camel-ai 0.1.6.4__tar.gz → 0.1.6.6__tar.gz

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: camel-ai
-Version: 0.1.6.4
+Version: 0.1.6.6
 Summary: Communicative Agents for AI Society Study
 Home-page: https://www.camel-ai.org/
 License: Apache-2.0
@@ -202,7 +202,7 @@ conda create --name camel python=3.9
 conda activate camel
 
 # Clone github repo
-git clone -b v0.1.6.4 https://github.com/camel-ai/camel.git
+git clone -b v0.1.6.6 https://github.com/camel-ai/camel.git
 
 # Change directory into project directory
 cd camel

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/README.md

@@ -110,7 +110,7 @@ conda create --name camel python=3.9
 conda activate camel
 
 # Clone github repo
-git clone -b v0.1.6.4 https://github.com/camel-ai/camel.git
+git clone -b v0.1.6.6 https://github.com/camel-ai/camel.git
 
 # Change directory into project directory
 cd camel

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/__init__.py

@@ -12,7 +12,7 @@
 # limitations under the License.
 # =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
 
-__version__ = '0.1.6.4'
+__version__ = '0.1.6.6'
 
 __all__ = [
     '__version__',

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/configs/gemini_config.py

@@ -81,7 +81,6 @@ class GeminiConfig(BaseConfig):
     response_mime_type: Optional[str] = None
     response_schema: Optional[Any] = None
     safety_settings: Optional[Any] = None
-    tools: Optional[Any] = None
     tool_config: Optional[Any] = None
     request_options: Optional[Any] = None
 

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/configs/groq_config.py

@@ -99,7 +99,7 @@ class GroqConfig(BaseConfig):
     response_format: Union[dict, NotGiven] = NOT_GIVEN
     frequency_penalty: float = 0.0
     user: str = ""
-    tool_choice: Optional[Union[dict[str, str], str]] = "none"
+    tool_choice: Optional[Union[dict[str, str], str]] = "auto"
 
 
 GROQ_API_PARAMS = {param for param in GroqConfig.model_fields.keys()}

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/configs/mistral_config.py

@@ -74,7 +74,7 @@ class MistralConfig(BaseConfig):
             if not isinstance(response_format, ResponseFormat):
                 raise ValueError(
                     f"The tool {response_format} should be an instance "
-                    "of `mistralai.models.chat_completion.ResponseFormat`."
+                    "of `mistralai.models.ResponseFormat`."
                 )
         return response_format
 

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/loaders/unstructured_io.py

@@ -12,6 +12,7 @@
 # limitations under the License.
 # =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
 import uuid
+import warnings
 from typing import (
     Any,
     Dict,
@@ -91,7 +92,7 @@ class UnstructuredIO:
     def parse_file_or_url(
         input_path: str,
         **kwargs: Any,
-    ) -> List[Element]:
+    ) -> Union[List[Element], None]:
         r"""Loads a file or a URL and parses its contents into elements.
 
         Args:
@@ -99,12 +100,12 @@ class UnstructuredIO:
             **kwargs: Extra kwargs passed to the partition function.
 
         Returns:
-            List[Element]: List of elements after parsing the file or URL.
+            Union[List[Element],None]: List of elements after parsing the file
+                or URL if success.
 
         Raises:
             FileNotFoundError: If the file does not exist at the path
                 specified.
-            Exception: For any other issues during file or URL parsing.
 
         Notes:
             Available document types:
@@ -128,8 +129,9 @@ class UnstructuredIO:
             try:
                 elements = partition_html(url=input_path, **kwargs)
                 return elements
-            except Exception as e:
-                raise Exception("Failed to parse the URL.") from e
+            except Exception:
+                warnings.warn(f"Failed to parse the URL: {input_path}")
+                return None
 
         else:
             # Handling file
@@ -146,10 +148,9 @@ class UnstructuredIO:
                 with open(input_path, "rb") as f:
                     elements = partition(file=f, **kwargs)
                     return elements
-            except Exception as e:
-                raise Exception(
-                    "Failed to parse the unstructured file."
-                ) from e
+            except Exception:
+                warnings.warn(f"Failed to partition the file: {input_path}")
+                return None
 
     @staticmethod
     def clean_text_data(

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/models/openai_compatibility_model.py

