 
 
-class PdfPlumberParser(PdfParser):
+class PDFPlumberParser(DocumentParser):
     """
     Parser for processing PDFs using the `pdfplumber` library.
     """
@@ -232,7 +272,7 @@ class PdfPlumberParser(PdfParser):
         Returns:
             Generator[pdfplumber.Page]: Generator yielding each page.
         """
-        with pdfplumber.open(self.pdf_bytes) as pdf:
+        with pdfplumber.open(self.doc_bytes) as pdf:
             for i, page in enumerate(pdf.pages):
                 yield i, page
 
@@ -247,3 +287,60 @@ class PdfPlumberParser(PdfParser):
             str: Extracted text from the page.
         """
         return self.fix_text(page.extract_text())
+
+
+class UnstructuredPDFParser(DocumentParser):
+    """
+    Parser for processing PDF files using the `unstructured` library.
+    """
+
+    def iterate_pages(self) -> Generator[Tuple[int, Any], None, None]:  # type: ignore
+        from unstructured.partition.pdf import partition_pdf
+
+        elements = partition_pdf(file=self.doc_bytes, include_page_breaks=True)
+        for i, el in enumerate(elements):
+            yield i, el
+
+    def extract_text_from_page(self, page: Any) -> str:
+        """
+        Extract text from a given `unstructured` element.
+
+        Args:
+            page (unstructured element): The `unstructured` element object.
+
+        Returns:
+            str: Extracted text from the element.
+        """
+        return self.fix_text(str(page))
+
+
+class UnstructuredDocxParser(DocumentParser):
+    """
+    Parser for processing DOCX files using the `unstructured` library.
+    """
+
+    def iterate_pages(self) -> Generator[Tuple[int, Any], None, None]:  # type: ignore
+        from unstructured.partition.docx import partition_docx
+
+        elements = partition_docx(file=self.doc_bytes)
+        for i, el in enumerate(elements):
+            yield i, el
+
+    def extract_text_from_page(self, page: Any) -> str:
+        """
+        Extract text from a given `unstructured` element.
+
+        Note:
+            The concept of "pages" doesn't actually exist in the .docx file format in
+            the same way it does in formats like .pdf. A .docx file is made up of a
+            series of elements like paragraphs and tables, but the division into
+            pages is done dynamically based on the rendering settings (like the page
+            size, margin size, font size, etc.).
+
+        Args:
+            page (unstructured element): The `unstructured` element object.
+
+        Returns:
+            str: Extracted text from the element.
+        """
+        return self.fix_text(str(page))

langroid/parsing/parser.py

@@ -23,6 +23,10 @@ class PdfParsingConfig(BaseSettings):
     library: str = "pdfplumber"
 
 
+class DocxParsingConfig(BaseSettings):
+    library: str = "unstructured"
+
+
 class ParsingConfig(BaseSettings):
     splitter: str = Splitter.TOKENS
     chunk_size: int = 200  # aim for this many tokens per chunk
@@ -35,6 +39,7 @@ class ParsingConfig(BaseSettings):
     separators: List[str] = ["\n\n", "\n", " ", ""]
     token_encoding_model: str = "text-embedding-ada-002"
     pdf: PdfParsingConfig = PdfParsingConfig()
+    docx: DocxParsingConfig = DocxParsingConfig()
 
 
 class Parser:

langroid/parsing/repo_loader.py

@@ -18,8 +18,8 @@ from github.Repository import Repository
 from pydantic import BaseSettings
 
 from langroid.mytypes import DocMetaData, Document
+from langroid.parsing.document_parser import DocumentParser
 from langroid.parsing.parser import Parser, ParsingConfig
-from langroid.parsing.pdf_parser import PdfParser
 
 logger = logging.getLogger(__name__)
 
@@ -493,12 +493,12 @@ class RepoLoader:
 
         for file_path in file_paths:
             _, file_extension = os.path.splitext(file_path)
-            if file_extension.lower() == ".pdf":
-                pdf_parser = PdfParser.create(
+            if file_extension.lower() in [".pdf", ".docx"]:
+                doc_parser = DocumentParser.create(
                     file_path,
                     parser.config,
                 )
-                docs.extend(pdf_parser.get_doc_chunks())
+                docs.extend(doc_parser.get_doc_chunks())
             else:
                 with open(file_path, "r") as f:
                     if lines is not None:

langroid/parsing/url_loader.py

@@ -9,8 +9,8 @@ from trafilatura.downloads import (
 )
 
 from langroid.mytypes import DocMetaData, Document
+from langroid.parsing.document_parser import DocumentParser
 from langroid.parsing.parser import Parser, ParsingConfig
-from langroid.parsing.pdf_parser import PdfParser
 
 logging.getLogger("trafilatura").setLevel(logging.ERROR)
 
