Merge remote-tracking branch 'origin/main' into geminitoolcalling

Signed-off-by: Mark Sze <[email protected]>

.github/workflows/contrib-graph-rag-tests.yml

@@ -64,3 +64,49 @@ jobs:
         with:
           file: ./coverage.xml
           flags: unittests
+
+  GraphRagIntegrationTest-Neo4j-Llmaindex-Ubuntu:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.11"]
+    services:
+      neo4j:
+        image: neo4j:latest
+        ports:
+          - 7687:7687
+          - 7474:7474
+        env:
+          NEO4J_AUTH: neo4j/password
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install packages and dependencies for all tests
+        run: |
+          python -m pip install --upgrade pip wheel
+          pip install pytest
+      - name: Install Neo4j and Llama-index when on linux
+        run: |
+          pip install -e .[neo4j_graph_rag]
+      - name: Set AUTOGEN_USE_DOCKER based on OS
+        shell: bash
+        run: |
+          echo "AUTOGEN_USE_DOCKER=False" >> $GITHUB_ENV
+      - name: Coverage
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          OAI_CONFIG_LIST: ${{ secrets.OAI_CONFIG_LIST }}
+        run: |
+          pip install pytest-cov>=5
+          pytest test/agentchat/contrib/graph_rag/test_neo4j_graph_rag.py --skip-openai
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v3
+        with:
+          file: ./coverage.xml
+          flags: unittests

.github/workflows/python-package.yml

@@ -43,11 +43,21 @@ jobs:
       # - name: Conda list
       #   shell: pwsh
       #   run: conda list
-      - name: Build autogen
+      - name: Build pyautogen
         shell: pwsh
         run: |
           pip install twine
-          python setup.py sdist bdist_wheel --name "autogen"
+          python setup.py sdist bdist_wheel
+      - name: Publish pyautogen to PyPI
+        env:
+          TWINE_USERNAME: ${{ secrets.PYAUTOGEN_PYPI_USERNAME }}
+          TWINE_PASSWORD: ${{ secrets.PYAUTOGEN_PYPI_PASSWORD }}
+        shell: pwsh
+        run: twine upload dist/*pyautogen*
+      - name: Build autogen
+        shell: pwsh
+        run: |
+          python setup_autogen.py sdist bdist_wheel
       - name: Publish autogen to PyPI
         env:
           TWINE_USERNAME: ${{ secrets.AUTOGEN_PYPI_USERNAME }}
@@ -57,21 +67,10 @@ jobs:
       - name: Build ag2
         shell: pwsh
         run: |
-          pip install twine
-          python setup.py sdist bdist_wheel --name "ag2"
+          python setup_ag2.py sdist bdist_wheel
       - name: Publish ag2 to PyPI
         env:
           TWINE_USERNAME: ${{ secrets.AUTOGEN_PYPI_USERNAME }}
           TWINE_PASSWORD: ${{ secrets.AUTOGEN_PYPI_PASSWORD }}
         shell: pwsh
         run: twine upload dist/ag2*
-      - name: Build pyautogen
-        shell: pwsh
-        run: |
-          python setup.py sdist bdist_wheel --name "pyautogen"
-      - name: Publish pyautogen to PyPI
-        env:
-          TWINE_USERNAME: ${{ secrets.PYAUTOGEN_PYPI_USERNAME }}
-          TWINE_PASSWORD: ${{ secrets.PYAUTOGEN_PYPI_PASSWORD }}
-        shell: pwsh
-        run: twine upload dist/*pyautogen*

.pre-commit-config.yaml

@@ -47,7 +47,10 @@ repos:
               website/docs/tutorial/code-executors.ipynb |
               website/docs/topics/code-execution/custom-executor.ipynb |
               website/docs/topics/non-openai-models/cloud-gemini.ipynb |
-              notebook/.*
+              notebook/.* |
+              test/agentchat/contrib/graph_rag/trip_planner_data/.* |
+              test/agentchat/contrib/graph_rag/paul_graham_essay.txt
+
             )$
   # See https://jaredkhan.com/blog/mypy-pre-commit
   - repo: local