@@ -103,3 +103,19 @@ class OpenAICompatibilityModel:
             bool: Whether the model is in stream mode.
         """
         return self.model_config_dict.get('stream', False)
+
+    @property
+    def token_limit(self) -> int:
+        r"""Returns the maximum token limit for the given model.
+
+        Returns:
+            int: The maximum token limit for the given model.
+        """
+        max_tokens = self.model_config_dict.get("max_tokens")
+        if isinstance(max_tokens, int):
+            return max_tokens
+        print(
+            "Must set `max_tokens` as an integer in `model_config_dict` when"
+            " setting up the model. Using 4096 as default value."
+        )
+        return 4096

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/retrievers/auto_retriever.py

@@ -15,7 +15,7 @@ import datetime
 import os
 import re
 from pathlib import Path
-from typing import List, Optional, Tuple, Union
+from typing import Collection, List, Optional, Sequence, Tuple, Union
 from urllib.parse import urlparse
 
 from camel.embeddings import BaseEmbedding, OpenAIEmbedding
@@ -28,6 +28,11 @@ from camel.storages import (
 )
 from camel.types import StorageType
 
+try:
+    from unstructured.documents.elements import Element
+except ImportError:
+    Element = None
+
 DEFAULT_TOP_K_RESULTS = 1
 DEFAULT_SIMILARITY_THRESHOLD = 0.75
 
@@ -97,15 +102,19 @@ class AutoRetriever:
             f"Unsupported vector storage type: {self.storage_type}"
         )
 
-    def _collection_name_generator(self, content: str) -> str:
+    def _collection_name_generator(self, content: Union[str, Element]) -> str:
         r"""Generates a valid collection name from a given file path or URL.
 
         Args:
-            contents (str): Local file path, remote URL or string content.
+            content (Union[str, Element]): Local file path, remote URL,
+                string content or Element object.
 
         Returns:
             str: A sanitized, valid collection name suitable for use.
         """
+        if isinstance(content, Element):
+            content = content.metadata.file_directory
+
         # Check if the content is URL
         parsed_url = urlparse(content)
         is_url = all([parsed_url.scheme, parsed_url.netloc])
@@ -193,18 +202,18 @@ class AutoRetriever:
     def run_vector_retriever(
         self,
         query: str,
-        contents: Union[str, List[str]],
+        contents: Union[str, List[str], Element, List[Element]],
         top_k: int = DEFAULT_TOP_K_RESULTS,
         similarity_threshold: float = DEFAULT_SIMILARITY_THRESHOLD,
         return_detailed_info: bool = False,
-    ) -> str:
+    ) -> dict[str, Sequence[Collection[str]]]:
         r"""Executes the automatic vector retriever process using vector
         storage.
 
         Args:
             query (str): Query string for information retriever.
-            contents (Union[str, List[str]]): Local file paths, remote URLs or
-                string contents.
+            contents (Union[str, List[str], Element, List[Element]]): Local
+                file paths, remote URLs, string contents or Element objects.
             top_k (int, optional): The number of top results to return during
                 retrieve. Must be a positive integer. Defaults to
                 `DEFAULT_TOP_K_RESULTS`.
@@ -216,9 +225,10 @@ class AutoRetriever:
                 metadata. Defaults to `False`.
 
         Returns:
-            string: By default, returns only the text information. If
-                `return_detailed_info` is `True`, return detailed information
-                including similarity score, content path and metadata.
+            dict[str, Sequence[Collection[str]]]: By default, returns
+                only the text information. If `return_detailed_info` is
+                `True`, return detailed information including similarity
+                score, content path and metadata.
 
         Raises:
             ValueError: If there's an vector storage existing with content
@@ -229,7 +239,9 @@ class AutoRetriever:
         if not contents:
             raise ValueError("content cannot be empty.")
 
-        contents = [contents] if isinstance(contents, str) else contents
+        contents = (
+            [contents] if isinstance(contents, (str, Element)) else contents
+        )
 
         all_retrieved_info = []
         for content in contents:
@@ -245,6 +257,7 @@ class AutoRetriever:
                 file_is_modified = False  # initialize with a default value
                 if (
                     vector_storage_instance.status().vector_count != 0
+                    and isinstance(content, str)
                     and os.path.exists(content)
                 ):
                     # Get original modified date from file
@@ -308,20 +321,17 @@ class AutoRetriever:
         # Select the 'top_k' results
         all_retrieved_info = all_retrieved_info_sorted[:top_k]
 
