langroid 0.1.226__tar.gz → 0.1.228__tar.gz

{langroid-0.1.226 → langroid-0.1.228}/PKG-INFO

@@ -1,14 +1,13 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.226
+Version: 0.1.228
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
 Author-email: pchalasani@gmail.com
-Requires-Python: >=3.9.1,<3.12
+Requires-Python: >=3.11,<3.12
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Provides-Extra: chainlit
 Provides-Extra: chromadb
@@ -19,10 +18,8 @@ Provides-Extra: mkdocs
 Provides-Extra: mysql
 Provides-Extra: neo4j
 Provides-Extra: postgres
-Provides-Extra: sciphi
 Provides-Extra: transformers
 Provides-Extra: unstructured
-Requires-Dist: agent-search (>=0.0.7,<0.0.8) ; extra == "sciphi"
 Requires-Dist: aiohttp (>=3.9.1,<4.0.0)
 Requires-Dist: async-generator (>=1.10,<2.0)
 Requires-Dist: autopep8 (>=2.0.2,<3.0.0)

{langroid-0.1.226 → langroid-0.1.228}/langroid/agent/openai_assistant.py

@@ -8,6 +8,10 @@ from enum import Enum
 from typing import Any, Dict, List, Optional, Tuple, Type, cast, no_type_check
 
 from openai.types.beta import Assistant, Thread
+from openai.types.beta.assistant_update_params import (
+    ToolResources,
+    ToolResourcesCodeInterpreter,
+)
 from openai.types.beta.threads import Message, Run
 from openai.types.beta.threads.runs import RunStep
 from pydantic import BaseModel
@@ -29,7 +33,7 @@ logger = logging.getLogger(__name__)
 
 
 class ToolType(str, Enum):
-    RETRIEVAL = "retrieval"
+    RETRIEVAL = "file_search"
     CODE_INTERPRETER = "code_interpreter"
     FUNCTION = "function"
 
@@ -127,7 +131,11 @@ class OpenAIAssistant(ChatAgent):
         self.config.files = list(set(self.config.files + files))
         self.assistant = self.assistants.update(
             self.assistant.id,
-            file_ids=[f.id for f in self.files],
+            tool_resources=ToolResources(
+                code_interpreter=ToolResourcesCodeInterpreter(
+                    file_ids=[f.id for f in self.files],
+                ),
+            ),
         )
 
     def add_assistant_tools(self, tools: List[AssistantTool]) -> None:

{langroid-0.1.226 → langroid-0.1.228}/langroid/agent/special/doc_chat_agent.py

@@ -169,7 +169,8 @@ class DocChatAgentConfig(ChatAgentConfig):
         dims=1536,
     )
 
-    vecdb: VectorStoreConfig = LanceDBConfig(
+    # Allow vecdb to be None in case we want to explicitly set it later
+    vecdb: Optional[VectorStoreConfig] = LanceDBConfig(
         collection_name="doc-chat-lancedb",
         replace_collection=True,
         storage_path=".lancedb/data/",
@@ -209,12 +210,13 @@ class DocChatAgent(ChatAgent):
 
     def clear(self) -> None:
         """Clear the document collection and the specific collection in vecdb"""
-        if self.vecdb is None:
-            raise ValueError("VecDB not set")
         self.original_docs = []
         self.original_docs_length = 0
         self.chunked_docs = []
         self.chunked_docs_clean = []
+        if self.vecdb is None:
+            logger.warning("Attempting to clear VecDB, but VecDB not set.")
+            return
         collection_name = self.vecdb.config.collection_name
         if collection_name is None:
             return

{langroid-0.1.226 → langroid-0.1.228}/langroid/language_models/openai_gpt.py

@@ -69,7 +69,7 @@ class OpenAIChatModel(str, Enum):
     GPT3_5_TURBO = "gpt-3.5-turbo-1106"
     GPT4 = "gpt-4"
     GPT4_32K = "gpt-4-32k"
-    GPT4_TURBO = "gpt-4-turbo-preview"
+    GPT4_TURBO = "gpt-4-turbo"
 
 
 class OpenAICompletionModel(str, Enum):

{langroid-0.1.226 → langroid-0.1.228}/langroid/vector_store/qdrantdb.py

@@ -192,8 +192,7 @@ class QdrantDB(VectorStore):
                 with the same name. Defaults to False.
         """
         self.config.collection_name = collection_name
-        collections = self.list_collections()
-        if collection_name in collections:
+        if self.client.collection_exists(collection_name=collection_name):
             coll = self.client.get_collection(collection_name=collection_name)
             if (
                 coll.status == CollectionStatus.GREEN
@@ -205,7 +204,8 @@ class QdrantDB(VectorStore):
                     return
                 else:
                     logger.warning("Recreating fresh collection")
-        self.client.recreate_collection(
+            self.client.delete_collection(collection_name=collection_name)
+        self.client.create_collection(
             collection_name=collection_name,
             vectors_config=VectorParams(
                 size=self.embedding_dim,
@@ -214,7 +214,7 @@ class QdrantDB(VectorStore):
         )
         collection_info = self.client.get_collection(collection_name=collection_name)
         assert collection_info.status == CollectionStatus.GREEN
-        assert collection_info.vectors_count == 0
+        assert collection_info.vectors_count in [0, None]
         if settings.debug:
             level = logger.getEffectiveLevel()
             logger.setLevel(logging.INFO)

