fix(docs-config): update docs and configs to make them more structured (#78)

update docs and configs

Author: BinWang28

README.md

@@ -7,12 +7,11 @@
 
 <div align="center">
 
-[![DOCS](https://img.shields.io/badge/Documentation-4285F4?style=for-the-badge&logo=gitbook&logoColor=white)](https://miromindai.github.io/MiroFlow/)
 [![DEMO](https://img.shields.io/badge/Demo-FFB300?style=for-the-badge&logo=airplayvideo&logoColor=white)](https://dr.miromind.ai/)
 [![MODELS](https://img.shields.io/badge/Models-5EDDD2?style=for-the-badge&logo=huggingface&logoColor=ffffff&labelColor)](https://huggingface.co/collections/miromind-ai/mirothinker-v02-68af084a18035f57b17cd902)
 [![DATA](https://img.shields.io/badge/Data-0040A1?style=for-the-badge&logo=huggingface&logoColor=ffffff&labelColor)](https://huggingface.co/datasets/miromind-ai/MiroVerse-v0.1)
-
 [![BLOG](https://img.shields.io/badge/Blog-4285F4?style=for-the-badge&logo=google-chrome&logoColor=white)](https://miromind.ai/blog/miroflow)
+
 [![GITHUB](https://img.shields.io/badge/Github-24292F?style=for-the-badge&logo=github&logoColor=white)](https://github.com/MiroMindAI)
 [![DISCORD](https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.com/invite/GPqEnkzQZd)
 [![WeChat](https://img.shields.io/badge/WeChat-07C160?style=for-the-badge&logo=wechat&logoColor=white)](https://huggingface.co/datasets/miromind-ai/MiroFlow-Benchmarks/resolve/main/assets/wechat.png)
@@ -22,7 +21,9 @@
 
 <div align="center">
 
-### 🚀 [Try our Demo!](https://dr.miromind.ai/)｜[中文](README_zh.md)｜[日本語](README_ja.md)
+## 📚 **[READ THE DOCUMENTATION](https://miromindai.github.io/MiroFlow/)**
+
+### 🚀 [Try Demo](https://dr.miromind.ai/) ｜ [中文](README_zh.md) ｜ [日本語](README_ja.md)
 
 </div>
 

config/agent_browsecomp-en_claude37sonnet.yaml

@@ -0,0 +1,78 @@
+defaults:
+  - benchmark: browsecomp-en
+  - override hydra/job_logging: none
+  - _self_  # Allow defining variables at the top of this file
+
+
+main_agent:
+  prompt_class: MainAgentPrompt_GAIA
+  llm: 
+    provider_class: "ClaudeOpenRouterClient"
+    model_name: "anthropic/claude-3.7-sonnet"
+    async_client: true
+    temperature: 0.3
+    top_p: 0.95
+    min_p: 0.0
+    top_k: -1
+    max_tokens: 32000
+    openrouter_api_key: "${oc.env:OPENROUTER_API_KEY,???}"
+    openrouter_base_url: "${oc.env:OPENROUTER_BASE_URL,https://openrouter.ai/api/v1}"
+    openrouter_provider: "anthropic"
+    disable_cache_control: false
+    keep_tool_result: -1
+    oai_tool_thinking: false
+  
+  tool_config:
+    - tool-reasoning
+
+  max_turns: 50  # Maximum number of turns for main agent execution
+  max_tool_calls_per_turn: 10  # Maximum number of tool calls per turn
+  
+  input_process:
+    hint_generation: true
+    hint_llm_base_url: "${oc.env:HINT_LLM_BASE_URL,https://api.openai.com/v1}"
+  output_process:
+    final_answer_extraction: true
+    final_answer_llm_base_url: "${oc.env:FINAL_ANSWER_LLM_BASE_URL,https://api.openai.com/v1}"
+
+  openai_api_key: "${oc.env:OPENAI_API_KEY,???}" # used for hint generation and final answer extraction
+  add_message_id: true
+  keep_tool_result: -1
+  chinese_context: "${oc.env:CHINESE_CONTEXT,false}"
+
+
+sub_agents:
+  agent-worker:
+    prompt_class: SubAgentWorkerPrompt
+    llm: 
+      provider_class: "ClaudeOpenRouterClient"
+      model_name: "anthropic/claude-3.7-sonnet"
+      async_client: true
+      temperature: 0.3
+      top_p: 0.95
+      min_p: 0.0
+      top_k: -1
+      max_tokens: 32000
+      openrouter_api_key: "${oc.env:OPENROUTER_API_KEY,???}"
+      openrouter_base_url: "${oc.env:OPENROUTER_BASE_URL,https://openrouter.ai/api/v1}"
+      openrouter_provider: "anthropic"
+      disable_cache_control: false
+      keep_tool_result: -1
+      oai_tool_thinking: false
+    
+    tool_config:
+      - tool-searching
+      - tool-image-video
+      - tool-reading
+      - tool-code
+      - tool-audio
+
+    max_turns: 50  # Maximum number of turns for main agent execution
+    max_tool_calls_per_turn: 10  # Maximum number of tool calls per turn
+
+
+# Can define some top-level or default parameters here
+output_dir: logs/
+data_dir: "${oc.env:DATA_DIR,data}"  # Points to where data is stored
+
+

