langroid 0.1.265__py3-none-any.whl → 0.2.0__py3-none-any.whl

langroid/language_models/mock_lm.py

@@ -0,0 +1,96 @@
+"""Mock Language Model for testing"""
+
+from typing import Dict, List, Optional, Union
+
+import langroid.language_models as lm
+from langroid.language_models import LLMResponse
+from langroid.language_models.base import LanguageModel, LLMConfig
+
+
+class MockLMConfig(LLMConfig):
+    """
+    Mock Language Model Configuration.
+
+    Attributes:
+        response_dict (Dict[str, str]): A "response rule-book", in the form of a
+            dictionary; if last msg in dialog is x,then respond with response_dict[x]
+    """
+
+    response_dict: Dict[str, str] = {}
+    default_response: str = "Mock response"
+    type: str = "mock"
+
+
+class MockLM(LanguageModel):
+
+    def __init__(self, config: MockLMConfig = MockLMConfig()):
+        super().__init__(config)
+        self.config: MockLMConfig = config
+
+    def chat(
+        self,
+        messages: Union[str, List[lm.LLMMessage]],
+        max_tokens: int = 200,
+        functions: Optional[List[lm.LLMFunctionSpec]] = None,
+        function_call: str | Dict[str, str] = "auto",
+    ) -> lm.LLMResponse:
+        """
+        Mock chat function for testing
+        """
+        last_msg = messages[-1].content if isinstance(messages, list) else messages
+        return lm.LLMResponse(
+            message=self.config.response_dict.get(
+                last_msg,
+                self.config.default_response,
+            ),
+            cached=False,
+        )
+
+    async def achat(
+        self,
+        messages: Union[str, List[lm.LLMMessage]],
+        max_tokens: int = 200,
+        functions: Optional[List[lm.LLMFunctionSpec]] = None,
+        function_call: str | Dict[str, str] = "auto",
+    ) -> lm.LLMResponse:
+        """
+        Mock chat function for testing
+        """
+        last_msg = messages[-1].content if isinstance(messages, list) else messages
+        return lm.LLMResponse(
+            message=self.config.response_dict.get(
+                last_msg,
+                self.config.default_response,
+            ),
+            cached=False,
+        )
+
+    def generate(self, prompt: str, max_tokens: int = 200) -> lm.LLMResponse:
+        """
+        Mock generate function for testing
+        """
+        return lm.LLMResponse(
+            message=self.config.response_dict.get(
+                prompt,
+                self.config.default_response,
+            ),
+            cached=False,
+        )
+
+    async def agenerate(self, prompt: str, max_tokens: int = 200) -> LLMResponse:
+        """
+        Mock generate function for testing
+        """
+        return lm.LLMResponse(
+            message=self.config.response_dict.get(
+                prompt,
+                self.config.default_response,
+            ),
+            cached=False,
+        )
+
+    def get_stream(self) -> bool:
+        return False
+
+    def set_stream(self, stream: bool) -> bool:
+        return False

langroid/language_models/utils.py

@@ -62,7 +62,7 @@ def retry_with_exponential_backoff(
                 if num_retries > max_retries:
                     raise Exception(
                         f"Maximum number of retries ({max_retries}) exceeded."
-                        f" Last error: {e}."
+                        f" Last error: {str(e)}."
                     )
 
                 # Increment the delay
@@ -128,6 +128,7 @@ def async_retry_with_exponential_backoff(
                 if num_retries > max_retries:
                     raise Exception(
                         f"Maximum number of retries ({max_retries}) exceeded."
+                        f" Last error: {str(e)}."
                     )
 
                 # Increment the delay

langroid/mytypes.py

@@ -1,10 +1,9 @@
-import hashlib
-import uuid
 from enum import Enum
 from textwrap import dedent
 from typing import Any, Callable, Dict, List, Union
+from uuid import uuid4
 
-from langroid.pydantic_v1 import BaseModel, Extra
+from langroid.pydantic_v1 import BaseModel, Extra, Field
 
 Number = Union[int, float]
 Embedding = List[Number]
@@ -40,7 +39,7 @@ class DocMetaData(BaseModel):
 
     source: str = "context"
     is_chunk: bool = False  # if it is a chunk, don't split
-    id: str = ""  # unique id for the document
+    id: str = Field(default_factory=lambda: str(uuid4()))
     window_ids: List[str] = []  # for RAG: ids of chunks around this one
 
     def dict_bool_int(self, *args: Any, **kwargs: Any) -> Dict[str, Any]:
@@ -67,41 +66,11 @@ class Document(BaseModel):
     content: str
     metadata: DocMetaData
 