-        retrieved_infos = "\n".join(str(info) for info in all_retrieved_info)
-        retrieved_infos_text = "\n".join(
-            info['text'] for info in all_retrieved_info if 'text' in info
-        )
+        text_retrieved_info = [item['text'] for item in all_retrieved_info]
 
-        detailed_info = (
-            f"Original Query:\n{{ {query} }}\n"
-            f"Retrieved Context:\n{retrieved_infos}"
-        )
+        detailed_info = {
+            "Original Query": query,
+            "Retrieved Context": all_retrieved_info,
+        }
 
-        text_info = (
-            f"Original Query:\n{{ {query} }}\n"
-            f"Retrieved Context:\n{retrieved_infos_text}"
-        )
+        text_info = {
+            "Original Query": query,
+            "Retrieved Context": text_retrieved_info,
+        }
 
         if return_detailed_info:
             return detailed_info

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/retrievers/bm25_retriever.py

@@ -74,13 +74,16 @@ class BM25Retriever(BaseRetriever):
         elements = self.unstructured_modules.parse_file_or_url(
             content_input_path, **kwargs
         )
-        self.chunks = self.unstructured_modules.chunk_elements(
-            chunk_type=chunk_type, elements=elements
-        )
+        if elements:
+            self.chunks = self.unstructured_modules.chunk_elements(
+                chunk_type=chunk_type, elements=elements
+            )
 
-        # Convert chunks to a list of strings for tokenization
-        tokenized_corpus = [str(chunk).split(" ") for chunk in self.chunks]
-        self.bm25 = BM25Okapi(tokenized_corpus)
+            # Convert chunks to a list of strings for tokenization
+            tokenized_corpus = [str(chunk).split(" ") for chunk in self.chunks]
+            self.bm25 = BM25Okapi(tokenized_corpus)
+        else:
+            self.bm25 = None
 
     def query(
         self,

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/retrievers/vector_retriever.py

@@ -12,7 +12,8 @@
 # limitations under the License.
 # =========== Copyright 2023 @ CAMEL-AI.org. All Rights Reserved. ===========
 import os
-from typing import Any, Dict, List, Optional
+import warnings
+from typing import Any, Dict, List, Optional, Union
 from urllib.parse import urlparse
 
 from camel.embeddings import BaseEmbedding, OpenAIEmbedding
@@ -25,6 +26,11 @@ from camel.storages import (
     VectorRecord,
 )
 
+try:
+    from unstructured.documents.elements import Element
+except ImportError:
+    Element = None
+
 DEFAULT_TOP_K_RESULTS = 1
 DEFAULT_SIMILARITY_THRESHOLD = 0.75
 
@@ -68,7 +74,7 @@ class VectorRetriever(BaseRetriever):
 
     def process(
         self,
-        content: str,
+        content: Union[str, Element],
         chunk_type: str = "chunk_by_title",
         **kwargs: Any,
     ) -> None:
@@ -77,21 +83,31 @@ class VectorRetriever(BaseRetriever):
         vector storage.
 
         Args:
-            contents (str): Local file path, remote URL or string content.
+            content (Union[str, Element]): Local file path, remote URL,
+                string content or Element object.
             chunk_type (str): Type of chunking going to apply. Defaults to
                 "chunk_by_title".
             **kwargs (Any): Additional keyword arguments for content parsing.
         """
-        # Check if the content is URL
-        parsed_url = urlparse(content)
-        is_url = all([parsed_url.scheme, parsed_url.netloc])
-        if is_url or os.path.exists(content):
-            elements = self.uio.parse_file_or_url(content, **kwargs)
+        if isinstance(content, Element):
+            elements = [content]
         else:
-            elements = [self.uio.create_element_from_text(text=content)]
-        chunks = self.uio.chunk_elements(
-            chunk_type=chunk_type, elements=elements
-        )
+            # Check if the content is URL
+            parsed_url = urlparse(content)
+            is_url = all([parsed_url.scheme, parsed_url.netloc])
+            if is_url or os.path.exists(content):
+                elements = self.uio.parse_file_or_url(content, **kwargs) or []
+            else:
+                elements = [self.uio.create_element_from_text(text=content)]
+        if elements:
+            chunks = self.uio.chunk_elements(
+                chunk_type=chunk_type, elements=elements
+            )
+        if not elements:
+            warnings.warn(
+                f"No elements were extracted from the content: {content}"
+            )
+            return
         # Iterate to process and store embeddings, set batch of 50
         for i in range(0, len(chunks), 50):
             batch_chunks = chunks[i : i + 50]
@@ -103,7 +119,12 @@ class VectorRetriever(BaseRetriever):
             # Prepare the payload for each vector record, includes the content
             # path, chunk metadata, and chunk text
             for vector, chunk in zip(batch_vectors, batch_chunks):
-                content_path_info = {"content path": content}
+                if isinstance(content, str):
+                    content_path_info = {"content path": content}
+                elif isinstance(content, Element):
+                    content_path_info = {
+                        "content path": content.metadata.file_directory
+                    }
                 chunk_metadata = {"metadata": chunk.metadata.to_dict()}
                 chunk_text = {"text": str(chunk)}
                 combined_dict = {

