camel-ai 0.2.76a8__tar.gz → 0.2.76a12__tar.gz

{camel_ai-0.2.76a8 → camel_ai-0.2.76a12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: camel-ai
-Version: 0.2.76a8
+Version: 0.2.76a12
 Summary: Communicative Agents for AI Society Study
 Project-URL: Homepage, https://www.camel-ai.org/
 Project-URL: Repository, https://github.com/camel-ai/camel
@@ -20,6 +20,7 @@ Requires-Dist: pillow<11.0.0,>=10.1.0
 Requires-Dist: psutil<6,>=5.9.8
 Requires-Dist: pydantic>=2.10.6
 Requires-Dist: tiktoken<0.8,>=0.7.0
+Requires-Dist: websockets<15.1,>=13.0
 Provides-Extra: all
 Requires-Dist: aci-sdk>=1.0.0b1; extra == 'all'
 Requires-Dist: agentops<0.4,>=0.3.21; extra == 'all'
@@ -235,6 +236,8 @@ Requires-Dist: docx>=0.2.4; extra == 'eigent'
 Requires-Dist: exa-py<2,>=1.10.0; extra == 'eigent'
 Requires-Dist: ffmpeg-python<0.3,>=0.2.0; extra == 'eigent'
 Requires-Dist: google-api-python-client==2.166.0; extra == 'eigent'
+Requires-Dist: google-auth-httplib2==0.2.0; extra == 'eigent'
+Requires-Dist: google-auth-oauthlib==1.2.1; extra == 'eigent'
 Requires-Dist: imageio[pyav]<3,>=2.34.2; extra == 'eigent'
 Requires-Dist: markitdown[all]>=0.1.1; extra == 'eigent'
 Requires-Dist: mcp-server-fetch==2025.1.17; extra == 'eigent'
@@ -612,7 +615,7 @@ We are a community-driven research collective comprising over 100 researchers de
 </div>
 
 <div align="center">
-  <a href="https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_rag.html">
+  <a href="https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_rag">
     <img src="docs/images/rag_pipeline.png" alt="RAG Pipeline">
   </a>
 </div>
@@ -698,10 +701,10 @@ We provide a [![Google Colab](https://colab.research.google.com/assets/colab-bad
 
 Explore different types of agents, their roles, and their applications.
 
-- **[Creating Your First Agent](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agent.html)**
-- **[Creating Your First Agent Society](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agents_society.html)**
-- **[Embodied Agents](https://docs.camel-ai.org/cookbooks/advanced_features/embodied_agents.html)**
-- **[Critic Agents](https://docs.camel-ai.org/cookbooks/advanced_features/critic_agents_and_tree_search.html)**
+- **[Creating Your First Agent](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agent)**
+- **[Creating Your First Agent Society](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agents_society)**
+- **[Embodied Agents](https://docs.camel-ai.org/cookbooks/advanced_features/embodied_agents)**
+- **[Critic Agents](https://docs.camel-ai.org/cookbooks/advanced_features/critic_agents_and_tree_search)**
 
 ### Seeking Help
 
@@ -722,19 +725,19 @@ Core components and utilities to build, operate, and enhance CAMEL-AI agents and
 
 | Module | Description |
 |:---|:---|
-| **[Agents](https://docs.camel-ai.org/key_modules/agents.html)** | Core agent architectures and behaviors for autonomous operation. |
-| **[Agent Societies](https://docs.camel-ai.org/key_modules/society.html)** | Components for building and managing multi-agent systems and collaboration. |
-| **[Data Generation](https://docs.camel-ai.org/key_modules/datagen.html)** | Tools and methods for synthetic data creation and augmentation. |
-| **[Models](https://docs.camel-ai.org/key_modules/models.html)** | Model architectures and customization options for agent intelligence. |
-| **[Tools](https://docs.camel-ai.org/key_modules/tools.html)** | Tools integration for specialized agent tasks. |
-| **[Memory](https://docs.camel-ai.org/key_modules/memory.html)** | Memory storage and retrieval mechanisms for agent state management. |
-| **[Storage](https://docs.camel-ai.org/key_modules/storages.html)** | Persistent storage solutions for agent data and states. |
+| **[Agents](https://docs.camel-ai.org/key_modules/agents)** | Core agent architectures and behaviors for autonomous operation. |
+| **[Agent Societies](https://docs.camel-ai.org/key_modules/society)** | Components for building and managing multi-agent systems and collaboration. |
+| **[Data Generation](https://docs.camel-ai.org/key_modules/datagen)** | Tools and methods for synthetic data creation and augmentation. |
+| **[Models](https://docs.camel-ai.org/key_modules/models)** | Model architectures and customization options for agent intelligence. |
+| **[Tools](https://docs.camel-ai.org/key_modules/tools)** | Tools integration for specialized agent tasks. |
+| **[Memory](https://docs.camel-ai.org/key_modules/memory)** | Memory storage and retrieval mechanisms for agent state management. |
+| **[Storage](https://docs.camel-ai.org/key_modules/storages)** | Persistent storage solutions for agent data and states. |
 | **[Benchmarks](https://github.com/camel-ai/camel/tree/master/camel/benchmarks)** | Performance evaluation and testing frameworks. |
-| **[Interpreters](https://docs.camel-ai.org/key_modules/interpreters.html)** | Code and command interpretation capabilities. |
-| **[Data Loaders](https://docs.camel-ai.org/key_modules/loaders.html)** | Data ingestion and preprocessing tools. |
-| **[Retrievers](https://docs.camel-ai.org/key_modules/retrievers.html)** | Knowledge retrieval and RAG components. |
+| **[Interpreters](https://docs.camel-ai.org/key_modules/interpreters)** | Code and command interpretation capabilities. |
+| **[Data Loaders](https://docs.camel-ai.org/key_modules/loaders)** | Data ingestion and preprocessing tools. |
+| **[Retrievers](https://docs.camel-ai.org/key_modules/retrievers)** | Knowledge retrieval and RAG components. |
 | **[Runtime](https://github.com/camel-ai/camel/tree/master/camel/runtime)** | Execution environment and process management. |
-| **[Human-in-the-Loop](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_human_in_loop_and_tool_approval.html)** | Interactive components for human oversight and intervention. |
+| **[Human-in-the-Loop](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_human_in_loop_and_tool_approval)** | Interactive components for human oversight and intervention. |
 ---
 
