camel-ai 0.2.13__py3-none-any.whl → 0.2.15__py3-none-any.whl

camel/schemas/outlines_converter.py

@@ -0,0 +1,249 @@
+# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
+
+from typing import Any, Callable, List, Literal, Type, Union
+
+from pydantic import BaseModel
+
+from .base import BaseConverter
+
+
+class OutlinesConverter(BaseConverter):
+    r"""OutlinesConverter is a class that converts a string or a function
+    into a BaseModel schema.
+
+    Args:
+        model_type (str, optional): The model type to be used.
+        platform (str, optional): The platform to be used.
+            1. transformers
+            2. mamba
+            3. vllm
+            4. llamacpp
+            5. mlx
+            (default: "transformers")
+        **kwargs: The keyword arguments to be used. See the outlines
+            documentation for more details. See
+            https://dottxt-ai.github.io/outlines/latest/reference/models/models/
+    """
+
+    def __init__(
+        self,
+        model_type: str,
+        platform: Literal[
+            "vllm", "transformers", "mamba", "llamacpp", "mlx"
+        ] = "transformers",
+        **kwargs: Any,
+    ):
+        self.model_type = model_type
+        from outlines import models
+
+        match platform:
+            case "vllm":
+                self._outlines_model = models.vllm(model_type, **kwargs)
+            case "transformers":
+                self._outlines_model = models.transformers(
+                    model_type, **kwargs
+                )
+            case "mamba":
+                self._outlines_model = models.mamba(model_type, **kwargs)
+            case "llamacpp":
+                self._outlines_model = models.llamacpp(model_type, **kwargs)
+            case "mlx":
+                self._outlines_model = models.mlxlm(model_type, **kwargs)
+            case _:
+                raise ValueError(f"Unsupported platform: {platform}")
+
+    def convert_regex(self, content: str, regex_pattern: str) -> str:
+        r"""Convert the content to the specified regex pattern.
+
+        Args:
+            content (str): The content to be converted.
+            regex_pattern (str): The regex pattern to be used.
+
+        Returns:
+            str: The converted content.
+        """
+        import outlines
+
+        regex_generator = outlines.generate.regex(
+            self._outlines_model, regex_pattern
+        )
+        return regex_generator(content)
+
+    def convert_json(
+        self,
+        content: str,
+        output_schema: Union[str, Callable],
+    ) -> dict:
+        r"""Convert the content to the specified JSON schema given by
+        output_schema.
+
+        Args:
+            content (str): The content to be converted.
+            output_schema (Union[str, Callable]): The expected format of the
+                response.
+
+        Returns:
+            dict: The converted content in JSON format.
+        """
+        import outlines
+
+        json_generator = outlines.generate.json(
+            self._outlines_model, output_schema
+        )
+        return json_generator(content)
+
+    def convert_pydantic(
+        self,
+        content: str,
+        output_schema: Type[BaseModel],
+    ) -> BaseModel:
+        r"""Convert the content to the specified Pydantic schema.
+
+        Args:
+            content (str): The content to be converted.
+            output_schema (Type[BaseModel]): The expected format of the
+                response.
+
+        Returns:
+            BaseModel: The converted content in pydantic model format.
+        """
+        import outlines
+
+        json_generator = outlines.generate.json(
+            self._outlines_model, output_schema
+        )
+        return json_generator(content)
+
+    def convert_type(self, content: str, type_name: type) -> str:
+        r"""Convert the content to the specified type.
+
+        The following types are currently available:
+            1. int
+            2. float
+            3. bool
+            4. datetime.date
+            5. datetime.time
+            6. datetime.datetime
+            7. custom types (https://dottxt-ai.github.io/outlines/latest/reference/generation/types/)
+
+        Args:
+            content (str): The content to be converted.
+            type_name (type): The type to be used.
+
+        Returns:
+            str: The converted content.
+        """
+        import outlines
+
+        type_generator = outlines.generate.format(
+            self._outlines_model, type_name
+        )
+        return type_generator(content)
+
+    def convert_choice(self, content: str, choices: List[str]) -> str:
+        r"""Convert the content to the specified choice.
+
+        Args:
+            content (str): The content to be converted.
+            choices (List[str]): The choices to be used.
+
+        Returns:
+            str: The converted content.
+        """
+        import outlines
+
+        choices_generator = outlines.generate.choice(
+            self._outlines_model, choices
+        )
+        return choices_generator(content)
+
+    def convert_grammar(self, content: str, grammar: str) -> str:
+        r"""Convert the content to the specified grammar.
+
+        Args:
+            content (str): The content to be converted.
+            grammar (str): The grammar to be used.
+
+        Returns:
+            str: The converted content.
+        """
+        import outlines
+
+        grammar_generator = outlines.generate.cfg(
+            self._outlines_model, grammar
+        )
+        return grammar_generator(content)
+
+    def convert(  # type: ignore[override]
+        self,
+        content: str,
+        type: Literal["regex", "json", "type", "choice", "grammar"],
+        **kwargs,
+    ) -> Any:
+        r"""Formats the input content into the expected BaseModel.
+
+        Args:
+            type (Literal["regex", "json", "type", "choice", "grammar"]):
+                The type of conversion to perform. Options are:
+                    - "regex": Match the content against a regex pattern.
+                    - "pydantic": Convert the content into a pydantic model.
+                    - "json": Convert the content into a JSON based on a
+                      schema.
+                    - "type": Convert the content into a specified type.
+                    - "choice": Match the content against a list of valid
+                      choices.
+                    - "grammar": Convert the content using a specified grammar.
+            content (str): The content to be formatted.
+            **kwargs: Additional keyword arguments specific to the conversion
+                type.
+
+            - For "regex":
+                regex_pattern (str): The regex pattern to use for matching.
+
+            - For "pydantic":
+                output_schema (Type[BaseModel]): The schema to validate and
+                    format the pydantic model.
+
+            - For "json":
+                output_schema (Union[str, Callable]): The schema to validate
+                    and format the JSON object.
+
+            - For "type":
+                type_name (str): The target type name for the conversion.
+
+            - For "choice":
+                choices (List[str]): A list of valid choices to match against.
+
+            - For "grammar":
+                grammar (str): The grammar definition to use for content
+                    conversion.
+        """
+        match type:
+            case "regex":
+                return self.convert_regex(content, kwargs.get("regex_pattern"))  # type: ignore[arg-type]
+            case "pydantic":
+                return self.convert_pydantic(
+                    content, kwargs.get("output_schema")
+                )  # type: ignore[arg-type]
+            case "json":
+                return self.convert_json(content, kwargs.get("output_schema"))  # type: ignore[arg-type]
+            case "type":
+                return self.convert_type(content, kwargs.get("type_name"))  # type: ignore[arg-type]
+            case "choice":
+                return self.convert_choice(content, kwargs.get("choices"))  # type: ignore[arg-type]
+            case "grammar":
+                return self.convert_grammar(content, kwargs.get("grammar"))  # type: ignore[arg-type]
+            case _:
+                raise ValueError("Unsupported output schema type")