-    @staticmethod
-    def hash_id(doc: str) -> str:
-        # Encode the document as UTF-8
-        doc_utf8 = str(doc).encode("utf-8")
-
-        # Create a SHA256 hash object
-        sha256_hash = hashlib.sha256()
-
-        # Update the hash object with the bytes of the document
-        sha256_hash.update(doc_utf8)
-
-        # Get the hexadecimal representation of the hash
-        hash_hex = sha256_hash.hexdigest()
-
-        # Convert the first part of the hash to a UUID
-        hash_uuid = uuid.UUID(hash_hex[:32])
-
-        return str(hash_uuid)
-
-    def _unique_hash_id(self) -> str:
-        return self.hash_id(str(self))
-
     def id(self) -> str:
-        if (
-            hasattr(self.metadata, "id")
-            and self.metadata.id is not None
-            and self.metadata.id != ""
-        ):
-            return self.metadata.id
-        else:
-            return self._unique_hash_id()
+        return self.metadata.id
 
     def __str__(self) -> str:
         # TODO: make metadata a pydantic model to enforce "source"
-        self.metadata.json()
         return dedent(
             f"""
         CONTENT: {self.content}         

langroid/parsing/document_parser.py

@@ -8,6 +8,7 @@ from io import BytesIO
 from typing import TYPE_CHECKING, Any, Generator, List, Tuple
 
 from langroid.exceptions import LangroidImportError
+from langroid.utils.object_registry import ObjectRegistry
 
 try:
     import fitz
@@ -341,6 +342,8 @@ class DocumentParser(Parser):
         split = []  # tokens in curr split
         pages: List[str] = []
         docs: List[Document] = []
+        # metadata.id to be shared by ALL chunks of this document
+        common_id = ObjectRegistry.new_id()
         for i, page in self.iterate_pages():
             page_text = self.extract_text_from_page(page)
             split += self.tokenizer.encode(page_text)
@@ -358,6 +361,7 @@ class DocumentParser(Parser):
                         metadata=DocMetaData(
                             source=f"{self.source} pages {pg}",
                             is_chunk=True,
+                            id=common_id,
                         ),
                     )
                 )
@@ -372,6 +376,7 @@ class DocumentParser(Parser):
                     metadata=DocMetaData(
                         source=f"{self.source} pages {pg}",
                         is_chunk=True,
+                        id=common_id,
                     ),
                 )
             )

langroid/parsing/parser.py

@@ -7,6 +7,7 @@ import tiktoken
 from langroid.mytypes import Document
 from langroid.parsing.para_sentence_split import create_chunks, remove_extra_whitespace
 from langroid.pydantic_v1 import BaseSettings
+from langroid.utils.object_registry import ObjectRegistry
 
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.WARNING)
@@ -75,11 +76,13 @@ class Parser:
             return
         # The original metadata.id (if any) is ignored since it will be same for all
         # chunks and is useless. We want a distinct id for each chunk.
+        # ASSUMPTION: all chunks c of a doc have same c.metadata.id !
         orig_ids = [c.metadata.id for c in chunks]
-        ids = [Document.hash_id(str(c)) for c in chunks]
+        ids = [ObjectRegistry.new_id() for c in chunks]
         id2chunk = {id: c for id, c in zip(ids, chunks)}
 