 ## Research
@@ -795,7 +798,7 @@ We believe that studying these agents on a large scale offers valuable insights
 
 ### 1. Utilize Various LLMs as Backends
 
-For more details, please see our [`Models Documentation`](https://docs.camel-ai.org/key_modules/models.html#).
+For more details, please see our [`Models Documentation`](https://docs.camel-ai.org/key_modules/models#).
 
 > **Data (Hosted on Hugging Face)**
 
@@ -824,42 +827,42 @@ Practical guides and tutorials for implementing specific functionalities in CAME
 ### 1. Basic Concepts
 | Cookbook | Description |
 |:---|:---|
-| **[Creating Your First Agent](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agent.html)** | A step-by-step guide to building your first agent. |
-| **[Creating Your First Agent Society](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agents_society.html)** | Learn to build a collaborative society of agents. |
-| **[Message Cookbook](https://docs.camel-ai.org/cookbooks/basic_concepts/agents_message.html)** | Best practices for message handling in agents. |
+| **[Creating Your First Agent](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agent)** | A step-by-step guide to building your first agent. |
+| **[Creating Your First Agent Society](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agents_society)** | Learn to build a collaborative society of agents. |
+| **[Message Cookbook](https://docs.camel-ai.org/cookbooks/basic_concepts/agents_message)** | Best practices for message handling in agents. |
 
 ### 2. Advanced Features
 | Cookbook | Description |
 |:---|:---|
-| **[Tools Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_tools.html)** | Integrating tools for enhanced functionality. |
-| **[Memory Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_memory.html)** | Implementing memory systems in agents. |
-| **[RAG Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_rag.html)** | Recipes for Retrieval-Augmented Generation. |
-| **[Graph RAG Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_graph_rag.html)** | Leveraging knowledge graphs with RAG. |
-| **[Track CAMEL Agents with AgentOps](https://docs.camel-ai.org/cookbooks/advanced_features/agents_tracking.html)** | Tools for tracking and managing agents in operations. |
+| **[Tools Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_tools)** | Integrating tools for enhanced functionality. |
+| **[Memory Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_memory)** | Implementing memory systems in agents. |
+| **[RAG Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_rag)** | Recipes for Retrieval-Augmented Generation. |
+| **[Graph RAG Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_graph_rag)** | Leveraging knowledge graphs with RAG. |
+| **[Track CAMEL Agents with AgentOps](https://docs.camel-ai.org/cookbooks/advanced_features/agents_tracking)** | Tools for tracking and managing agents in operations. |
 
 ### 3. Model Training & Data Generation
 | Cookbook | Description |
 |:---|:---|
-| **[Data Generation with CAMEL and Finetuning with Unsloth](https://docs.camel-ai.org/cookbooks/data_generation/sft_data_generation_and_unsloth_finetuning_Qwen2_5_7B.html)** | Learn how to generate data with CAMEL and fine-tune models effectively with Unsloth. |
-| **[Data Gen with Real Function Calls and Hermes Format](https://docs.camel-ai.org/cookbooks/data_generation/data_gen_with_real_function_calls_and_hermes_format.html)** | Explore how to generate data with real function calls and the Hermes format. |
-| **[CoT Data Generation and Upload Data to Huggingface](https://docs.camel-ai.org/cookbooks/data_generation/distill_math_reasoning_data_from_deepseek_r1.html)** | Uncover how to generate CoT data with CAMEL and seamlessly upload it to Huggingface. |
-| **[CoT Data Generation and SFT Qwen with Unsolth](https://docs.camel-ai.org/cookbooks/data_generation/cot_data_gen_sft_qwen_unsolth_upload_huggingface.html)** | Discover how to generate CoT data using CAMEL and SFT Qwen with Unsolth, and seamlessly upload your data and model to Huggingface. |
+| **[Data Generation with CAMEL and Finetuning with Unsloth](https://docs.camel-ai.org/cookbooks/data_generation/sft_data_generation_and_unsloth_finetuning_Qwen2_5_7B)** | Learn how to generate data with CAMEL and fine-tune models effectively with Unsloth. |
+| **[Data Gen with Real Function Calls and Hermes Format](https://docs.camel-ai.org/cookbooks/data_generation/data_gen_with_real_function_calls_and_hermes_format)** | Explore how to generate data with real function calls and the Hermes format. |
+| **[CoT Data Generation and Upload Data to Huggingface](https://docs.camel-ai.org/cookbooks/data_generation/distill_math_reasoning_data_from_deepseek_r1)** | Uncover how to generate CoT data with CAMEL and seamlessly upload it to Huggingface. |
+| **[CoT Data Generation and SFT Qwen with Unsolth](https://docs.camel-ai.org/cookbooks/data_generation/cot_data_gen_sft_qwen_unsolth_upload_huggingface)** | Discover how to generate CoT data using CAMEL and SFT Qwen with Unsolth, and seamlessly upload your data and model to Huggingface. |
 
