Merge branch 'main' into users/david/ollama-tools

autogen/agentchat/contrib/agent_builder.py

@@ -103,7 +103,7 @@ class AgentBuilder:
 """
 
     AGENT_NAME_PROMPT = """# Your task
-Suggest no more then {max_agents} experts with their name according to the following user requirement.
+Suggest no more than {max_agents} experts with their name according to the following user requirement.
 
 ## User requirement
 {task}

autogen/agentchat/contrib/graph_rag/document.py

@@ -0,0 +1,24 @@
+from dataclasses import dataclass
+from enum import Enum, auto
+from typing import Optional
+
+
+class DocumentType(Enum):
+    """
+    Enum for supporting document type.
+    """
+
+    TEXT = auto()
+    HTML = auto()
+    PDF = auto()
+
+
+@dataclass
+class Document:
+    """
+    A wrapper of graph store query results.
+    """
+
+    doctype: DocumentType
+    data: Optional[object] = None
+    path_or_url: Optional[str] = ""

autogen/agentchat/contrib/graph_rag/graph_query_engine.py

@@ -0,0 +1,51 @@
+from dataclasses import dataclass, field
+from typing import List, Optional, Protocol
+
+from .document import Document
+
+
+@dataclass
+class GraphStoreQueryResult:
+    """
+    A wrapper of graph store query results.
+
+    answer: human readable answer to question/query.
+    results: intermediate results to question/query, e.g. node entities.
+    """
+
+    answer: Optional[str] = None
+    results: list = field(default_factory=list)
+
+
+class GraphQueryEngine(Protocol):
+    """An abstract base class that represents a graph query engine on top of a underlying graph database.
+
+    This interface defines the basic methods for graph rag.
+    """
+
+    def init_db(self, input_doc: List[Document] | None = None):
+        """
+        This method initializes graph database with the input documents or records.
+        Usually, it takes the following steps,
+        1. connecting to a graph database.
+        2. extract graph nodes, edges based on input data, graph schema and etc.
+        3. build indexes etc.
+
+        Args:
+        input_doc: a list of input documents that are used to build the graph in database.
+
+        Returns: GraphStore
+        """
+        pass
+
+    def add_records(self, new_records: List) -> bool:
+        """
+        Add new records to the underlying database and add to the graph if required.
+        """
+        pass
+
+    def query(self, question: str, n_results: int = 1, **kwargs) -> GraphStoreQueryResult:
+        """
+        This method transform a string format question into database query and return the result.
+        """
+        pass

autogen/agentchat/contrib/graph_rag/graph_rag_capability.py

@@ -0,0 +1,56 @@
+from autogen.agentchat.contrib.capabilities.agent_capability import AgentCapability
+from autogen.agentchat.conversable_agent import ConversableAgent
+
+from .graph_query_engine import GraphQueryEngine
+
+
+class GraphRagCapability(AgentCapability):
+    """
+    A graph rag capability uses a graph query engine to give a conversable agent the graph rag ability.
+
+    An agent class with graph rag capability could
+    1. create a graph in the underlying database with input documents.
+    2. retrieved relevant information based on messages received by the agent.
+    3. generate answers from retrieved information and send messages back.
+
+    For example,
+    graph_query_engine = GraphQueryEngine(...)
+    graph_query_engine.init_db([Document(doc1), Document(doc2), ...])
+
+    graph_rag_agent = ConversableAgent(
+        name="graph_rag_agent",
+        max_consecutive_auto_reply=3,
+        ...
+    )
+    graph_rag_capability = GraphRagCapbility(graph_query_engine)
+    graph_rag_capability.add_to_agent(graph_rag_agent)
+
+    user_proxy = UserProxyAgent(
+        name="user_proxy",
+        code_execution_config=False,
+        is_termination_msg=lambda msg: "TERMINATE" in msg["content"],
+        human_input_mode="ALWAYS",
+    )
+    user_proxy.initiate_chat(graph_rag_agent, message="Name a few actors who've played in 'The Matrix'")
+
+    # ChatResult(
+        # chat_id=None,
+        # chat_history=[
+            # {'content': 'Name a few actors who've played in \'The Matrix\'', 'role': 'graph_rag_agent'},
+            # {'content': 'A few actors who have played in The Matrix are:
+            #   - Keanu Reeves
+            #   - Laurence Fishburne
+            #   - Carrie-Anne Moss
+            #   - Hugo Weaving',
+            #   'role': 'user_proxy'},
+        # ...)
+
+    """
+
+    def __init__(self, query_engine: GraphQueryEngine):
+        """
+        initialize graph rag capability with a graph query engine
+        """
+        ...
+
+    def add_to_agent(self, agent: ConversableAgent): ...