camel/societies/role_playing.py

@@ -509,8 +509,8 @@ class RolePlaying:
         # step and once in role play), and the model generates only one
         # response when multi-response support is enabled.
         if (
-            'n' in self.user_agent.model_config_dict.keys()
-            and self.user_agent.model_config_dict['n'] > 1
+            'n' in self.user_agent.model_backend.model_config_dict.keys()
+            and self.user_agent.model_backend.model_config_dict['n'] > 1
         ):
             self.user_agent.record_message(user_msg)
 
@@ -532,8 +532,8 @@ class RolePlaying:
         # step and once in role play), and the model generates only one
         # response when multi-response support is enabled.
         if (
-            'n' in self.assistant_agent.model_config_dict.keys()
-            and self.assistant_agent.model_config_dict['n'] > 1
+            'n' in self.assistant_agent.model_backend.model_config_dict.keys()
+            and self.assistant_agent.model_backend.model_config_dict['n'] > 1
         ):
             self.assistant_agent.record_message(assistant_msg)
 

camel/societies/workforce/workforce.py

@@ -251,7 +251,7 @@ class Workforce(BaseNode):
                 additional_info = "A Workforce node"
             elif isinstance(child, SingleAgentWorker):
                 additional_info = "tools: " + (
-                    ", ".join(child.worker.func_dict.keys())
+                    ", ".join(child.worker.tool_dict.keys())
                 )
             elif isinstance(child, RolePlayingWorker):
                 additional_info = "A Role playing node"
@@ -369,7 +369,7 @@ class Workforce(BaseNode):
             model_config_dict=model_config_dict,
         )
 
-        return ChatAgent(worker_sys_msg, model=model, tools=function_list)
+        return ChatAgent(worker_sys_msg, model=model, tools=function_list)  # type: ignore[arg-type]
 
     async def _get_returned_task(self) -> Task:
         r"""Get the task that's published by this node and just get returned

camel/storages/graph_storages/nebula_graph.py

@@ -12,8 +12,19 @@
 # limitations under the License.
 # ========= Copyright 2023-2024 @ CAMEL-AI.org. All Rights Reserved. =========
 
+import logging
+import re
 import time
-from typing import TYPE_CHECKING, Any, Dict, List, Tuple
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
+
+from camel.storages.graph_storages.base import BaseGraphStorage
+from camel.storages.graph_storages.graph_element import (
+    GraphElement,
+)
+from camel.utils.commons import dependencies_required
+
+logger = logging.getLogger(__name__)
+
 
 if TYPE_CHECKING:
     from nebula3.data.ResultSet import (  # type: ignore[import-untyped]
@@ -24,11 +35,6 @@ if TYPE_CHECKING:
         Session,
     )
 