 ### 4. Multi-Agent Systems & Applications
 | Cookbook | Description |
 |:---|:---|
-| **[Role-Playing Scraper for Report & Knowledge Graph Generation](https://docs.camel-ai.org/cookbooks/applications/roleplaying_scraper.html)** | Create role-playing agents for data scraping and reporting. |
-| **[Create A Hackathon Judge Committee with Workforce](https://docs.camel-ai.org/cookbooks/multi_agent_society/workforce_judge_committee.html)** | Building a team of agents for collaborative judging. |
-| **[Dynamic Knowledge Graph Role-Playing: Multi-Agent System with dynamic, temporally-aware knowledge graphs](https://docs.camel-ai.org/cookbooks/applications/dyamic_knowledge_graph.html)** |  Builds dynamic, temporally-aware knowledge graphs for financial applications using a multi-agent system. It processes financial reports, news articles, and research papers to help traders analyze data, identify relationships, and uncover market insights. The system also utilizes diverse and optional element node deduplication techniques to ensure data integrity and optimize graph structure for financial decision-making. |
-| **[Customer Service Discord Bot with Agentic RAG](https://docs.camel-ai.org/cookbooks/applications/customer_service_Discord_bot_using_SambaNova_with_agentic_RAG.html)** | Learn how to build a robust customer service bot for Discord using Agentic RAG. |
-| **[Customer Service Discord Bot with Local Model](https://docs.camel-ai.org/cookbooks/applications/customer_service_Discord_bot_using_local_model_with_agentic_RAG.html)** | Learn how to build a robust customer service bot for Discord using Agentic RAG which supports local deployment. |
+| **[Role-Playing Scraper for Report & Knowledge Graph Generation](https://docs.camel-ai.org/cookbooks/applications/roleplaying_scraper)** | Create role-playing agents for data scraping and reporting. |
+| **[Create A Hackathon Judge Committee with Workforce](https://docs.camel-ai.org/cookbooks/multi_agent_society/workforce_judge_committee)** | Building a team of agents for collaborative judging. |
+| **[Dynamic Knowledge Graph Role-Playing: Multi-Agent System with dynamic, temporally-aware knowledge graphs](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_dkg)** |  Builds dynamic, temporally-aware knowledge graphs for financial applications using a multi-agent system. It processes financial reports, news articles, and research papers to help traders analyze data, identify relationships, and uncover market insights. The system also utilizes diverse and optional element node deduplication techniques to ensure data integrity and optimize graph structure for financial decision-making. |
+| **[Customer Service Discord Bot with Agentic RAG](https://docs.camel-ai.org/cookbooks/applications/customer_service_Discord_bot_using_SambaNova_with_agentic_RAG)** | Learn how to build a robust customer service bot for Discord using Agentic RAG. |
+| **[Customer Service Discord Bot with Local Model](https://docs.camel-ai.org/cookbooks/applications/customer_service_Discord_bot_using_local_model_with_agentic_RAG)** | Learn how to build a robust customer service bot for Discord using Agentic RAG which supports local deployment. |
 
 ### 5. Data Processing
 | Cookbook | Description |
 |:---|:---|
-| **[Video Analysis](https://docs.camel-ai.org/cookbooks/data_processing/video_analysis.html)** | Techniques for agents in video data analysis. |
-| **[3 Ways to Ingest Data from Websites with Firecrawl](https://docs.camel-ai.org/cookbooks/data_processing/ingest_data_from_websites_with_Firecrawl.html)** | Explore three methods for extracting and processing data from websites using Firecrawl. |
-| **[Create AI Agents that work with your PDFs](https://docs.camel-ai.org/cookbooks/data_processing/agent_with_chunkr_for_pdf_parsing.html)** | Learn how to create AI agents that work with your PDFs using Chunkr and Mistral AI. |
+| **[Video Analysis](https://docs.camel-ai.org/cookbooks/data_processing/video_analysis)** | Techniques for agents in video data analysis. |
+| **[3 Ways to Ingest Data from Websites with Firecrawl](https://docs.camel-ai.org/cookbooks/data_processing/ingest_data_from_websites_with_Firecrawl)** | Explore three methods for extracting and processing data from websites using Firecrawl. |
+| **[Create AI Agents that work with your PDFs](https://docs.camel-ai.org/cookbooks/data_processing/agent_with_chunkr_for_pdf_parsing)** | Learn how to create AI agents that work with your PDFs using Chunkr and Mistral AI. |
 
 <br>
 
@@ -1000,7 +1003,7 @@ The source code is licensed under Apache 2.0.
 <br>
 
 [docs-image]: https://img.shields.io/badge/Documentation-EB3ECC
-[docs-url]: https://camel-ai.github.io/camel/index.html
+[docs-url]: https://camel-ai.github.io/camel/index
 [star-image]: https://img.shields.io/github/stars/camel-ai/camel?label=stars&logo=github&color=brightgreen
 [star-url]: https://github.com/camel-ai/camel/stargazers
 [package-license-image]: https://img.shields.io/badge/License-Apache_2.0-blue.svg
@@ -1024,4 +1027,4 @@ The source code is licensed under Apache 2.0.
 [package-download-url]: https://pypi.org/project/camel-ai
 [join-us]:https://eigent-ai.notion.site/eigent-ai-careers
 [join-us-image]:https://img.shields.io/badge/Join%20Us-yellow?style=plastic
-[image-join-us]: https://camel-ai.github.io/camel_asset/graphics/join_us.png
+[image-join-us]: https://camel-ai.github.io/camel_asset/graphics/join_us.png