autogen/coding/local_commandline_code_executor.py

@@ -221,7 +221,12 @@ def _setup_functions(self) -> None:
             cmd = [py_executable, "-m", "pip", "install"] + required_packages
             try:
                 result = subprocess.run(
-                    cmd, cwd=self._work_dir, capture_output=True, text=True, timeout=float(self._timeout)
+                    cmd,
+                    cwd=self._work_dir,
+                    capture_output=True,
+                    text=True,
+                    timeout=float(self._timeout),
+                    encoding="utf-8",
                 )
             except subprocess.TimeoutExpired as e:
                 raise ValueError("Pip install timed out") from e
@@ -303,7 +308,13 @@ def _execute_code_dont_check_setup(self, code_blocks: List[CodeBlock]) -> Comman
 
             try:
                 result = subprocess.run(
-                    cmd, cwd=self._work_dir, capture_output=True, text=True, timeout=float(self._timeout), env=env
+                    cmd,
+                    cwd=self._work_dir,
+                    capture_output=True,
+                    text=True,
+                    timeout=float(self._timeout),
+                    env=env,
+                    encoding="utf-8",
                 )
             except subprocess.TimeoutExpired:
                 logs_all += "\n" + TIMEOUT_MSG

autogen/oai/anthropic.py

@@ -314,7 +314,7 @@ def oai_messages_to_anthropic_messages(params: Dict[str, Any]) -> list[dict[str,
     last_tool_result_index = -1
     for message in params["messages"]:
         if message["role"] == "system":
-            params["system"] = message["content"]
+            params["system"] = params.get("system", "") + (" " if "system" in params else "") + message["content"]
         else:
             # New messages will be added here, manage role alternations
             expected_role = "user" if len(processed_messages) % 2 == 0 else "assistant"

dotnet/eng/MetaInfo.props

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="utf-8"?>
 <Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
     <PropertyGroup>
-        <VersionPrefix>0.1.0</VersionPrefix>
+        <VersionPrefix>0.2.0</VersionPrefix>
         <Authors>AutoGen</Authors>
         <PackageProjectUrl>https://microsoft.github.io/autogen-for-net/</PackageProjectUrl>
         <RepositoryUrl>https://github.com/microsoft/autogen</RepositoryUrl>

dotnet/sample/AutoGen.OpenAI.Sample/Structural_Output.cs

@@ -9,11 +9,10 @@
 using Json.Schema;
 using Json.Schema.Generation;
 using OpenAI;
-using OpenAI.Chat;
 
 namespace AutoGen.OpenAI.Sample;
 
-internal class Structural_Output
+public class Structural_Output
 {
     public static async Task RunAsync()
     {
@@ -23,24 +22,25 @@ public static async Task RunAsync()
 
         var schemaBuilder = new JsonSchemaBuilder().FromType<Person>();
         var schema = schemaBuilder.Build();
-
-        var personSchemaFormat = ChatResponseFormat.CreateJsonSchemaFormat(
-            name: "Person",
-            jsonSchema: BinaryData.FromObjectAsJson(schema),
-            description: "Person schema");
-
         var openAIClient = new OpenAIClient(apiKey);
         var openAIClientAgent = new OpenAIChatAgent(
             chatClient: openAIClient.GetChatClient(model),
             name: "assistant",
-            systemMessage: "You are a helpful assistant",
-            responseFormat: personSchemaFormat) // structural output by passing schema to response format
+            systemMessage: "You are a helpful assistant")
             .RegisterMessageConnector()
             .RegisterPrintMessage();
         #endregion create_agent
 
         #region chat_with_agent
-        var reply = await openAIClientAgent.SendAsync("My name is John, I am 25 years old, and I live in Seattle. I like to play soccer and read books.");
+        var prompt = new TextMessage(Role.User, """
+            My name is John, I am 25 years old, and I live in Seattle. I like to play soccer and read books.
+            """);
+        var reply = await openAIClientAgent.GenerateReplyAsync(
+            messages: [prompt],
+            options: new GenerateReplyOptions
+            {
+                OutputSchema = schema,
+            });
 
         var person = JsonSerializer.Deserialize<Person>(reply.GetContent());
         Console.WriteLine($"Name: {person.Name}");
@@ -60,31 +60,34 @@ public static async Task RunAsync()
         person.City.Should().Be("Seattle");
         person.Hobbies.Count.Should().Be(2);
     }
-}
 