         # group the ids by orig_id
+        # (each distinct orig_id refers to a different document)
         orig_id_to_ids: Dict[str, List[str]] = {}
         for orig_id, id in zip(orig_ids, ids):
             if orig_id not in orig_id_to_ids:
@@ -108,6 +111,10 @@ class Parser:
             if d.content.strip() == "":
                 continue
             chunks = remove_extra_whitespace(d.content).split(self.config.separators[0])
+            # note we are ensuring we COPY the document metadata into each chunk,
+            # which ensures all chunks of a given doc have same metadata
+            # (and in particular same metadata.id, which is important later for
+            # add_window_ids)
             chunk_docs = [
                 Document(
                     content=c, metadata=d.metadata.copy(update=dict(is_chunk=True))
@@ -156,6 +163,10 @@ class Parser:
             if d.content.strip() == "":
                 continue
             chunks = create_chunks(d.content, self.config.chunk_size, self.num_tokens)
+            # note we are ensuring we COPY the document metadata into each chunk,
+            # which ensures all chunks of a given doc have same metadata
+            # (and in particular same metadata.id, which is important later for
+            # add_window_ids)
             chunk_docs = [
                 Document(
                     content=c, metadata=d.metadata.copy(update=dict(is_chunk=True))
@@ -171,6 +182,10 @@ class Parser:
         final_docs = []
         for d in docs:
             chunks = self.chunk_tokens(d.content)
+            # note we are ensuring we COPY the document metadata into each chunk,
+            # which ensures all chunks of a given doc have same metadata
+            # (and in particular same metadata.id, which is important later for
+            # add_window_ids)
             chunk_docs = [
                 Document(
                     content=c, metadata=d.metadata.copy(update=dict(is_chunk=True))
@@ -274,7 +289,7 @@ class Parser:
         # we need this to distinguish docs later in add_window_ids
         for d in docs:
             if d.metadata.id in [None, ""]:
-                d.metadata.id = d._unique_hash_id()
+                d.metadata.id = ObjectRegistry.new_id()
         # some docs are already splits, so don't split them further!
         chunked_docs = [d for d in docs if d.metadata.is_chunk]
         big_docs = [d for d in docs if not d.metadata.is_chunk]

langroid/utils/__init__.py

@@ -5,6 +5,7 @@ from . import logging
 from . import pydantic_utils
 from . import system
 from . import output
+from . import object_registry
 
 __all__ = [
     "configuration",
@@ -14,4 +15,5 @@ __all__ = [
     "pydantic_utils",
     "system",
     "output",
+    "object_registry",
 ]

langroid/utils/object_registry.py

@@ -0,0 +1,66 @@
+import time
+from typing import TYPE_CHECKING, Dict, Optional, TypeAlias, TypeVar
+from uuid import uuid4
+
+from langroid.pydantic_v1 import BaseModel
+
+if TYPE_CHECKING:
+    from langroid.agent.base import Agent
+    from langroid.agent.chat_agent import ChatAgent
+    from langroid.agent.chat_document import ChatDocument
+
+    # any derivative of BaseModel that has an id() method or an id attribute
+    ObjWithId: TypeAlias = ChatDocument | ChatAgent | Agent
+else:
+    ObjWithId = BaseModel
+
+# Define a type variable that can be any subclass of BaseModel
+T = TypeVar("T", bound=BaseModel)
+
+
+class ObjectRegistry:
+    """A global registry to hold id -> object mappings."""
+
+    registry: Dict[str, ObjWithId] = {}
+
+    @classmethod
+    def add(cls, obj: ObjWithId) -> str:
+        """Adds an object to the registry, returning the object's ID."""
+        object_id = obj.id() if callable(obj.id) else obj.id
+        cls.registry[object_id] = obj
+        return object_id
+
+    @classmethod
+    def get(cls, obj_id: str) -> Optional[ObjWithId]:
+        """Retrieves an object by ID if it still exists."""
+        return cls.registry.get(obj_id)
+
+    @classmethod
+    def register_object(cls, obj: ObjWithId) -> str:
+        """Registers an object in the registry, returning the object's ID."""
+        return cls.add(obj)
+
+    @classmethod
+    def remove(cls, obj_id: str) -> None:
+        """Removes an object from the registry."""
+        if obj_id in cls.registry:
+            del cls.registry[obj_id]
+
+    @classmethod
+    def cleanup(cls) -> None:
+        """Cleans up the registry by removing entries where the object is None."""
+        to_remove = [key for key, value in cls.registry.items() if value is None]
+        for key in to_remove:
+            del cls.registry[key]
+
+    @staticmethod
+    def new_id() -> str:
+        """Generates a new unique ID."""
+        return str(uuid4())
+
+
+def scheduled_cleanup(interval: int = 600) -> None:
+    """Periodically cleans up the global registry every 'interval' seconds."""
+    while True:
+        ObjectRegistry.cleanup()
+        time.sleep(interval)

langroid/utils/system.py

@@ -181,5 +181,4 @@ def hash(s: str) -> str:
 
 def generate_unique_id() -> str:
     """Generate a unique ID using UUID4."""
-    unique_id = str(uuid.uuid4())
-    return unique_id
+    return str(uuid.uuid4())

langroid/vector_store/base.py

@@ -12,6 +12,7 @@ from langroid.mytypes import Document
 from langroid.pydantic_v1 import BaseSettings
 from langroid.utils.algorithms.graph import components, topological_sort
 from langroid.utils.configuration import settings
+from langroid.utils.object_registry import ObjectRegistry
 from langroid.utils.output.printing import print_long_text
 from langroid.utils.pandas_utils import stringify
 