config/agent_mirothinker.yaml renamed to config/agent_browsecomp-en_mirothinker.yaml

@@ -1,35 +1,37 @@
 defaults:
-  - benchmark: gaia-validation
+  - benchmark: browsecomp-en
   - override hydra/job_logging: none
   - _self_  # Allow defining variables at the top of this file
 
 
 main_agent:
-  prompt_class: MainAgentPromptBoxedAnswer
+  prompt_class: MainAgentPrompt_GAIA
   llm: 
     provider_class: "MiroThinkerSGLangClient"
-    model_name: "MODEL_NAME"
+    model_name: "DUMMY_MODEL_NAME"
     async_client: true
-    temperature: 0.6
+    temperature: 0.3
     top_p: 0.95
     min_p: 0.0
     top_k: -1
-    max_tokens: 8192
+    max_tokens: 4096
     oai_mirothinker_api_key: "${oc.env:OAI_MIROTHINKER_API_KEY,dummy_key}"
     oai_mirothinker_base_url: "${oc.env:OAI_MIROTHINKER_BASE_URL,http://localhost:61005/v1}"
     keep_tool_result: -1
     oai_tool_thinking: false
 
-  tool_config: []
+  tool_config:
+    - tool-reasoning
 
-  max_turns: -1  # Maximum number of turns for main agent execution
+  max_turns: 50  # Maximum number of turns for main agent execution
   max_tool_calls_per_turn: 10  # Maximum number of tool calls per turn
 
   input_process:
     hint_generation: false
     hint_llm_base_url: "${oc.env:HINT_LLM_BASE_URL,https://api.openai.com/v1}"
+
   output_process:
-    final_answer_extraction: false
+    final_answer_extraction: true
     final_answer_llm_base_url: "${oc.env:FINAL_ANSWER_LLM_BASE_URL,https://api.openai.com/v1}"
 
   openai_api_key: "${oc.env:OPENAI_API_KEY,???}" # used for hint generation and final answer extraction
@@ -43,25 +45,31 @@ sub_agents:
     prompt_class: SubAgentWorkerPrompt
     llm: 
       provider_class: "MiroThinkerSGLangClient"
-      model_name: "MODEL_NAME"
+      model_name: "DUMMY_MODEL_NAME"
       async_client: true
-      temperature: 0.6
-      top_p: 0.95
+      temperature: 0.3
+      top_p: 1.0
       min_p: 0.0
       top_k: -1
-      max_tokens: 8192
+      max_tokens: 4096
       oai_mirothinker_api_key: "${oc.env:OAI_MIROTHINKER_API_KEY,dummy_key}"
       oai_mirothinker_base_url: "${oc.env:OAI_MIROTHINKER_BASE_URL,http://localhost:61005/v1}"
       keep_tool_result: -1
       oai_tool_thinking: false
 
     tool_config:
+      - tool-searching
+      - tool-image-video
       - tool-reading
+      - tool-code
+      - tool-audio
 