@@ -44,12 +44,12 @@ class URLLoader:
                 sleep_time=5,
             )
             for url, result in buffered_downloads(buffer, threads):
-                if url.lower().endswith(".pdf"):
-                    pdf_parser = PdfParser.create(
+                if url.lower().endswith(".pdf") or url.lower().endswith(".docx"):
+                    doc_parser = DocumentParser.create(
                         url,
                         self.parser.config,
                     )
-                    docs.extend(pdf_parser.get_doc_chunks())
+                    docs.extend(doc_parser.get_doc_chunks())
                 else:
                     text = trafilatura.extract(
                         result,

langroid/vector_store/base.py

@@ -132,4 +132,4 @@ class VectorStore(ABC):
     def show_if_debug(self, doc_score_pairs: List[Tuple[Document, float]]) -> None:
         if settings.debug:
             for i, (d, s) in enumerate(doc_score_pairs):
-                print_long_text("red", "italic red", f"MATCH-{i}", d.content)
+                print_long_text("red", "italic red", f"\nMATCH-{i}\n", d.content)

{langroid-0.1.73.dist-info → langroid-0.1.77.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.73
+Version: 0.1.77
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
@@ -70,6 +70,7 @@ Requires-Dist: trafilatura (>=1.5.0,<2.0.0)
 Requires-Dist: typer (>=0.7.0,<0.8.0)
 Requires-Dist: types-redis (>=4.5.5.2,<5.0.0.0)
 Requires-Dist: types-requests (>=2.31.0.1,<3.0.0.0)
+Requires-Dist: unstructured[docx,pdf,pptx] (>=0.10.16,<0.11.0)
 Requires-Dist: wget (>=3.2,<4.0)
 Description-Content-Type: text/markdown
 
@@ -130,8 +131,8 @@ This Multi-Agent paradigm is inspired by the
 [Actor Framework](https://en.wikipedia.org/wiki/Actor_model)
 (but you do not need to know anything about this!). 
 
-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 `Llama-Index`.
+`Langroid` is a fresh take on LLM app-development, where considerable thought has gone 
+into simplifying the developer experience; it does not use `Langchain`.
 
 We welcome contributions -- See the [contributions](./CONTRIBUTING.md) document
 for ideas on what to contribute.
@@ -142,6 +143,7 @@ for ideas on what to contribute.
 <summary> <b>:fire: Updates/Releases</b></summary>
 
 - **Sep 2023:**
+  - **0.1.76:** DocChatAgent: support for loading `docx` files (preliminary).
   - **0.1.72:** Many improvements to DocChatAgent: better embedding model, 
           hybrid search to improve retrieval, better pdf parsing, re-ranking retrieved results with cross-encoders. 
   - **Use with local LLama Models:** see tutorial [here](https://langroid.github.io/langroid/blog/2023/09/14/using-langroid-with-local-llms/)
@@ -169,7 +171,7 @@ See [this test](tests/main/test_recipient_tool.py) for example usage.
   - **0.1.27**: Added [support](langroid/cachedb/momento_cachedb.py) 
     for [Momento Serverless Cache](https://www.gomomento.com/) as an alternative to Redis.
   - **0.1.24**: [`DocChatAgent`](langroid/agent/special/doc_chat_agent.py) 
-    now [accepts](langroid/parsing/pdf_parser.py) PDF files or URLs.
+    now [accepts](langroid/parsing/document_parser.py) PDF files or URLs.
 
 </details>
 
@@ -233,9 +235,6 @@ Here is what it looks like in action:
 