@@ -163,7 +164,7 @@ class VectorStore(ABC):
         vecdbs don't like having blank ids."""
         for d in documents:
             if d.metadata.id in [None, ""]:
-                d.metadata.id = d._unique_hash_id()
+                d.metadata.id = ObjectRegistry.new_id()
 
     @abstractmethod
     def similar_texts_with_scores(
@@ -254,7 +255,7 @@ class VectorStore(ABC):
                 metadata=metadata,
             )
             # make a fresh id since content is in general different
-            document.metadata.id = document.hash_id(document.content)
+            document.metadata.id = ObjectRegistry.new_id()
             final_docs += [document]
             final_scores += [max(id2max_score[id] for id in w)]
         return list(zip(final_docs, final_scores))

{langroid-0.1.265.dist-info → langroid-0.2.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.265
+Version: 0.2.0
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
@@ -423,7 +423,7 @@ Here is what it looks like in action
 
 # :zap: Highlights
 (For a more up-to-date list see the 
-[release](https://github.com/langroid/langroid?tab=readme-ov-file#fire-updatesreleases) 
+[Updates/Releases](https://github.com/langroid/langroid?tab=readme-ov-file#fire-updatesreleases) 
 section above)
 - **Agents as first-class citizens:** The [Agent](https://langroid.github.io/langroid/reference/agent/base/#langroid.agent.base.Agent) class encapsulates LLM conversation state,
   and optionally a vector-store and tools. Agents are a core abstraction in Langroid;
@@ -439,8 +439,8 @@ section above)
 - **Modularity, Reusability, Loose coupling:** The `Agent` and `Task` abstractions allow users to design
   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 or remote/commercial) via proxy libraries and local model servers
-such as [LiteLLM](https://docs.litellm.ai/docs/providers) that in effect mimic the OpenAI API. 
+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. 
 - **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.
@@ -450,7 +450,7 @@ such as [LiteLLM](https://docs.litellm.ai/docs/providers) that in effect mimic t
 - **Observability, Logging, Lineage:** Langroid generates detailed logs of multi-agent interactions and
   maintains provenance/lineage of messages, so that you can trace back
   the origin of a message.
-- **Tools/Plugins/Function-calling**: Langroid supports OpenAI's recently
+- **[Tools/Plugins/Function-calling](https://langroid.github.io/langroid/quick-start/chat-agent-tool/)**: Langroid supports OpenAI's recently
   released [function calling](https://platform.openai.com/docs/guides/gpt/function-calling)
   feature. In addition, Langroid has its own native equivalent, which we
   call **tools** (also known as "plugins" in other contexts). Function