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/toolkits/retrieval_toolkit.py

@@ -57,7 +57,7 @@ class RetrievalToolkit(BaseToolkit):
         retrieved_info = auto_retriever.run_vector_retriever(
             query=query, contents=contents, top_k=3
         )
-        return retrieved_info
+        return str(retrieved_info)
 
     def get_tools(self) -> List[OpenAIFunction]:
         r"""Returns a list of OpenAIFunction objects representing the

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/camel/types/enums.py

@@ -26,7 +26,6 @@ class RoleType(Enum):
 class ModelType(Enum):
     GPT_3_5_TURBO = "gpt-3.5-turbo"
     GPT_4 = "gpt-4"
-    GPT_4_32K = "gpt-4-32k"
     GPT_4_TURBO = "gpt-4-turbo"
     GPT_4O = "gpt-4o"
     GPT_4O_MINI = "gpt-4o-mini"
@@ -96,7 +95,6 @@ class ModelType(Enum):
         return self in {
             ModelType.GPT_3_5_TURBO,
             ModelType.GPT_4,
-            ModelType.GPT_4_32K,
             ModelType.GPT_4_TURBO,
             ModelType.GPT_4O,
             ModelType.GPT_4O_MINI,
@@ -110,7 +108,6 @@ class ModelType(Enum):
         return self in {
             ModelType.GPT_3_5_TURBO,
             ModelType.GPT_4,
-            ModelType.GPT_4_32K,
             ModelType.GPT_4_TURBO,
             ModelType.GPT_4O,
         }
@@ -231,7 +228,6 @@ class ModelType(Enum):
         }:
             return 16_384
         elif self in {
-            ModelType.GPT_4_32K,
             ModelType.MISTRAL_CODESTRAL,
             ModelType.MISTRAL_7B,
             ModelType.MISTRAL_MIXTRAL_8x7B,
@@ -440,7 +436,7 @@ class ModelPlatformType(Enum):
     AZURE = "azure"
     ANTHROPIC = "anthropic"
     GROQ = "groq"
-    OPENSOURCE = "opensource"
+    OPEN_SOURCE = "open-source"
     OLLAMA = "ollama"
     LITELLM = "litellm"
     ZHIPU = "zhipuai"
@@ -448,7 +444,7 @@ class ModelPlatformType(Enum):
     GEMINI = "gemini"
     VLLM = "vllm"
     MISTRAL = "mistral"
-    OPENAICOMPATIBILITYMODEL = "openai-compatibility-model"
+    OPENAI_COMPATIBILITY_MODEL = "openai-compatibility-model"
 
     @property
     def is_openai(self) -> bool:
@@ -498,13 +494,13 @@ class ModelPlatformType(Enum):
     @property
     def is_open_source(self) -> bool:
         r"""Returns whether this platform is opensource."""
-        return self is ModelPlatformType.OPENSOURCE
+        return self is ModelPlatformType.OPEN_SOURCE
 
     @property
     def is_openai_compatibility_model(self) -> bool:
         r"""Returns whether this is a platform supporting openai
         compatibility"""
-        return self is ModelPlatformType.OPENAICOMPATIBILITYMODEL
+        return self is ModelPlatformType.OPENAI_COMPATIBILITY_MODEL
 
     @property
     def is_gemini(self) -> bool:

{camel_ai-0.1.6.4 → camel_ai-0.1.6.6}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.poetry]
 name = "camel-ai"
-version = "0.1.6.4"
+version = "0.1.6.6"
 authors = ["CAMEL-AI.org"]
 description = "Communicative Agents for AI Society Study"
 readme = "README.md"