MAINTAINERS.md

@@ -21,13 +21,15 @@
 | Rudy Wu     | [rudyalways](https://github.com/rudyalways)                | Google                | all, group chats, sequential chats                |
 | Haiyang Li  | [ohdearquant](https://github.com/ohdearquant)               | -               | all, sequential chats, structured output, low-level|
 | Eric Moore  | [emooreatx](https://github.com/emooreatx)               | IBM               | all|
+| Evan David    | [evandavid1](https://github.com/evandavid1)                | -                      | all |
+| Tvrtko Sternak  | [sternakt](https://github.com/sternakt)               | airt.ai               | structured output |
+
 
 **Pending Maintainers list (Marked with \*, Waiting for explicit approval from the maintainers)**
 | Name            | GitHub Handle                                              | Organization           | Features                                |
 |-----------------|------------------------------------------------------------|------------------------|-----------------------------------------|
 | Olaoluwa Ademola Salami * | [olaoluwasalami](https://github.com/olaoluwasalami)  | DevOps Engineer        |                                          |
 | Rajan Chari *    | [rajan-chari](https://github.com/rajan-chari)                | Microsoft Research                | CAP                        |
-| Evan David *    | [evandavid1](https://github.com/evandavid1)                | -                      | gpt assistant, group chat, rag, autobuild |
 
 ## I would like to join this list. How can I help the project?
 > We're always looking for new contributors to join our team and help improve the project. For more information, please refer to our [CONTRIBUTING](https://ag2ai.github.io/ag2/docs/contributor-guide/contributing) guide.

README.md

@@ -25,19 +25,11 @@
 > We invite collaborators from all organizations and individuals to join the development.
 
 
-:fire: :tada: AG2 is available via `ag2` (or its alias  `autogen` or  `pyautogen`)  on PyPI! Starting with version 0.3.2, you can now install AG2 using:
-```
-pip install ag2
-```
-or
+:fire: :tada: AG2 is available via `pyautogen` (or its alias  `autogen` or  `ag2`)  on PyPI!
+
 ```
 pip install pyautogen
 ```
-or
-```
-pip install autogen
-```
-
 
 📄 **License:**
 We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-source collaboration while providing additional protections for contributors and users alike.

autogen/agentchat/contrib/graph_rag/falkor_graph_query_engine.py

@@ -3,9 +3,10 @@
 # SPDX-License-Identifier: Apache-2.0
 
 import os
-from dataclasses import dataclass, field
+import warnings
 from typing import List
 
+from falkordb import FalkorDB, Graph
 from graphrag_sdk import KnowledgeGraph, Source
 from graphrag_sdk.model_config import KnowledgeGraphModelConfig
 from graphrag_sdk.models import GenerativeModel
@@ -35,6 +36,8 @@ def __init__(
         Initialize a FalkorDB knowledge graph.
         Please also refer to https://github.com/FalkorDB/GraphRAG-SDK/blob/main/graphrag_sdk/kg.py
 
+        TODO: Fix LLM API cost calculation for FalkorDB useages.
+
         Args:
             name (str): Knowledge graph name.
             host (str): FalkorDB hostname.
@@ -53,8 +56,38 @@ def __init__(
         self.model = model
         self.model_config = KnowledgeGraphModelConfig.with_model(model)
         self.ontology = ontology
+        self.knowledge_graph = None
+        self.falkordb = FalkorDB(host=self.host, port=self.port, username=self.username, password=self.password)
+
+    def connect_db(self):
+        """
+        Connect to an existing knowledge graph.
+        """
+        if self.name in self.falkordb.list_graphs():
+            try:
+                self.ontology = self._load_ontology_from_db(self.name)
+            except Exception:
+                warnings.warn("Graph Ontology is not loaded.")
+
+            if self.ontology is None:
+                raise ValueError(f"Ontology of the knowledge graph '{self.name}' can't be None.")
+
+            self.knowledge_graph = KnowledgeGraph(
+                name=self.name,
+                host=self.host,
+                port=self.port,
+                username=self.username,
+                password=self.password,
+                model_config=self.model_config,
+                ontology=self.ontology,
+            )
+
+            # Establishing a chat session will maintain the history
+            self._chat_session = self.knowledge_graph.chat_session()
+        else:
+            raise ValueError(f"Knowledge graph '{self.name}' does not exist")
 