-from camel.storages.graph_storages.base import BaseGraphStorage
-from camel.storages.graph_storages.graph_element import (
-    GraphElement,
-)
-from camel.utils.commons import dependencies_required
 
 MAX_RETRIES = 5
 RETRY_DELAY = 3
@@ -178,55 +184,81 @@ class NebulaGraph(BaseGraphStorage):
         """
         nodes = self._extract_nodes(graph_elements)
         for node in nodes:
-            self.add_node(node['id'], node['type'])
+            try:
+                self.add_node(node['id'], node['type'])
+            except Exception as e:
+                logger.warning(f"Failed to add node {node}. Error: {e}")
+                continue
 
         relationships = self._extract_relationships(graph_elements)
         for rel in relationships:
-            self.add_triplet(rel['subj']['id'], rel['obj']['id'], rel['type'])
+            try:
+                self.add_triplet(
+                    rel['subj']['id'], rel['obj']['id'], rel['type']
+                )
+            except Exception as e:
+                logger.warning(f"Failed to add relationship {rel}. Error: {e}")
+                continue
 
     def ensure_edge_type_exists(
         self,
         edge_type: str,
+        time_label: Optional[str] = None,
     ) -> None:
         r"""Ensures that a specified edge type exists in the NebulaGraph
         database. If the edge type already exists, this method does nothing.
 
         Args:
             edge_type (str): The name of the edge type to be created.
+            time_label (str, optional): A specific timestamp to set as the
+                default value for the time label property. If not
+                provided, no timestamp will be added. (default: :obj:`None`)
 
         Raises:
             Exception: If the edge type creation fails after multiple retry
                 attempts, an exception is raised with the error message.
         """
-        create_edge_stmt = f'CREATE EDGE IF NOT EXISTS {edge_type}()'
+        create_edge_stmt = f"CREATE EDGE IF NOT EXISTS {edge_type} ()"
+        if time_label is not None:
+            time_label = self._validate_time_label(time_label)
+            create_edge_stmt = f"""CREATE EDGE IF NOT EXISTS {edge_type}
+            (time_label DATETIME DEFAULT {time_label})"""
 
         for attempt in range(MAX_RETRIES):
             res = self.query(create_edge_stmt)
             if res.is_succeeded():
-                return  # Tag creation succeeded, exit the method
+                return  # Edge type creation succeeded
 
             if attempt < MAX_RETRIES - 1:
                 time.sleep(RETRY_DELAY)
             else:
                 # Final attempt failed, raise an exception
                 raise Exception(
-                    f"Failed to create tag `{edge_type}` after "
+                    f"Failed to create edge type `{edge_type}` after "
                     f"{MAX_RETRIES} attempts: {res.error_msg()}"
                 )
 
-    def ensure_tag_exists(self, tag_name: str) -> None:
+    def ensure_tag_exists(
+        self, tag_name: str, time_label: Optional[str] = None
+    ) -> None:
         r"""Ensures a tag is created in the NebulaGraph database. If the tag
         already exists, it does nothing.
 
         Args:
             tag_name (str): The name of the tag to be created.
+            time_label (str, optional): A specific timestamp to set as the
+                default value for the time label property. If not provided,
+                no timestamp will be added. (default: :obj:`None`)
 
         Raises:
             Exception: If the tag creation fails after retries, an exception
                 is raised with the error message.
         """
-
-        create_tag_stmt = f'CREATE TAG IF NOT EXISTS {tag_name}()'
+        create_tag_stmt = f"CREATE TAG IF NOT EXISTS {tag_name} ()"
+        if time_label is not None:
+            time_label = self._validate_time_label(time_label)
+            create_tag_stmt = f"""CREATE TAG IF NOT EXISTS {tag_name}
+            (time_label DATETIME DEFAULT {time_label})"""
 
         for attempt in range(MAX_RETRIES):
             res = self.query(create_tag_stmt)
@@ -246,24 +278,39 @@ class NebulaGraph(BaseGraphStorage):
         self,
         node_id: str,
         tag_name: str,
+        time_label: Optional[str] = None,
     ) -> None:
         r"""Add a node with the specified tag and properties.
 