 # :gear: Installation and Setup
 
-:whale: For a simpler setup, see the Docker section below, which lets you get started just
-by setting up environment variables in a `.env` file.
-
 ### Install `langroid`
 Langroid requires Python 3.11+. We recommend using a virtual environment.
 Use `pip` to install `langroid` (from PyPi) to your virtual environment:
@@ -243,12 +242,11 @@ Use `pip` to install `langroid` (from PyPi) to your virtual environment:
 pip install langroid
 ```
 The core Langroid package lets you use OpenAI Embeddings models via their API. 
-If you instead want to use the `all-MiniLM-L6-v2` embeddings model
-from from HuggingFace, install Langroid like this:
+If you instead want to use the `sentence-transformers` embedding models from HuggingFace, 
+install Langroid like this: 
 ```bash
 pip install langroid[hf-embeddings]
 ```
-Note that this will install `torch` and `sentence-transformers` libraries.
 
 <details>
 <summary><b>Optional Installs for using SQL Chat with a PostgreSQL DB </b></summary>

{langroid-0.1.73.dist-info → langroid-0.1.77.dist-info}/RECORD

@@ -6,7 +6,7 @@ langroid/agent/chat_document.py,sha256=k7Klav3FIBTf2w95bQtxgqBrf2fMo1ydSlklQvv4R
 langroid/agent/helpers.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/agent/junk,sha256=LxfuuW7Cijsg0szAzT81OjWWv1PMNI-6w_-DspVIO2s,339
 langroid/agent/special/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langroid/agent/special/doc_chat_agent.py,sha256=G_xBlGzGlHBieICROiZw7JvBf_bWmuEc5algTFH6pRc,23744
+langroid/agent/special/doc_chat_agent.py,sha256=oBy9K6ScT01AWmdSBvKyhuivjv6ZWD6mYcpxY8kGZQk,23897
 langroid/agent/special/recipient_validator_agent.py,sha256=R3Rit93BNWQar_9stuDBGzmLr2W-IYOQ7oq-tlNNlps,6035
 langroid/agent/special/retriever_agent.py,sha256=c4FKTLnMVuHAIDfdKXSHxhvigYeTEccRWVsO_dHrSNg,7181
 langroid/agent/special/sql/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -20,6 +20,7 @@ langroid/agent/special/table_chat_agent.py,sha256=2nRGW25WDEbR-ukQjeV3mzsC0qk2gO
 langroid/agent/task.py,sha256=UqbjZP4hiG3yRrPWf-nqIyLtK8i0c3fWUEYKbcZ3n50,28275
 langroid/agent/tool_message.py,sha256=8I59BMkqfH_qpWazhv9_rpPjlaG826vVG5dyJGeOn3o,5936
 langroid/agent/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+langroid/agent/tools/generator_tool.py,sha256=LcLlucujJVGORGLHwIT3tsOzVE1wIhgiDLOcXeeylAI,775
 langroid/agent/tools/google_search_tool.py,sha256=64F9oMNdS237BBOitrvYXN4Il_ES_fNrHkh35tBEDfA,1160
 langroid/agent/tools/recipient_tool.py,sha256=-2QWXHhnbTkUsg-jNig6yKt8RnSQ1SLwR6KmBzvYhYk,10217
 langroid/agent_config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -30,7 +31,7 @@ langroid/cachedb/redis_cachedb.py,sha256=xuQ96FAqcHTfK8PEt1tjrh1BkMWUjojFHIgjDfF
 langroid/embedding_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/embedding_models/base.py,sha256=7QD9IlsiKNmDn8TAu92IVmSWHHlpZcMsSUlsQxUMUZE,1161
 langroid/embedding_models/clustering.py,sha256=tZWElUqXl9Etqla0FAa7og96iDKgjqWjucZR_Egtp-A,6684
-langroid/embedding_models/models.py,sha256=MWKXvSA3TbkSz6qL4-y1_2RkjLlECim7GxnEsID26_E,3093
+langroid/embedding_models/models.py,sha256=0YJPWWqMk17R2WcQWRQEI3S51QergDRb-IWhGQVkPF4,3144