-    max_turns: -1  # Maximum number of turns for main agent execution
+    max_turns: 50  # Maximum number of turns for main agent execution
     max_tool_calls_per_turn: 10  # Maximum number of tool calls per turn
 
 
 # Can define some top-level or default parameters here
 output_dir: logs/
-data_dir: "${oc.env:DATA_DIR,data}"  # Points to where data is stored
+data_dir: "${oc.env:DATA_DIR,data}"  # Points to where data is stored
+
+

config/agent_finsearchcomp_claude37sonnet.yaml

@@ -0,0 +1,77 @@
+defaults:
+  - benchmark: finsearchcomp
+  - override hydra/job_logging: none
+  - _self_  # Allow defining variables at the top of this file
+
+
+main_agent:
+  prompt_class: MainAgentPrompt_GAIA
+  llm: 
+    provider_class: "ClaudeOpenRouterClient"
+    model_name: "anthropic/claude-3.7-sonnet"
+    async_client: true
+    temperature: 0.6
+    top_p: 0.95
+    min_p: 0.0
+    top_k: -1
+    max_tokens: 32000
+    openrouter_api_key: "${oc.env:OPENROUTER_API_KEY,???}"
+    openrouter_base_url: "${oc.env:OPENROUTER_BASE_URL,https://openrouter.ai/api/v1}"
+    openrouter_provider: "anthropic"
+    disable_cache_control: false
+    keep_tool_result: -1
+    oai_tool_thinking: false
+  
+  tool_config:
+    - tool-reasoning
+
+  max_turns: 20  # Maximum number of turns for main agent execution
+  max_tool_calls_per_turn: 10  # Maximum number of tool calls per turn
+  
+  input_process:
+    hint_generation: true
+    hint_llm_base_url: "${oc.env:HINT_LLM_BASE_URL,https://api.openai.com/v1}"
+  output_process:
+    final_answer_extraction: true
+    final_answer_llm_base_url: "${oc.env:FINAL_ANSWER_LLM_BASE_URL,https://api.openai.com/v1}"
+
+  openai_api_key: "${oc.env:OPENAI_API_KEY,???}" # used for hint generation and final answer extraction
+  add_message_id: true
+  keep_tool_result: -1
+  chinese_context: "${oc.env:CHINESE_CONTEXT,false}"
+
+
+sub_agents:
+  agent-worker:
+    prompt_class: SubAgentWorkerPrompt
+    llm: 
+      provider_class: "ClaudeOpenRouterClient"
+      model_name: "anthropic/claude-3.7-sonnet"
+      async_client: true
+      temperature: 0.6
+      top_p: 0.95
+      min_p: 0.0
+      top_k: -1
+      max_tokens: 32000
+      openrouter_api_key: "${oc.env:OPENROUTER_API_KEY,???}"
+      openrouter_base_url: "${oc.env:OPENROUTER_BASE_URL,https://openrouter.ai/api/v1}"
+      openrouter_provider: "anthropic"
+      disable_cache_control: false
+      keep_tool_result: -1
+      oai_tool_thinking: false
+    
+    tool_config:
+      - tool-searching
+      - tool-image-video
+      - tool-reading
+      - tool-code
+      - tool-audio
+
+    max_turns: 20  # Maximum number of turns for main agent execution
+    max_tool_calls_per_turn: 10  # Maximum number of tool calls per turn
+
+# Can define some top-level or default parameters here
+output_dir: logs/
+data_dir: "${oc.env:DATA_DIR,data}"  # Points to where data is stored
+
+

config/agent_finsearchcomp.yaml renamed to config/agent_finsearchcomp_mirothinker.yaml