{camel_ai-0.2.76a8 → camel_ai-0.2.76a12}/README.md

@@ -213,7 +213,7 @@ We are a community-driven research collective comprising over 100 researchers de
 </div>
 
 <div align="center">
-  <a href="https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_rag.html">
+  <a href="https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_rag">
     <img src="docs/images/rag_pipeline.png" alt="RAG Pipeline">
   </a>
 </div>
@@ -299,10 +299,10 @@ We provide a [![Google Colab](https://colab.research.google.com/assets/colab-bad
 
 Explore different types of agents, their roles, and their applications.
 
-- **[Creating Your First Agent](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agent.html)**
-- **[Creating Your First Agent Society](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agents_society.html)**
-- **[Embodied Agents](https://docs.camel-ai.org/cookbooks/advanced_features/embodied_agents.html)**
-- **[Critic Agents](https://docs.camel-ai.org/cookbooks/advanced_features/critic_agents_and_tree_search.html)**
+- **[Creating Your First Agent](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agent)**
+- **[Creating Your First Agent Society](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agents_society)**
+- **[Embodied Agents](https://docs.camel-ai.org/cookbooks/advanced_features/embodied_agents)**
+- **[Critic Agents](https://docs.camel-ai.org/cookbooks/advanced_features/critic_agents_and_tree_search)**
 
 ### Seeking Help
 
@@ -323,19 +323,19 @@ Core components and utilities to build, operate, and enhance CAMEL-AI agents and
 
 | Module | Description |
 |:---|:---|
-| **[Agents](https://docs.camel-ai.org/key_modules/agents.html)** | Core agent architectures and behaviors for autonomous operation. |
-| **[Agent Societies](https://docs.camel-ai.org/key_modules/society.html)** | Components for building and managing multi-agent systems and collaboration. |
-| **[Data Generation](https://docs.camel-ai.org/key_modules/datagen.html)** | Tools and methods for synthetic data creation and augmentation. |
-| **[Models](https://docs.camel-ai.org/key_modules/models.html)** | Model architectures and customization options for agent intelligence. |
-| **[Tools](https://docs.camel-ai.org/key_modules/tools.html)** | Tools integration for specialized agent tasks. |
-| **[Memory](https://docs.camel-ai.org/key_modules/memory.html)** | Memory storage and retrieval mechanisms for agent state management. |
-| **[Storage](https://docs.camel-ai.org/key_modules/storages.html)** | Persistent storage solutions for agent data and states. |
+| **[Agents](https://docs.camel-ai.org/key_modules/agents)** | Core agent architectures and behaviors for autonomous operation. |
+| **[Agent Societies](https://docs.camel-ai.org/key_modules/society)** | Components for building and managing multi-agent systems and collaboration. |
+| **[Data Generation](https://docs.camel-ai.org/key_modules/datagen)** | Tools and methods for synthetic data creation and augmentation. |
+| **[Models](https://docs.camel-ai.org/key_modules/models)** | Model architectures and customization options for agent intelligence. |
+| **[Tools](https://docs.camel-ai.org/key_modules/tools)** | Tools integration for specialized agent tasks. |
+| **[Memory](https://docs.camel-ai.org/key_modules/memory)** | Memory storage and retrieval mechanisms for agent state management. |
+| **[Storage](https://docs.camel-ai.org/key_modules/storages)** | Persistent storage solutions for agent data and states. |
 | **[Benchmarks](https://github.com/camel-ai/camel/tree/master/camel/benchmarks)** | Performance evaluation and testing frameworks. |
-| **[Interpreters](https://docs.camel-ai.org/key_modules/interpreters.html)** | Code and command interpretation capabilities. |
-| **[Data Loaders](https://docs.camel-ai.org/key_modules/loaders.html)** | Data ingestion and preprocessing tools. |
-| **[Retrievers](https://docs.camel-ai.org/key_modules/retrievers.html)** | Knowledge retrieval and RAG components. |
+| **[Interpreters](https://docs.camel-ai.org/key_modules/interpreters)** | Code and command interpretation capabilities. |
+| **[Data Loaders](https://docs.camel-ai.org/key_modules/loaders)** | Data ingestion and preprocessing tools. |
+| **[Retrievers](https://docs.camel-ai.org/key_modules/retrievers)** | Knowledge retrieval and RAG components. |
 | **[Runtime](https://github.com/camel-ai/camel/tree/master/camel/runtime)** | Execution environment and process management. |
-| **[Human-in-the-Loop](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_human_in_loop_and_tool_approval.html)** | Interactive components for human oversight and intervention. |
+| **[Human-in-the-Loop](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_human_in_loop_and_tool_approval)** | Interactive components for human oversight and intervention. |
 ---
 
 ## Research
@@ -396,7 +396,7 @@ We believe that studying these agents on a large scale offers valuable insights
 
 ### 1. Utilize Various LLMs as Backends
 
-For more details, please see our [`Models Documentation`](https://docs.camel-ai.org/key_modules/models.html#).
+For more details, please see our [`Models Documentation`](https://docs.camel-ai.org/key_modules/models#).
 