-    def init_db(self, input_doc: List[Document] | None):
+    def init_db(self, input_doc: List[Document]):
         """
         Build the knowledge graph with input documents.
         """
@@ -81,10 +114,16 @@ def init_db(self, input_doc: List[Document] | None):
                 ontology=self.ontology,
             )
 
-            # Establish a chat session, this will maintain the history
-            self._chat_session = self.knowledge_graph.chat_session()
             self.knowledge_graph.process_sources(sources)
 
+            # Establishing a chat session will maintain the history
+            self._chat_session = self.knowledge_graph.chat_session()
+
+            # Save Ontology to graph for future access.
+            self._save_ontology_to_db(self.name, self.ontology)
+        else:
+            raise ValueError("No input documents could be loaded.")
+
     def add_records(self, new_records: List) -> bool:
         raise NotImplementedError("This method is not supported by FalkorDB SDK yet.")
 
@@ -101,11 +140,26 @@ def query(self, question: str, n_results: int = 1, **kwargs) -> GraphStoreQueryR
         Returns: FalkorGraphQueryResult
         """
         if self.knowledge_graph is None:
-            raise ValueError("Knowledge graph is not created.")
+            raise ValueError("Knowledge graph has not been selected or created.")
 
         response = self._chat_session.send_message(question)
 
         # History will be considered when querying by setting the last_answer
         self._chat_session.last_answer = response["response"]
 
         return GraphStoreQueryResult(answer=response["response"], results=[])
+
+    def __get_ontology_storage_graph(self, graph_name: str) -> Graph:
+        ontology_table_name = graph_name + "_ontology"
+        return self.falkordb.select_graph(ontology_table_name)
+
+    def _save_ontology_to_db(self, graph_name: str, ontology: Ontology):
+        """
+        Save graph ontology to a separate table with {graph_name}_ontology
+        """
+        graph = self.__get_ontology_storage_graph(graph_name)
+        ontology.save_to_graph(graph)
+
+    def _load_ontology_from_db(self, graph_name: str) -> Ontology:
+        graph = self.__get_ontology_storage_graph(graph_name)
+        return Ontology.from_graph(graph)

autogen/agentchat/contrib/graph_rag/falkor_graph_rag_capability.py

@@ -55,6 +55,8 @@ def _reply_using_falkordb_query(
         Query FalkorDB and return the message. Internally, it utilises OpenAI to generate a reply based on the given messages.
         The history with FalkorDB is also logged and updated.
 
+        The agent's system message will be incorporated into the query, if it's not blank.
+
         If no results are found, a default message is returned: "I'm sorry, I don't have an answer for that."
 
         Args:
@@ -66,16 +68,38 @@ def _reply_using_falkordb_query(
         Returns:
             A tuple containing a boolean indicating success and the assistant's reply.
         """
-        question = self._get_last_question(messages[-1])
+        # question = self._get_last_question(messages[-1])
+        question = self._messages_summary(messages, recipient.system_message)
         result: GraphStoreQueryResult = self.query_engine.query(question)
 
         return True, result.answer if result.answer else "I'm sorry, I don't have an answer for that."
 
-    def _get_last_question(self, message: Union[Dict, str]):
-        """Retrieves the last message from the conversation history."""
-        if isinstance(message, str):
-            return message
-        if isinstance(message, Dict):
-            if "content" in message:
-                return message["content"]
-        return None
+    def _messages_summary(self, messages: Union[Dict, str], system_message: str) -> str:
+        """Summarize the messages in the conversation history. Excluding any message with 'tool_calls' and 'tool_responses'
+        Includes the 'name' (if it exists) and the 'content', with a new line between each one, like:
+        customer:
+        <content>
+
+        agent:
+        <content>
+        """
+
+        if isinstance(messages, str):
+            if system_message:
+                summary = f"IMPORTANT: {system_message}\nContext:\n\n{messages}"
+            else:
+                return messages
+
+        elif isinstance(messages, List):
+            summary = ""
+            for message in messages:
+                if "content" in message and "tool_calls" not in message and "tool_responses" not in message:
+                    summary += f"{message.get('name', '')}: {message.get('content','')}\n\n"
+
+            if system_message:
+                summary = f"IMPORTANT: {system_message}\nContext:\n\n{summary}"
+
+            return summary
+
+        else:
+            raise ValueError("Invalid messages format. Must be a list of messages or a string.")