{langroid-0.1.265.dist-info → langroid-0.2.0.dist-info}/RECORD

@@ -1,16 +1,16 @@
 langroid/__init__.py,sha256=z_fCOLQJPOw3LLRPBlFB5-2HyCjpPgQa4m4iY5Fvb8Y,1800
 langroid/agent/__init__.py,sha256=ll0Cubd2DZ-fsCMl7e10hf9ZjFGKzphfBco396IKITY,786
-langroid/agent/base.py,sha256=CHFUZ4vnC1CSMMT5POnY4AWu96RQ-4uDUARUbhGAGo8,37195
+langroid/agent/base.py,sha256=rqkf5FN1jO7IGqa_bvnQc37d8LZRal1RHVJe0Dvtlsc,37680
 langroid/agent/batch.py,sha256=feRA_yRG768ElOQjrKEefcRv6Aefd_yY7qktuYUQDwc,10040
 langroid/agent/callbacks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/agent/callbacks/chainlit.py,sha256=UKG2_v4ktfkEaGvdouVRHEqQejEYya2Rli8jrP65TmA,22055
-langroid/agent/chat_agent.py,sha256=hnmeOxdi4i5w8WaL2kPjQOEpenoRW_hG5EfeMWuuVsQ,39478
-langroid/agent/chat_document.py,sha256=tXFuUw2fs8WVIhVt10Sne0IpOzPPEaFz_1yqQgU6V4U,9218
+langroid/agent/chat_agent.py,sha256=eRTrTjGlu36gTbdBLbQ5M5EtBMIcdEc9bjgMLTa40oQ,41506
+langroid/agent/chat_document.py,sha256=8yH7o0aMVtUDHh3InpEErjhlY6t4Lr6KQzBrAKcYsEM,11141
 langroid/agent/helpers.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/agent/junk,sha256=LxfuuW7Cijsg0szAzT81OjWWv1PMNI-6w_-DspVIO2s,339
 langroid/agent/openai_assistant.py,sha256=rmGJD5n0eE7_O1EkPyXgHFMNGc3vb2GKweZMhzmRWvI,33068
 langroid/agent/special/__init__.py,sha256=gik_Xtm_zV7U9s30Mn8UX3Gyuy4jTjQe9zjiE3HWmEo,1273
-langroid/agent/special/doc_chat_agent.py,sha256=dlXsY7brhrGOf_TA39EgkcL80L102Gkunoid7GvIZNY,54444
+langroid/agent/special/doc_chat_agent.py,sha256=CXFLfDMEabaBZwZwFgNOaG3E3S86xcBM4txrsMD_70I,54014
 langroid/agent/special/lance_doc_chat_agent.py,sha256=USp0U3eTaJzwF_3bdqE7CedSLbaqAi2tm-VzygcyLaA,10175
 langroid/agent/special/lance_rag/__init__.py,sha256=QTbs0IVE2ZgDg8JJy1zN97rUUg4uEPH7SLGctFNumk4,174
 langroid/agent/special/lance_rag/critic_agent.py,sha256=ufTdpHSeHgCzN85Q0sfWOrpBpsCjGVZdAg5yOH1ogU8,7296
@@ -32,9 +32,9 @@ langroid/agent/special/sql/utils/populate_metadata.py,sha256=1J22UsyEPKzwK0XlJZt
 langroid/agent/special/sql/utils/system_message.py,sha256=qKLHkvQWRQodTtPLPxr1GSLUYUFASZU8x-ybV67cB68,1885
 langroid/agent/special/sql/utils/tools.py,sha256=vFYysk6Vi7HJjII8B4RitA3pt_z3gkSglDNdhNVMiFc,1332
 langroid/agent/special/table_chat_agent.py,sha256=d9v2wsblaRx7oMnKhLV7uO_ujvk9gh59pSGvBXyeyNc,9659
-langroid/agent/task.py,sha256=AA8MKWVeZ6VeI3uAVhXzMgZWULGRtYoNXQ6HeAzS4oU,61011
+langroid/agent/task.py,sha256=ZTnG8h214FF3Vm54Eyl37j5OzKIHc313QbiUkMlofwM,67091
 langroid/agent/tool_message.py,sha256=wIyZnUcZpxkiRPvM9O3MO3b5BBAdLEEan9kqPbvtApc,9743
-langroid/agent/tools/__init__.py,sha256=8Pc9BlGCB5FQ2IDGKS_WPpHCoWp5jblMU8EHJwwikAY,303
+langroid/agent/tools/__init__.py,sha256=e-63cfwQNk_ftRKQwgDAJQK16QLbRVWDBILeXIc7wLk,402
 langroid/agent/tools/duckduckgo_search_tool.py,sha256=NhsCaGZkdv28nja7yveAhSK_w6l_Ftym8agbrdzqgfo,1935