 > **Data (Hosted on Hugging Face)**
 
@@ -425,42 +425,42 @@ Practical guides and tutorials for implementing specific functionalities in CAME
 ### 1. Basic Concepts
 | Cookbook | Description |
 |:---|:---|
-| **[Creating Your First Agent](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agent.html)** | A step-by-step guide to building your first agent. |
-| **[Creating Your First Agent Society](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agents_society.html)** | Learn to build a collaborative society of agents. |
-| **[Message Cookbook](https://docs.camel-ai.org/cookbooks/basic_concepts/agents_message.html)** | Best practices for message handling in agents. |
+| **[Creating Your First Agent](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agent)** | A step-by-step guide to building your first agent. |
+| **[Creating Your First Agent Society](https://docs.camel-ai.org/cookbooks/basic_concepts/create_your_first_agents_society)** | Learn to build a collaborative society of agents. |
+| **[Message Cookbook](https://docs.camel-ai.org/cookbooks/basic_concepts/agents_message)** | Best practices for message handling in agents. |
 
 ### 2. Advanced Features
 | Cookbook | Description |
 |:---|:---|
-| **[Tools Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_tools.html)** | Integrating tools for enhanced functionality. |
-| **[Memory Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_memory.html)** | Implementing memory systems in agents. |
-| **[RAG Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_rag.html)** | Recipes for Retrieval-Augmented Generation. |
-| **[Graph RAG Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_graph_rag.html)** | Leveraging knowledge graphs with RAG. |
-| **[Track CAMEL Agents with AgentOps](https://docs.camel-ai.org/cookbooks/advanced_features/agents_tracking.html)** | Tools for tracking and managing agents in operations. |
+| **[Tools Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_tools)** | Integrating tools for enhanced functionality. |
+| **[Memory Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_memory)** | Implementing memory systems in agents. |
+| **[RAG Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_rag)** | Recipes for Retrieval-Augmented Generation. |
+| **[Graph RAG Cookbook](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_graph_rag)** | Leveraging knowledge graphs with RAG. |
+| **[Track CAMEL Agents with AgentOps](https://docs.camel-ai.org/cookbooks/advanced_features/agents_tracking)** | Tools for tracking and managing agents in operations. |
 
 ### 3. Model Training & Data Generation
 | Cookbook | Description |
 |:---|:---|
-| **[Data Generation with CAMEL and Finetuning with Unsloth](https://docs.camel-ai.org/cookbooks/data_generation/sft_data_generation_and_unsloth_finetuning_Qwen2_5_7B.html)** | Learn how to generate data with CAMEL and fine-tune models effectively with Unsloth. |
-| **[Data Gen with Real Function Calls and Hermes Format](https://docs.camel-ai.org/cookbooks/data_generation/data_gen_with_real_function_calls_and_hermes_format.html)** | Explore how to generate data with real function calls and the Hermes format. |
-| **[CoT Data Generation and Upload Data to Huggingface](https://docs.camel-ai.org/cookbooks/data_generation/distill_math_reasoning_data_from_deepseek_r1.html)** | Uncover how to generate CoT data with CAMEL and seamlessly upload it to Huggingface. |
-| **[CoT Data Generation and SFT Qwen with Unsolth](https://docs.camel-ai.org/cookbooks/data_generation/cot_data_gen_sft_qwen_unsolth_upload_huggingface.html)** | Discover how to generate CoT data using CAMEL and SFT Qwen with Unsolth, and seamlessly upload your data and model to Huggingface. |
+| **[Data Generation with CAMEL and Finetuning with Unsloth](https://docs.camel-ai.org/cookbooks/data_generation/sft_data_generation_and_unsloth_finetuning_Qwen2_5_7B)** | Learn how to generate data with CAMEL and fine-tune models effectively with Unsloth. |
+| **[Data Gen with Real Function Calls and Hermes Format](https://docs.camel-ai.org/cookbooks/data_generation/data_gen_with_real_function_calls_and_hermes_format)** | Explore how to generate data with real function calls and the Hermes format. |
+| **[CoT Data Generation and Upload Data to Huggingface](https://docs.camel-ai.org/cookbooks/data_generation/distill_math_reasoning_data_from_deepseek_r1)** | Uncover how to generate CoT data with CAMEL and seamlessly upload it to Huggingface. |
+| **[CoT Data Generation and SFT Qwen with Unsolth](https://docs.camel-ai.org/cookbooks/data_generation/cot_data_gen_sft_qwen_unsolth_upload_huggingface)** | Discover how to generate CoT data using CAMEL and SFT Qwen with Unsolth, and seamlessly upload your data and model to Huggingface. |
 
