langroid 0.28.6__tar.gz → 0.28.7__tar.gz

{langroid-0.28.6 → langroid-0.28.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.28.6
+Version: 0.28.7
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani

langroid-0.28.7/langroid/agent/team.py

@@ -0,0 +1,41 @@
+from abc import ABC, abstractmethod
+
+class TeamComponent(ABC):
+    @abstractmethod
+    def run(self, msg):
+        pass
+
+class Team(TeamComponent):
+    def __init__(self):
+        self.components = []
+        self.input_port = []
+        self.followers = []
+        self.scheduler = None
+
+    def follow(self, team):
+        team.followers.append(self)
+
+    def add_component(self, component):
+        self.components.append(component)
+
+    def notify_followers(self, result):
+        for follower in self.followers:
+            follower.input_port.append(result)
+
+    def run(self, msg):
+        if self.scheduler:
+            return self.scheduler.run(self.components, msg)
+        # Default sequential execution
+        result = ""
+        for component in self.components:
+            result += component.run(msg)
+        self.notify_followers(result)
+        return result
+
+class Agent(TeamComponent):
+    def __init__(self, name):
+        self.name = name
+
+    def run(self, msg):
+        result = f"Agent {self.name} processed: {msg}"
+        return result

{langroid-0.28.6 → langroid-0.28.7}/langroid/vector_store/base.py

@@ -30,6 +30,7 @@ class VectorStoreConfig(BaseSettings):
     embedding: EmbeddingModelsConfig = OpenAIEmbeddingsConfig(
         model_type="openai",
     )
+    embedding_model: Optional[EmbeddingModel] = None
     timeout: int = 60
     host: str = "127.0.0.1"
     port: int = 6333
@@ -46,7 +47,10 @@ class VectorStore(ABC):
 
     def __init__(self, config: VectorStoreConfig):
         self.config = config
-        self.embedding_model = EmbeddingModel.create(config.embedding)
+        if config.embedding_model is None:
+            self.embedding_model = EmbeddingModel.create(config.embedding)
+        else:
+            self.embedding_model = config.embedding_model
 
     @staticmethod
     def create(config: VectorStoreConfig) -> Optional["VectorStore"]:

{langroid-0.28.6 → langroid-0.28.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langroid"
-version = "0.28.6"
+version = "0.28.7"
 description = "Harness LLMs with Multi-Agent Programming"
 authors = ["Prasad Chalasani <pchalasani@gmail.com>"]
 readme = "README.md"