 langroid/agent/tools/extract_tool.py,sha256=u5lL9rKBzaLBOrRyLnTAZ97pQ1uxyLP39XsWMnpaZpw,3789
 langroid/agent/tools/generator_tool.py,sha256=y0fB0ZObjA0b3L0uSTtrqRCKHDUR95arBftqiUeKD2o,663
@@ -42,6 +42,7 @@ langroid/agent/tools/google_search_tool.py,sha256=y7b-3FtgXf0lfF4AYxrZ3K5pH2dhid
 langroid/agent/tools/metaphor_search_tool.py,sha256=qj4gt453cLEX3EGW7nVzVu6X7LCdrwjSlcNY0qJW104,2489
 langroid/agent/tools/recipient_tool.py,sha256=NrLxIeQT-kbMv7AeYX0uqvGeMK4Q3fIDvG15OVzlgk8,9624
 langroid/agent/tools/retrieval_tool.py,sha256=2q2pfoYbZNfbWQ0McxrtmfF0ekGglIgRl-6uF26pa-E,871
+langroid/agent/tools/rewind_tool.py,sha256=aeu35_OjmCDTCgWH6nn8noXIC7ACD7-Rh-qh36wnBOg,5516
 langroid/agent/tools/run_python_code.py,sha256=BvoxYzzHijU-p4703n2iVlt5BCieR1oMSy50w0tQZAg,1787
 langroid/agent/tools/segment_extract_tool.py,sha256=__srZ_VGYLVOdPrITUM8S0HpmX4q7r5FHWMDdHdEv8w,1440
 langroid/agent_config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -60,28 +61,28 @@ langroid/embedding_models/protoc/embeddings_pb2.pyi,sha256=UkNy7BrNsmQm0vLb3NtGX
 langroid/embedding_models/protoc/embeddings_pb2_grpc.py,sha256=9dYQqkW3JPyBpSEjeGXTNpSqAkC-6FPtBHyteVob2Y8,2452
 langroid/embedding_models/remote_embeds.py,sha256=6_kjXByVbqhY9cGwl9R83ZcYC2km-nGieNNAo1McHaY,5151
 langroid/exceptions.py,sha256=w_Cr41nPAmsa6gW5nNFaO9yDcBCWdQqRspL1jYvZf5w,2209
-langroid/language_models/__init__.py,sha256=55602F5QA58MmRq-yRjoXK6xZOMRHQrR4QGaCnlX218,822
+langroid/language_models/__init__.py,sha256=vrBtgR8Cq9UVfoI7nTms0IN7fd4y2JYpUP3GNV1DegY,898
 langroid/language_models/azure_openai.py,sha256=ncRCbKooqLVOY-PWQUIo9C3yTuKEFbAwyngXT_M4P7k,5989
-langroid/language_models/base.py,sha256=UbHcXSzQ5pTc_H5VSDh45c6dsyJwfY0H5_6ofEBXH-8,16917
+langroid/language_models/base.py,sha256=aVptuo_LpymIQFpJh836lcFCUpJNOV3ukxvQAQMCqFc,17426
 langroid/language_models/config.py,sha256=9Q8wk5a7RQr8LGMT_0WkpjY8S4ywK06SalVRjXlfCiI,378
-langroid/language_models/openai_assistants.py,sha256=9K-DEAL2aSWHeXj2hwCo2RAlK9_1oCPtqX2u1wISCj8,36
+langroid/language_models/mock_lm.py,sha256=L0YqrrxLCePs_5MrK7rJ5-SajNxDtuVU_VvZVRfs9q4,2834
 langroid/language_models/openai_gpt.py,sha256=RXnLKULuCSeDeUPQvaZ4naqJgMKcMZogCtRDLycd4j8,50714
 langroid/language_models/prompt_formatter/__init__.py,sha256=2-5cdE24XoFDhifOLl8yiscohil1ogbP1ECkYdBlBsk,372
 langroid/language_models/prompt_formatter/base.py,sha256=eDS1sgRNZVnoajwV_ZIha6cba5Dt8xjgzdRbPITwx3Q,1221
 langroid/language_models/prompt_formatter/hf_formatter.py,sha256=TFL6ppmeQWnzr6CKQzRZFYY810zE1mr8DZnhw6i85ok,5217
 langroid/language_models/prompt_formatter/llama2_formatter.py,sha256=YdcO88qyBeuMENVIVvVqSYuEpvYSTndUe_jd6hVTko4,2899
-langroid/language_models/utils.py,sha256=j8xEEm__-2b9eql1oTiWQk5dHW59UwmrRKs5kMHaGGo,4803