 ### 4. Multi-Agent Systems & Applications
 | Cookbook | Description |
 |:---|:---|
-| **[Role-Playing Scraper for Report & Knowledge Graph Generation](https://docs.camel-ai.org/cookbooks/applications/roleplaying_scraper.html)** | Create role-playing agents for data scraping and reporting. |
-| **[Create A Hackathon Judge Committee with Workforce](https://docs.camel-ai.org/cookbooks/multi_agent_society/workforce_judge_committee.html)** | Building a team of agents for collaborative judging. |
-| **[Dynamic Knowledge Graph Role-Playing: Multi-Agent System with dynamic, temporally-aware knowledge graphs](https://docs.camel-ai.org/cookbooks/applications/dyamic_knowledge_graph.html)** |  Builds dynamic, temporally-aware knowledge graphs for financial applications using a multi-agent system. It processes financial reports, news articles, and research papers to help traders analyze data, identify relationships, and uncover market insights. The system also utilizes diverse and optional element node deduplication techniques to ensure data integrity and optimize graph structure for financial decision-making. |
-| **[Customer Service Discord Bot with Agentic RAG](https://docs.camel-ai.org/cookbooks/applications/customer_service_Discord_bot_using_SambaNova_with_agentic_RAG.html)** | Learn how to build a robust customer service bot for Discord using Agentic RAG. |
-| **[Customer Service Discord Bot with Local Model](https://docs.camel-ai.org/cookbooks/applications/customer_service_Discord_bot_using_local_model_with_agentic_RAG.html)** | Learn how to build a robust customer service bot for Discord using Agentic RAG which supports local deployment. |
+| **[Role-Playing Scraper for Report & Knowledge Graph Generation](https://docs.camel-ai.org/cookbooks/applications/roleplaying_scraper)** | Create role-playing agents for data scraping and reporting. |
+| **[Create A Hackathon Judge Committee with Workforce](https://docs.camel-ai.org/cookbooks/multi_agent_society/workforce_judge_committee)** | Building a team of agents for collaborative judging. |
+| **[Dynamic Knowledge Graph Role-Playing: Multi-Agent System with dynamic, temporally-aware knowledge graphs](https://docs.camel-ai.org/cookbooks/advanced_features/agents_with_dkg)** |  Builds dynamic, temporally-aware knowledge graphs for financial applications using a multi-agent system. It processes financial reports, news articles, and research papers to help traders analyze data, identify relationships, and uncover market insights. The system also utilizes diverse and optional element node deduplication techniques to ensure data integrity and optimize graph structure for financial decision-making. |
+| **[Customer Service Discord Bot with Agentic RAG](https://docs.camel-ai.org/cookbooks/applications/customer_service_Discord_bot_using_SambaNova_with_agentic_RAG)** | Learn how to build a robust customer service bot for Discord using Agentic RAG. |
+| **[Customer Service Discord Bot with Local Model](https://docs.camel-ai.org/cookbooks/applications/customer_service_Discord_bot_using_local_model_with_agentic_RAG)** | Learn how to build a robust customer service bot for Discord using Agentic RAG which supports local deployment. |
 
 ### 5. Data Processing
 | Cookbook | Description |
 |:---|:---|
-| **[Video Analysis](https://docs.camel-ai.org/cookbooks/data_processing/video_analysis.html)** | Techniques for agents in video data analysis. |
-| **[3 Ways to Ingest Data from Websites with Firecrawl](https://docs.camel-ai.org/cookbooks/data_processing/ingest_data_from_websites_with_Firecrawl.html)** | Explore three methods for extracting and processing data from websites using Firecrawl. |
-| **[Create AI Agents that work with your PDFs](https://docs.camel-ai.org/cookbooks/data_processing/agent_with_chunkr_for_pdf_parsing.html)** | Learn how to create AI agents that work with your PDFs using Chunkr and Mistral AI. |
+| **[Video Analysis](https://docs.camel-ai.org/cookbooks/data_processing/video_analysis)** | Techniques for agents in video data analysis. |
+| **[3 Ways to Ingest Data from Websites with Firecrawl](https://docs.camel-ai.org/cookbooks/data_processing/ingest_data_from_websites_with_Firecrawl)** | Explore three methods for extracting and processing data from websites using Firecrawl. |
+| **[Create AI Agents that work with your PDFs](https://docs.camel-ai.org/cookbooks/data_processing/agent_with_chunkr_for_pdf_parsing)** | Learn how to create AI agents that work with your PDFs using Chunkr and Mistral AI. |
 
 <br>
 
@@ -601,7 +601,7 @@ The source code is licensed under Apache 2.0.
 <br>
 
 [docs-image]: https://img.shields.io/badge/Documentation-EB3ECC
-[docs-url]: https://camel-ai.github.io/camel/index.html
+[docs-url]: https://camel-ai.github.io/camel/index
 [star-image]: https://img.shields.io/github/stars/camel-ai/camel?label=stars&logo=github&color=brightgreen
 [star-url]: https://github.com/camel-ai/camel/stargazers
 [package-license-image]: https://img.shields.io/badge/License-Apache_2.0-blue.svg
@@ -625,4 +625,4 @@ The source code is licensed under Apache 2.0.
 [package-download-url]: https://pypi.org/project/camel-ai
 [join-us]:https://eigent-ai.notion.site/eigent-ai-careers
 [join-us-image]:https://img.shields.io/badge/Join%20Us-yellow?style=plastic
-[image-join-us]: https://camel-ai.github.io/camel_asset/graphics/join_us.png
+[image-join-us]: https://camel-ai.github.io/camel_asset/graphics/join_us.png

{camel_ai-0.2.76a8 → camel_ai-0.2.76a12}/camel/__init__.py

@@ -14,7 +14,7 @@
 
 from camel.logger import disable_logging, enable_logging, set_log_level
 
-__version__ = '0.2.76a8'
+__version__ = '0.2.76a12'
 