@@ -8,7 +8,7 @@ main_agent:
   prompt_class: MainAgentPrompt_GAIA
   llm: 
     provider_class: "MiroThinkerSGLangClient"
-    model_name: "MODEL_NAME"
+    model_name: "DUMMY_MODEL_NAME"
     async_client: true
     temperature: 0.6
     top_p: 0.95
@@ -44,7 +44,7 @@ sub_agents:
     prompt_class: SubAgentWorkerPrompt
     llm: 
       provider_class: "MiroThinkerSGLangClient"
-      model_name: "MODEL_NAME"
+      model_name: "DUMMY_MODEL_NAME"
       async_client: true
       temperature: 0.6
       top_p: 0.95
@@ -69,3 +69,5 @@ sub_agents:
 # Can define some top-level or default parameters here
 output_dir: logs/
 data_dir: "${oc.env:DATA_DIR,data}"  # Points to where data is stored
+
+

config/agent_gaia-validation-text-only_mirothinker.yaml

@@ -8,7 +8,7 @@ main_agent:
   prompt_class: MainAgentPrompt_GAIA
   llm: 
     provider_class: "MiroThinkerSGLangClient"
-    model_name: "MODEL_NAME"
+    model_name: "DUMMY_MODEL_NAME"
     async_client: true
     temperature: 0.3
     top_p: 0.95
@@ -45,7 +45,7 @@ sub_agents:
     prompt_class: SubAgentWorkerPrompt
     llm: 
       provider_class: "MiroThinkerSGLangClient"
-      model_name: "anthropic/claude-3.7-sonnet"
+      model_name: "DUMMY_MODEL_NAME"
       async_client: true
       temperature: 0.3
       top_p: 1.0

config/agent_gaia-validation-text-only_mirothinker_single_agent.yaml

@@ -0,0 +1,53 @@
+defaults:
+  - benchmark: gaia-validation-text-only
+  - override hydra/job_logging: none
+  - _self_  # Allow defining variables at the top of this file
+
+
+main_agent:
+  prompt_class: MainAgentPrompt_GAIA
+  llm: 
+    provider_class: "MiroThinkerSGLangClient"
+    model_name: "MODEL_NAME"
+    async_client: true
+    temperature: 0.3
+    top_p: 0.95
+    min_p: 0.0
+    top_k: -1
+    max_tokens: 4096
+    oai_mirothinker_api_key: "${oc.env:OAI_MIROTHINKER_API_KEY,dummy_key}"
+    oai_mirothinker_base_url: "${oc.env:OAI_MIROTHINKER_BASE_URL,http://localhost:61005/v1}"
+    keep_tool_result: -1
+    oai_tool_thinking: false
+  
+  tool_config:
+    - tool-reasoning
+    - tool-searching
+    - tool-image-video
+    - tool-reading
+    - tool-code
+    - tool-audio
+
+  max_turns: 50  # Maximum number of turns for main agent execution
+  max_tool_calls_per_turn: 10  # Maximum number of tool calls per turn
+  
+  input_process:
+    hint_generation: false
+    hint_llm_base_url: "${oc.env:HINT_LLM_BASE_URL,https://api.openai.com/v1}"
+
+  output_process:
+    final_answer_extraction: true
+    final_answer_llm_base_url: "${oc.env:FINAL_ANSWER_LLM_BASE_URL,https://api.openai.com/v1}"
+
+  openai_api_key: "${oc.env:OPENAI_API_KEY,???}" # used for hint generation and final answer extraction
+  add_message_id: true
+  keep_tool_result: -1
+  chinese_context: "${oc.env:CHINESE_CONTEXT,false}"
+
+
+sub_agents: null
+
+# Can define some top-level or default parameters here
+output_dir: logs/
+data_dir: "${oc.env:DATA_DIR,data}"  # Points to where data is stored
+