-langroid/mytypes.py,sha256=B5uKN4FMdHiJaAKozg8EmcPfle3sHlj11NcBnpXn7nE,3057
+langroid/language_models/utils.py,sha256=o6Zo2cnnvKrfSgF26knVQ1xkSxEoE7yN85296gNdVOw,4858
+langroid/mytypes.py,sha256=YjlunP4n_-J3wDNQM4MBtLyOuaa1qJJpwzVfvn0Ca1A,2206
 langroid/parsing/__init__.py,sha256=ZgSAfgTC6VsTLFlRSWT-TwYco7SQeRMeZG-49MnKYGY,936
 langroid/parsing/agent_chats.py,sha256=sbZRV9ujdM5QXvvuHVjIi2ysYSYlap-uqfMMUKulrW0,1068
 langroid/parsing/code-parsing.md,sha256=--cyyNiSZSDlIwcjAV4-shKrSiRe2ytF3AdSoS_hD2g,3294
 langroid/parsing/code_parser.py,sha256=Fwa8MWY5EGk7Ekr8II5c-o9vBf4m1HfB5_K7e_EDYzo,3739
 langroid/parsing/config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-langroid/parsing/document_parser.py,sha256=bN-D1kqx6qe1Sx-AMR8a8WbPJYPdoxLYPdgGl7dfW3I,24017
+langroid/parsing/document_parser.py,sha256=WGnA5ADwMHliGJt6WW9rc4RiFXQcKU33b5zdPiGrtEY,24265
 langroid/parsing/image_text.py,sha256=sbLIQ5nHe2UnYUksBaQsmZGaX-X0qgEpPd7CEzi_z5M,910
 langroid/parsing/para_sentence_split.py,sha256=AJBzZojP3zpB-_IMiiHismhqcvkrVBQ3ZINoQyx_bE4,2000
 langroid/parsing/parse_json.py,sha256=tgB_oatcrgt6L9ZplC-xBBXjLzL1gjSQf1L2_W5kwFA,4230
-langroid/parsing/parser.py,sha256=VU3G2GXwho5vJ3tCDgw6_1W-guqAbPtml8RcJxvp-Xs,10755
+langroid/parsing/parser.py,sha256=AgtmlVUvrkSG1l7-YZPX8rlldgXjh_HqXAMqpXkBxUo,11746
 langroid/parsing/repo_loader.py,sha256=3GjvPJS6Vf5L6gV2zOU8s-Tf1oq_fZm-IB_RL_7CTsY,29373
 langroid/parsing/routing.py,sha256=_NFPe7wLjd5B6s47w3M8-5vldL8e2Sz51Gb5bwF5ooY,1072
 langroid/parsing/search.py,sha256=plQtjarB9afGfJLB0CyPXPq3mM4m7kRsfd0_4brziEI,8846
@@ -99,7 +100,7 @@ langroid/prompts/prompts_config.py,sha256=p_lp9nbMuQwhhMwAZsOxveRw9C0ZFZvql7pdIf
 langroid/prompts/templates.py,sha256=kz0rPiM6iLGhhpDonF3Y87OznSe9FRI6A0pHU0wgW4Q,6314
 langroid/pydantic_v1/__init__.py,sha256=HxPGVERapVueRUORgSpj2JX_vTZxVlVbWvhpQlpjygE,283
 langroid/pydantic_v1/main.py,sha256=p_k7kDY9eDrsA5dxNNqXusKLgx7mS_icGnS7fu4goqY,147
-langroid/utils/__init__.py,sha256=ARx5To4Hsv1K5QAzK4uUqdEoB_iq5HK797vae1AcMBI,300
+langroid/utils/__init__.py,sha256=Sruos2tB4G7Tn0vlblvYlX9PEGR0plI2uE0PJ4d_EC4,353
 langroid/utils/algorithms/__init__.py,sha256=WylYoZymA0fnzpB4vrsH_0n7WsoLhmuZq8qxsOCjUpM,41
 langroid/utils/algorithms/graph.py,sha256=JbdpPnUOhw4-D6O7ou101JLA3xPCD0Lr3qaPoFCaRfo,2866
 langroid/utils/configuration.py,sha256=A70LdvdMuunlLSGI1gBmBL5j6Jhz-1syNP8R4AdjqDc,3295
@@ -109,25 +110,26 @@ langroid/utils/globals.py,sha256=Az9dOFqR6n9CoTYSqa2kLikQWS0oCQ9DFQIQAnG-2q8,135
 langroid/utils/llms/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/utils/llms/strings.py,sha256=CSAX9Z6FQOLXOzbLMe_Opqtc3ruDAKTTk7cPqc6Blh0,263
 langroid/utils/logging.py,sha256=WN180zjxhlozwtyTcLWmbVkXylBs5EvQj85dBPeVUwc,3985