         Args:
             node_id (str): The ID of the node.
             tag_name (str): The tag name of the node.
+            time_label (str, optional): A specific timestamp to set for
+                the node's time label property. If not provided, no timestamp
+                will be added. (default: :obj:`None`)
         """
-        self.ensure_tag_exists(tag_name)
+        node_id = re.sub(r'[^a-zA-Z0-9\u4e00-\u9fa5]', '', node_id)
+        tag_name = re.sub(r'[^a-zA-Z0-9\u4e00-\u9fa5]', '', tag_name)
 
-        # Insert node without properties
-        insert_stmt = (
-            f'INSERT VERTEX IF NOT EXISTS {tag_name}() VALUES "{node_id}":()'
-        )
+        self.ensure_tag_exists(tag_name, time_label)
+
+        # Insert node with or without time_label property
+        if time_label is not None:
+            time_label = self._validate_time_label(time_label)
+            insert_stmt = (
+                f'INSERT VERTEX IF NOT EXISTS {tag_name}(time_label) VALUES '
+                f'"{node_id}":("{time_label}")'
+            )
+        else:
+            insert_stmt = (
+                f'INSERT VERTEX IF NOT EXISTS {tag_name}() VALUES '
+                f'"{node_id}":()'
+            )
 
         for attempt in range(MAX_RETRIES):
             res = self.query(insert_stmt)
             if res.is_succeeded():
-                return  # Tag creation succeeded, exit the method
+                return  # Node creation succeeded, exit the method
 
             if attempt < MAX_RETRIES - 1:
                 time.sleep(RETRY_DELAY)
@@ -329,7 +376,7 @@ class NebulaGraph(BaseGraphStorage):
     @property
     def get_structured_schema(self) -> Dict[str, Any]:
         r"""Generates a structured schema consisting of node and relationship
-        properties, relationships, and metadata.
+        properties, relationships, and metadata, including timestamps.
 
         Returns:
             Dict[str, Any]: A dictionary representing the structured schema.
@@ -400,6 +447,7 @@ class NebulaGraph(BaseGraphStorage):
         subj: str,
         obj: str,
         rel: str,
+        time_label: Optional[str] = None,
     ) -> None:
         r"""Adds a relationship (triplet) between two entities in the Nebula
         Graph database.
@@ -408,24 +456,44 @@ class NebulaGraph(BaseGraphStorage):
             subj (str): The identifier for the subject entity.
             obj (str): The identifier for the object entity.
             rel (str): The relationship between the subject and object.
+            time_label (str, optional): A specific timestamp to set for the
+                time label property of the relationship. If not provided,
+                no timestamp will be added. (default: :obj:`None`)
+
+        Raises:
+            ValueError: If the time_label format is invalid.
+            Exception: If creating the relationship fails.
         """
+        subj = re.sub(r'[^a-zA-Z0-9\u4e00-\u9fa5]', '', subj)
+        obj = re.sub(r'[^a-zA-Z0-9\u4e00-\u9fa5]', '', obj)
+        rel = re.sub(r'[^a-zA-Z0-9\u4e00-\u9fa5]', '', rel)
+
         self.ensure_tag_exists(subj)
         self.ensure_tag_exists(obj)
-        self.ensure_edge_type_exists(rel)
+        self.ensure_edge_type_exists(rel, time_label)
         self.add_node(node_id=subj, tag_name=subj)
         self.add_node(node_id=obj, tag_name=obj)
 
-        # Avoid latenicy
+        # Avoid latency
         time.sleep(1)
 
-        insert_stmt = (
-            f'INSERT EDGE IF NOT EXISTS {rel}() VALUES "{subj}"->"{obj}":();'
-        )
+        # Create edge with or without time_label property
+        if time_label is not None:
+            time_label = self._validate_time_label(time_label)
+            insert_stmt = (
+                f'INSERT EDGE IF NOT EXISTS {rel}(time_label) VALUES '
+                f'"{subj}"->"{obj}":("{time_label}")'
+            )
+        else:
+            insert_stmt = (
+                f'INSERT EDGE IF NOT EXISTS {rel}() VALUES '
+                f'"{subj}"->"{obj}":()'
+            )
 
         res = self.query(insert_stmt)
         if not res.is_succeeded():
             raise Exception(
-                f'create relationship `]{subj}` -> `{obj}`'
+                f'create relationship `{subj}` -> `{obj}`'
                 + f'failed: {res.error_msg()}'
             )
 
@@ -545,3 +613,27 @@ class NebulaGraph(BaseGraphStorage):
             )
 
         return rel_schema_props, rel_structure_props
+
+    def _validate_time_label(self, time_label: str) -> str:
+        r"""Validates the format of a time label string.
+
+        Args:
+            time_label (str): The time label string to validate.
+                Should be in format 'YYYY-MM-DDThh:mm:ss'.
+
+        Returns:
+            str: The validated time label.
+
+        Raises:
+            ValueError: If the time label format is invalid.
+        """
+        try:
+            # Check if the format matches YYYY-MM-DDThh:mm:ss
+            pattern = r'^\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}$'
+            if not re.match(pattern, time_label):
+                raise ValueError(
+                    "Time label must be in format 'YYYY-MM-DDThh:mm:ss'"
+                )
+            return time_label
+        except Exception as e:
+            raise ValueError(f"Invalid time label format: {e!s}")