-#region person_class
-public class Person
-{
-    [JsonPropertyName("name")]
-    [Description("Name of the person")]
-    [Required]
-    public string Name { get; set; }
-
-    [JsonPropertyName("age")]
-    [Description("Age of the person")]
-    [Required]
-    public int Age { get; set; }
-
-    [JsonPropertyName("city")]
-    [Description("City of the person")]
-    public string? City { get; set; }
-
-    [JsonPropertyName("address")]
-    [Description("Address of the person")]
-    public string? Address { get; set; }
-
-    [JsonPropertyName("hobbies")]
-    [Description("Hobbies of the person")]
-    public List<string>? Hobbies { get; set; }
+
+    #region person_class
+    [Title("Person")]
+    public class Person
+    {
+        [JsonPropertyName("name")]
+        [Description("Name of the person")]
+        [Required]
+        public string Name { get; set; }
+
+        [JsonPropertyName("age")]
+        [Description("Age of the person")]
+        [Required]
+        public int Age { get; set; }
+
+        [JsonPropertyName("city")]
+        [Description("City of the person")]
+        public string? City { get; set; }
+
+        [JsonPropertyName("address")]
+        [Description("Address of the person")]
+        public string? Address { get; set; }
+
+        [JsonPropertyName("hobbies")]
+        [Description("Hobbies of the person")]
+        public List<string>? Hobbies { get; set; }
+    }
+    #endregion person_class
+
 }
-#endregion person_class

dotnet/sample/AutoGen.OpenAI.Sample/Use_Json_Mode.cs

@@ -4,13 +4,12 @@
 using System.Text.Json;
 using System.Text.Json.Serialization;
 using AutoGen.Core;
-using AutoGen.OpenAI;
 using AutoGen.OpenAI.Extension;
 using FluentAssertions;
 using OpenAI;
 using OpenAI.Chat;
 
-namespace AutoGen.BasicSample;
+namespace AutoGen.OpenAI.Sample;
 
 public class Use_Json_Mode
 {
@@ -50,18 +49,20 @@ public static async Task RunAsync()
         person.Age.Should().Be(25);
         person.Address.Should().BeNullOrEmpty();
     }
-}
 
-#region person_class
-public class Person
-{
-    [JsonPropertyName("name")]
-    public string Name { get; set; }
 
-    [JsonPropertyName("age")]
-    public int Age { get; set; }
+    #region person_class
+    public class Person
+    {
+        [JsonPropertyName("name")]
+        public string Name { get; set; }
+
+        [JsonPropertyName("age")]
+        public int Age { get; set; }
 
-    [JsonPropertyName("address")]
-    public string Address { get; set; }
+        [JsonPropertyName("address")]
+        public string Address { get; set; }
+    }
+    #endregion person_class
 }
-#endregion person_class
+

dotnet/src/AutoGen.Core/Agent/IAgent.cs

@@ -5,6 +5,7 @@
 using System.Linq;
 using System.Threading;
 using System.Threading.Tasks;
+using Json.Schema;
 
 namespace AutoGen.Core;
 
@@ -42,6 +43,7 @@ public GenerateReplyOptions(GenerateReplyOptions other)
         this.MaxToken = other.MaxToken;
         this.StopSequence = other.StopSequence?.Select(s => s)?.ToArray();
         this.Functions = other.Functions?.Select(f => f)?.ToArray();
+        this.OutputSchema = other.OutputSchema;
     }
 
     public float? Temperature { get; set; }
@@ -51,4 +53,9 @@ public GenerateReplyOptions(GenerateReplyOptions other)
     public string[]? StopSequence { get; set; }
 
     public FunctionContract[]? Functions { get; set; }
+
+    /// <summary>
+    /// Structural schema for the output. This property only applies to certain LLMs.
+    /// </summary>
+    public JsonSchema? OutputSchema { get; set; }
 }

dotnet/src/AutoGen.OpenAI.V1/Middleware/OpenAIChatRequestMessageConnector.cs

@@ -335,7 +335,10 @@ private IEnumerable<ChatRequestMessage> ProcessToolCallMessage(IAgent agent, Too
 
         var toolCall = message.ToolCalls.Select((tc, i) => new ChatCompletionsFunctionToolCall(tc.ToolCallId ?? $"{tc.FunctionName}_{i}", tc.FunctionName, tc.FunctionArguments));
         var textContent = message.GetContent() ?? string.Empty;
-        var chatRequestMessage = new ChatRequestAssistantMessage(textContent) { Name = message.From };
+
+        // don't include the name field when it's tool call message.
+        // fix https://github.com/microsoft/autogen/issues/3437
+        var chatRequestMessage = new ChatRequestAssistantMessage(textContent);
         foreach (var tc in toolCall)
         {
             chatRequestMessage.ToolCalls.Add(tc);