+langroid/utils/object_registry.py,sha256=iPz9GHzvmCeVoidB3JdAMEKcxJEqTdUr0otQEexDZ5s,2100
 langroid/utils/output/__init__.py,sha256=7P0f--4IZneNsTxXY5fd6d6iW-CeVe-KSsl-87sbBPc,340
 langroid/utils/output/citations.py,sha256=PSY2cpti8W-ZGFMAgj1lYoEIZy0lsniLpCliMsVkXtc,1425
 langroid/utils/output/printing.py,sha256=yzPJZN-8_jyOJmI9N_oLwEDfjMwVgk3IDiwnZ4eK_AE,2962
 langroid/utils/output/status.py,sha256=rzbE7mDJcgNNvdtylCseQcPGCGghtJvVq3lB-OPJ49E,1049
 langroid/utils/pandas_utils.py,sha256=UctS986Jtl_MvU5rA7-GfrjEHXP7MNu8ePhepv0bTn0,755
 langroid/utils/pydantic_utils.py,sha256=FKC8VKXH2uBEpFjnnMgIcEsQn6hs31ftea8zv5pMK9g,21740
-langroid/utils/system.py,sha256=ClIQOpJOeCgfi9n5c-bOS62B2cuqrZFGkWPRbjCpSqk,5208
+langroid/utils/system.py,sha256=nvKeeUAj4eviR4kYpcr9h-HYdhqUNMTRBTHBOhz0GdU,5182
 langroid/utils/web/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/utils/web/login.py,sha256=1iz9eUAHa87vpKIkzwkmFa00avwFWivDSAr7QUhK7U0,2528
 langroid/vector_store/__init__.py,sha256=6xBjb_z4QtUy4vz4RuFbcbSwmHrggHL8-q0DwCf3PMM,972
-langroid/vector_store/base.py,sha256=1bzFEDJcbKIaZnTPhBjnQ260c6QYs5SpZwGMtwt0-6Y,13481
+langroid/vector_store/base.py,sha256=tuEPaxJcuU_39sRnUjjNd8D8n8IjP6jrbwQv_ecNpSw,13532
 langroid/vector_store/chromadb.py,sha256=bZ5HjwgKgfJj1PUHsatYsrHv-v0dpOfMR2l0tJ2H0_A,7890
 langroid/vector_store/lancedb.py,sha256=9x7e_5zo7nLhMbhjYby2ZpBJ-vyawcC0_XAuatfHJf8,20517
 langroid/vector_store/meilisearch.py,sha256=6frB7GFWeWmeKzRfLZIvzRjllniZ1cYj3HmhHQICXLs,11663
 langroid/vector_store/momento.py,sha256=QaPzUnTwlswoawGB-paLtUPyLRvckFXLfLDfvbTzjNQ,10505
 langroid/vector_store/qdrant_cloud.py,sha256=3im4Mip0QXLkR6wiqVsjV1QvhSElfxdFSuDKddBDQ-4,188
 langroid/vector_store/qdrantdb.py,sha256=wYOuu5c2vIKn9ZgvTXcAiZXMpV8AOXEWFAzI8S8UP-0,16828
-pyproject.toml,sha256=zJRntm67SKuTYmuGM9SuBHq3t8_YCES7QJZrUnOBhEs,6966
-langroid-0.1.265.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.1.265.dist-info/METADATA,sha256=k8pBX7RAwBzJqfOxHE0HOezRNV1HGgxhRFEu9r9BpWQ,52514
-langroid-0.1.265.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-langroid-0.1.265.dist-info/RECORD,,
+pyproject.toml,sha256=dZYHxf2D_qc8g68xt4KgMoa7tuxbY_JpLn-Pd541kuw,6964
+langroid-0.2.0.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.2.0.dist-info/METADATA,sha256=vcctmhiBgiBI4LlzmbJFMfRG7nwjD4B1IZvnDu0XR_M,52823
+langroid-0.2.0.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+langroid-0.2.0.dist-info/RECORD,,

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langroid"
-version = "0.1.265"
+version = "0.2.0"
 description = "Harness LLMs with Multi-Agent Programming"
 authors = ["Prasad Chalasani <pchalasani@gmail.com>"]
 readme = "README.md"

langroid/language_models/openai_assistants.py

@@ -1,3 +0,0 @@
-import openai
-
-openai.models.list()