 langroid/language_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/language_models/azure_openai.py,sha256=9NLr9s9l7JlCHSuMooxYLLgs1d04IwE_bO7r22bhrg8,3458
 langroid/language_models/base.py,sha256=zHCZIEmIk-sFMq7GWooZe8qq4GjaJ3YRhTzTC4irgGM,19931
@@ -46,14 +47,14 @@ langroid/parsing/agent_chats.py,sha256=sbZRV9ujdM5QXvvuHVjIi2ysYSYlap-uqfMMUKulr
 langroid/parsing/code-parsing.md,sha256=--cyyNiSZSDlIwcjAV4-shKrSiRe2ytF3AdSoS_hD2g,3294
 langroid/parsing/code_parser.py,sha256=BbDAzp35wkYQ9U1dpf1ARL0lVyi0tfqEc6_eox2C090,3727
 langroid/parsing/config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+langroid/parsing/document_parser.py,sha256=w31HvTt8aijusYUk9XN9FpEUo-xc8_-iTK1UGdEM-jg,11212
 langroid/parsing/json.py,sha256=MVqBUfInALQm1QKbcfEvLzWxBz_UztCIyGk7AK5uFPo,1650
 langroid/parsing/para_sentence_split.py,sha256=AJBzZojP3zpB-_IMiiHismhqcvkrVBQ3ZINoQyx_bE4,2000
-langroid/parsing/parser.py,sha256=PxYsZD2nEPhGjL6czR98DABS6sLnJ_AWdvRbIrZk6PQ,7945
-langroid/parsing/pdf_parser.py,sha256=wB5PnNXxhcRssiVUH6nDQ2Fxp0O3VqJcT3vlA7-J38M,7858
-langroid/parsing/repo_loader.py,sha256=lXREULMd6ftmHLeoUMzQlr_QuYkQhfUBQs2-zeC4fhY,27306
+langroid/parsing/parser.py,sha256=99RE4sQg5CHH4xEznuJOE_yl3lIIehkRyGmUdq4hmuo,8070
+langroid/parsing/repo_loader.py,sha256=2OWCNZg6PjoXpIxCusumCb-LIItXPE9ROx53kXdrxAE,27332
 langroid/parsing/search.py,sha256=nyJYyKcXZ5fOtT8vLfveejq4AYAOoloTGappU9HMSpM,4414
 langroid/parsing/table_loader.py,sha256=uqbupGr4y_7os18RtaY5GpD0hWcgzROoNy8dQIHB4kc,1767
-langroid/parsing/url_loader.py,sha256=i2UsVKdcB65AQoDV_sjQAddoRmmvnNh3TG06cEVODn0,2105
+langroid/parsing/url_loader.py,sha256=dhmUTysS_YZyIXVAekxCGPiCbFsOsHXj_eHMow0xoGQ,2153
 langroid/parsing/url_loader_cookies.py,sha256=Lg4sNpRz9MByWq2mde6T0hKv68VZSV3mtMjNEHuFeSU,2327
 langroid/parsing/urls.py,sha256=_Bcf1iRdT7cQrQ8hnbPX0Jtzxc0lVFaucTS5rJoKA14,3709
 langroid/parsing/utils.py,sha256=zqvZWpZktRJTKx_JAqxaIyoudMdKVdB1zzjnOhVYHS4,2196
@@ -80,11 +81,11 @@ langroid/utils/web/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuF
 langroid/utils/web/login.py,sha256=1iz9eUAHa87vpKIkzwkmFa00avwFWivDSAr7QUhK7U0,2528
 langroid/utils/web/selenium_login.py,sha256=mYI6EvVmne34N9RajlsxxRqJQJvV-WG4LGp6sEECHPw,1156
 langroid/vector_store/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langroid/vector_store/base.py,sha256=YNUjdrqJMIDP235bxJPGV7BeXIBO8PdFy2yQubKePsk,4461
+langroid/vector_store/base.py,sha256=mw36zLzdQeG_c1KIWeRmycXnXIzFvqRW2RG7xf6jTGk,4465
 langroid/vector_store/chromadb.py,sha256=2a68iLkgBGoGmuJ80ogJ0rRuoh-Wqdj3rlxVGagMxWk,5384
 langroid/vector_store/qdrant_cloud.py,sha256=3im4Mip0QXLkR6wiqVsjV1QvhSElfxdFSuDKddBDQ-4,188
 langroid/vector_store/qdrantdb.py,sha256=RxLCLaaampLS-Gi-ccYEydUjzI0qUJC9jEvc8g2OXEE,9857
-langroid-0.1.73.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.1.73.dist-info/WHEEL,sha256=vVCvjcmxuUltf8cYhJ0sJMRDLr1XsPuxEId8YDzbyCY,88
-langroid-0.1.73.dist-info/METADATA,sha256=_EuiKeBEewZeP-W5h3yf3matXQ7T82zGxdFBdyv2w44,36171
-langroid-0.1.73.dist-info/RECORD,,
+langroid-0.1.77.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.1.77.dist-info/WHEEL,sha256=vVCvjcmxuUltf8cYhJ0sJMRDLr1XsPuxEId8YDzbyCY,88
+langroid-0.1.77.dist-info/METADATA,sha256=Wh4Sg4QTZjSCK4pU_5S942dJAGZ1ci1dRUQYdxD7rBk,36083
+langroid-0.1.77.dist-info/RECORD,,