 __all__ = [
     '__version__',

{camel_ai-0.2.76a8 → camel_ai-0.2.76a12}/camel/loaders/chunkr_reader.py

@@ -34,6 +34,12 @@ class ChunkrReaderConfig:
         high_resolution (bool, optional): Whether to use high resolution OCR.
             (default: :obj:`True`)
         ocr_strategy (str, optional): The OCR strategy. Defaults to 'Auto'.
+        **kwargs: Additional keyword arguments to pass to the Chunkr
+            Configuration. This accepts all other Configuration parameters
+            such as expires_in, pipeline, segment_processing,
+            segmentation_strategy, etc.
+            See: https://github.com/lumina-ai-inc/chunkr/blob/main/core/src/
+            models/task.rs#L749
     """
 
     def __init__(
@@ -41,10 +47,12 @@ class ChunkrReaderConfig:
         chunk_processing: int = 512,
         high_resolution: bool = True,
         ocr_strategy: str = "Auto",
+        **kwargs,
     ):
         self.chunk_processing = chunk_processing
         self.high_resolution = high_resolution
         self.ocr_strategy = ocr_strategy
+        self.kwargs = kwargs
 
 
 class ChunkrReader:
@@ -190,4 +198,5 @@ class ChunkrReader:
                 "Auto": OcrStrategy.AUTO,
                 "All": OcrStrategy.ALL,
             }.get(chunkr_config.ocr_strategy, OcrStrategy.ALL),
+            **chunkr_config.kwargs,
         )

{camel_ai-0.2.76a8 → camel_ai-0.2.76a12}/camel/memories/records.py

@@ -94,6 +94,42 @@ class MemoryRecord(BaseModel):
         if "role_type" in data and isinstance(data["role_type"], str):
             data["role_type"] = RoleType(data["role_type"])
 
+        # Deserialize image_list from base64 strings/URLs back to PIL Images/
+        # URLs
+        if "image_list" in data and data["image_list"] is not None:
+            import base64
+            from io import BytesIO
+
+            from PIL import Image
+
+            image_objects = []
+            for img_item in data["image_list"]:
+                if isinstance(img_item, dict):
+                    # New format with type indicator
+                    if img_item["type"] == "url":
+                        # URL string, keep as-is
+                        image_objects.append(img_item["data"])
+                    else:  # type == "base64"
+                        # Base64 encoded image, convert to PIL Image
+                        img_bytes = base64.b64decode(img_item["data"])
+                        img = Image.open(BytesIO(img_bytes))
+                        # Restore the format attribute if it was saved
+                        if "format" in img_item:
+                            img.format = img_item["format"]
+                        image_objects.append(img)
+                else:
+                    # Legacy format: assume it's a base64 string
+                    img_bytes = base64.b64decode(img_item)
+                    img = Image.open(BytesIO(img_bytes))
+                    image_objects.append(img)
+            data["image_list"] = image_objects
+
+        # Deserialize video_bytes from base64 string
+        if "video_bytes" in data and data["video_bytes"] is not None:
+            import base64
+
+            data["video_bytes"] = base64.b64decode(data["video_bytes"])
+
         # Get valid constructor parameters (cached)
         valid_params = cls._get_constructor_params(message_cls)
 

{camel_ai-0.2.76a8 → camel_ai-0.2.76a12}/camel/messages/base.py

@@ -64,8 +64,9 @@ class BaseMessage:
         content (str): The content of the message.
         video_bytes (Optional[bytes]): Optional bytes of a video associated
             with the message. (default: :obj:`None`)
-        image_list (Optional[List[Image.Image]]): Optional list of PIL Image
-            objects associated with the message. (default: :obj:`None`)
+        image_list (Optional[List[Union[Image.Image, str]]]): Optional list of
+            PIL Image objects or image URLs (strings) associated with the
+            message. (default: :obj:`None`)
         image_detail (Literal["auto", "low", "high"]): Detail level of the
             images associated with the message. (default: :obj:`auto`)
         video_detail (Literal["auto", "low", "high"]): Detail level of the
@@ -80,7 +81,7 @@ class BaseMessage:
     content: str
 