{langroid-0.1.226 → langroid-0.1.228}/pyproject.toml

@@ -1,13 +1,13 @@
 [tool.poetry]
 name = "langroid"
-version = "0.1.226"
+version = "0.1.228"
 description = "Harness LLMs with Multi-Agent Programming"
 authors = ["Prasad Chalasani <pchalasani@gmail.com>"]
 readme = "README.md"
 license = "MIT"
 
 [tool.poetry.dependencies]
-python = ">=3.9.1,<3.12"
+python = ">=3.11,<3.12"
 mkdocs = {version="^1.4.2", optional=true}
 mkdocs-material = {version="^9.1.5", optional=true}
 mkdocstrings = {extras = ["python"], version = "^0.21.2", optional=true}
@@ -84,7 +84,6 @@ lancedb = "^0.6.2"
 pyarrow = "15.0.0"
 pytest-redis = "^3.0.2"
 neo4j = {version = "^5.14.1", optional = true}
-agent-search = {version = "^0.0.7", optional = true}
 python-docx = "^1.1.0"
 aiohttp = "^3.9.1"
 grpcio = "^1.62.1"
@@ -108,7 +107,6 @@ postgres = ["psycopg2", "pytest-postgresql"]
 mysql = ["pymysql", "pytest-mysql"]
 litellm = ["litellm"]
 neo4j = ["neo4j"]
-sciphi = ["agent-search"]
 metaphor = ["metaphor-python"]
 chainlit = ["chainlit", "python-socketio"]
 chromadb = ["chromadb"]

langroid-0.1.226/langroid/agent/tools/sciphi_search_rag_tool.py

@@ -1,79 +0,0 @@
-"""
-A tool which returns a Search RAG response from the SciPhi API.
-their titles, links, summaries. Since the tool is stateless (i.e. does not need
-access to agent state), it can be enabled for any agent, without having to define a
-special method inside the agent: `agent.enable_message(SciPhiSearchRAGTool)`
-
-Example return output appears as follows below:
-
-<-- Query -->
-```
-Find 3 results on the internet about the LK-99 superconducting material.
-``
-
-<-- Response (compressed for this example)-->
-```
-[ result1 ]
-
-[ result2 ]
-
-[ result3 ]
-
-```
-
-NOTE: Using this tool requires getting an API key from sciphi.ai.
-Setup is as simple as shown below
-# Get a free API key at https://www.sciphi.ai/account
-# export SCIPHI_API_KEY=$MY_SCIPHI_API_KEY before running the agent
-# OR add SCIPHI_API_KEY=$MY_SCIPHI_API_KEY to your .env file
-
-This tool requires installing langroid with the `sciphi` extra, e.g.
-`pip install langroid[sciphi]` or `poetry add langroid[sciphi]`
-(it installs the `agent-search` package from pypi).
-
-For more information, please refer to the official docs:
-https://agent-search.readthedocs.io/en/latest/
-"""
-
-from typing import List
-
-try:
-    from agent_search import SciPhi
-except ImportError:
-    raise ImportError(
-        "You are attempting to use the `agent-search` library;"
-        "To use it, please install langroid with the `sciphi` extra, e.g. "
-        "`pip install langroid[sciphi]` or `poetry add langroid[sciphi]` "
-        "(it installs the `agent-search` package from pypi)."
-    )
-
-from langroid.agent.tool_message import ToolMessage
-
-
-class SciPhiSearchRAGTool(ToolMessage):
-    request: str = "web_search_rag"
-    purpose: str = """
-            To search the web with provider <search_provider> and 
-            return a response summary with llm model <llm_model> the given <query>. 
-            """
-    query: str
-
-    def handle(self) -> str:
-        rag_response = SciPhi().get_search_rag_response(
-            query=self.query, search_provider="bing", llm_model="SciPhi/Sensei-7B-V1"
-        )
-        result = rag_response["response"]
-        result = (
-            f"### RAG Response:\n{result}\n\n"
-            + "### Related Queries:\n"
-            + "\n".join(rag_response["related_queries"])
-        )
-        return result  # type: ignore
-
-    @classmethod
-    def examples(cls) -> List["ToolMessage"]:
-        return [
-            cls(
-                query="When was the Llama2 Large Language Model (LLM) released?",
-            ),
-        ]