     video_bytes: Optional[bytes] = None
-    image_list: Optional[List[Image.Image]] = None
+    image_list: Optional[List[Union[Image.Image, str]]] = None
     image_detail: Literal["auto", "low", "high"] = "auto"
     video_detail: Literal["auto", "low", "high"] = "auto"
     parsed: Optional[Union[BaseModel, dict]] = None
@@ -92,7 +93,7 @@ class BaseMessage:
         content: str,
         meta_dict: Optional[Dict[str, str]] = None,
         video_bytes: Optional[bytes] = None,
-        image_list: Optional[List[Image.Image]] = None,
+        image_list: Optional[List[Union[Image.Image, str]]] = None,
         image_detail: Union[
             OpenAIVisionDetailType, str
         ] = OpenAIVisionDetailType.AUTO,
@@ -109,8 +110,9 @@ class BaseMessage:
                 dictionary for the message.
             video_bytes (Optional[bytes]): Optional bytes of a video
                 associated with the message.
-            image_list (Optional[List[Image.Image]]): Optional list of PIL
-                Image objects associated with the message.
+            image_list (Optional[List[Union[Image.Image, str]]]): Optional list
+                of PIL Image objects or image URLs (strings) associated with
+                the message.
             image_detail (Union[OpenAIVisionDetailType, str]): Detail level of
                 the images associated with the message.
             video_detail (Union[OpenAIVisionDetailType, str]): Detail level of
@@ -137,7 +139,7 @@ class BaseMessage:
         content: str,
         meta_dict: Optional[Dict[str, str]] = None,
         video_bytes: Optional[bytes] = None,
-        image_list: Optional[List[Image.Image]] = None,
+        image_list: Optional[List[Union[Image.Image, str]]] = None,
         image_detail: Union[
             OpenAIVisionDetailType, str
         ] = OpenAIVisionDetailType.AUTO,
@@ -154,8 +156,9 @@ class BaseMessage:
                 dictionary for the message.
             video_bytes (Optional[bytes]): Optional bytes of a video
                 associated with the message.
-            image_list (Optional[List[Image.Image]]): Optional list of PIL
-                Image objects associated with the message.
+            image_list (Optional[List[Union[Image.Image, str]]]): Optional list
+                of PIL Image objects or image URLs (strings) associated with
+                the message.
             image_detail (Union[OpenAIVisionDetailType, str]): Detail level of
                 the images associated with the message.
             video_detail (Union[OpenAIVisionDetailType, str]): Detail level of
@@ -436,31 +439,64 @@ class BaseMessage:
         )
         if self.image_list and len(self.image_list) > 0:
             for image in self.image_list:
-                if image.format is None:
-                    # Set default format to PNG as fallback
-                    image.format = 'PNG'
-
-                image_type: str = image.format.lower()
-                if image_type not in OpenAIImageType:
-                    raise ValueError(
-                        f"Image type {image.format} "
-                        f"is not supported by OpenAI vision model"
+                # Check if image is a URL string or PIL Image
+                if isinstance(image, str):
+                    # Image is a URL string
+                    hybrid_content.append(
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": image,
+                                "detail": self.image_detail,
+                            },
+                        }
                     )
-                with io.BytesIO() as buffer:
-                    image.save(fp=buffer, format=image.format)
-                    encoded_image = base64.b64encode(buffer.getvalue()).decode(
-                        "utf-8"
+                else:
+                    # Image is a PIL Image object
+                    if image.format is None:
+                        # Set default format to PNG as fallback
+                        image.format = 'PNG'
+
+                    image_type: str = image.format.lower()
+                    if image_type not in OpenAIImageType:
+                        raise ValueError(
+                            f"Image type {image.format} "
+                            f"is not supported by OpenAI vision model"
+                        )
+
+                    # Convert RGBA to RGB for formats that don't support
+                    # transparency or when the image has transparency channel
+                    img_to_save = image
+                    if image.mode in ('RGBA', 'LA', 'P') and image_type in (
+                        'jpeg',
+                        'jpg',
+                    ):
+                        # JPEG doesn't support transparency, convert to RGB
+                        img_to_save = image.convert('RGB')
+                    elif (
+                        image.mode in ('RGBA', 'LA', 'P')
+                        and image_type == 'png'
+                    ):
+                        # For PNG with transparency, convert to RGBA if needed
+                        if image.mode in ('LA', 'P'):
+                            img_to_save = image.convert('RGBA')
+                        # else: RGBA mode, keep as-is
+
+                    with io.BytesIO() as buffer:
+                        img_to_save.save(fp=buffer, format=image.format)
+                        encoded_image = base64.b64encode(
+                            buffer.getvalue()
+                        ).decode("utf-8")
+                    image_prefix = f"data:image/{image_type};base64,"
+                    hybrid_content.append(
+                        {
+                            "type": "image_url",
+                            "image_url": {
+                                "url": f"{image_prefix}{encoded_image}",
+                                "detail": self.image_detail,
+                            },
+                        }
                     )
-                image_prefix = f"data:image/{image_type};base64,"
-                hybrid_content.append(
-                    {
-                        "type": "image_url",
-                        "image_url": {
-                            "url": f"{image_prefix}{encoded_image}",
-                            "detail": self.image_detail,
-                        },
-                    }
-                )
 
         if self.video_bytes:
             import imageio.v3 as iio
@@ -552,9 +588,66 @@ class BaseMessage:
         Returns:
             dict: The converted dictionary.
         """
-        return {
+        result = {
             "role_name": self.role_name,
             "role_type": self.role_type.value,
             **(self.meta_dict or {}),
             "content": self.content,
         }
+
+        # Include image/video fields if present
+        if self.image_list is not None:
+            # Handle both PIL Images and URL strings
+            import base64
+            from io import BytesIO
+
+            image_data_list = []
+            for img in self.image_list:
+                if isinstance(img, str):
+                    # Image is a URL string, store as-is
+                    image_data_list.append({"type": "url", "data": img})
+                else:
+                    # Image is a PIL Image, convert to base64
+                    # Preserve format, default to PNG if not set
+                    img_format = img.format if img.format else "PNG"
+
+                    # Handle transparency for different formats
+                    img_to_save = img
+                    if img.mode in (
+                        'RGBA',
+                        'LA',
+                        'P',
+                    ) and img_format.upper() in ('JPEG', 'JPG'):
+                        # JPEG doesn't support transparency, convert to RGB
+                        img_to_save = img.convert('RGB')
+                    elif (
+                        img.mode in ('LA', 'P') and img_format.upper() == 'PNG'
+                    ):
+                        # For PNG with transparency, convert to RGBA if needed
+                        img_to_save = img.convert('RGBA')
+                    # else: keep as-is for other combinations
+
+                    buffered = BytesIO()
+                    img_to_save.save(buffered, format=img_format)
+                    img_str = base64.b64encode(buffered.getvalue()).decode()
+                    image_data_list.append(
+                        {
+                            "type": "base64",
+                            "data": img_str,
+                            "format": img_format,  # Preserve format
+                        }
+                    )
+            result["image_list"] = image_data_list
+
+        if self.video_bytes is not None:
+            import base64
+
+            result["video_bytes"] = base64.b64encode(self.video_bytes).decode()
+
+        if self.image_detail is not None:
+            result["image_detail"] = self.image_detail
+
+        if self.video_detail is not None:
+            result["video_detail"] = self.video_detail
+
+        return result