diff --git a/__pycache__/app.cpython-313.pyc b/__pycache__/app.cpython-313.pyc index 675f804..a9a716a 100644 Binary files a/__pycache__/app.cpython-313.pyc and b/__pycache__/app.cpython-313.pyc differ diff --git a/__pycache__/config.cpython-313.pyc b/__pycache__/config.cpython-313.pyc index b16f2b0..ac3533b 100644 Binary files a/__pycache__/config.cpython-313.pyc and b/__pycache__/config.cpython-313.pyc differ diff --git a/agents/__pycache__/research_agent.cpython-313.pyc b/agents/__pycache__/research_agent.cpython-313.pyc index fcaafbd..71186bd 100644 Binary files a/agents/__pycache__/research_agent.cpython-313.pyc and b/agents/__pycache__/research_agent.cpython-313.pyc differ diff --git a/agents/research_agent.py b/agents/research_agent.py index 5244528..9d16a9f 100644 --- a/agents/research_agent.py +++ b/agents/research_agent.py @@ -5,27 +5,37 @@ import config class ResearchAgent: """研究模式专用 Agent""" - def __init__(self, role: str, llm_client: LLMClient): + def __init__(self, role: str, llm_client: LLMClient, name: str = None): self.role = role self.llm_client = llm_client self.role_config = config.RESEARCH_MODEL_ROLES.get(role, {}) - self.name = self.role_config.get("name", role.capitalize()) + self.name = name if name else self.role_config.get("name", role.capitalize()) @property def model_name(self) -> str: return self.llm_client.model def _get_system_prompt(self, context: str = "") -> str: - if self.role == "expert_a": + if self.role == "council_member": + return f"""You are {self.name}, a member of the Multi-Model Decision Council. +Your goal is to participate in a round-table discussion to solve the user's problem. +Be conversational, insightful, and constructive. +Build upon others' ideas or respectfully disagree with valid reasoning. +Context: {context}""" + + elif self.role == "expert_a": return f"""You are Expert A, a Senior Analyst. -Your goal is to provide a deep, foundational analysis of the user's topic. -Structure your thinking clearly. Propose a solid initial framework or solution. +You are participating in a round-table discussion. +Your goal is to analyze the topic and propose solutions. +Be conversational, direct, and responsive to other experts. +Do not write a full final report; focus on the current discussion turn. Context: {context}""" elif self.role == "expert_b": return f"""You are Expert B, a Critical Reviewer. -Your goal is to find flaws, risks, and missed opportunities in Expert A's analysis. -Be constructive but rigorous. Don't just agree; add value by challenging assumptions. +You are participating in a round-table discussion. +Your goal is to critique Expert A's points and offer alternative perspectives. +Be conversational and constructive. Challenge assumptions directly. Context: {context}""" elif self.role == "expert_c": diff --git a/app.py b/app.py index a7070fc..56a6a56 100644 --- a/app.py +++ b/app.py @@ -131,20 +131,8 @@ with st.sidebar: st.divider() - if mode == "Deep Research": - st.subheader("🧪 研究模型配置") - - # 3 个角色的模型配置 - roles_config = {} - for role_key, role_info in config.RESEARCH_MODEL_ROLES.items(): - roles_config[role_key] = st.selectbox( - f"{role_info['name']} ({role_info['description']})", - options=list(AVAILABLE_MODELS.keys()), - index=list(AVAILABLE_MODELS.keys()).index(role_info['default_model']) if role_info['default_model'] in AVAILABLE_MODELS else 0, - key=f"model_{role_key}" - ) - - else: # Debate Workshop + + if mode == "Debate Workshop": # Debate Workshop Settings # 模型选择 model = st.selectbox( "🤖 选择通用模型", @@ -205,11 +193,39 @@ with st.sidebar: # ==================== 主界面逻辑 ==================== if mode == "Deep Research": - st.title("🧪 Multi-Model Council V2") - st.markdown("*多模型智囊团：分析 (Expert A) -> 批判 (Expert B) -> 改进 (Expert A) -> 决策 (Expert C)*") + st.title("🧪 Multi-Model Council V4") + st.markdown("*多模型智囊团：自定义 N 个专家进行多轮对话讨论，最后由最后一位专家决策*") - # Input - research_topic = st.text_area("研究/决策主题", placeholder="请输入你想深入研究或决策的主题...", height=100) + col1, col2 = st.columns([3, 1]) + with col1: + research_topic = st.text_area("研究/决策主题", placeholder="请输入你想深入研究或决策的主题...", height=100) + with col2: + max_rounds = st.number_input("讨论轮数", min_value=1, max_value=5, value=2, help="专家们进行对话的轮数") + + # Expert Configuration + st.subheader("👥 专家配置") + num_experts = st.number_input("专家数量", min_value=2, max_value=5, value=3) + + experts_config = [] + cols = st.columns(num_experts) + + for i in range(num_experts): + with cols[i]: + default_model_key = list(AVAILABLE_MODELS.keys())[i % len(AVAILABLE_MODELS)] + st.markdown(f"**Expert {i+1}**") + # Default names + default_name = f"Expert {i+1}" + if i == num_experts - 1: + default_name = f"Expert {i+1} (Synthesizer)" + + expert_name = st.text_input(f"名称 #{i+1}", value=default_name, key=f"expert_name_{i}") + expert_model = st.selectbox(f"模型 #{i+1}", options=list(AVAILABLE_MODELS.keys()), index=list(AVAILABLE_MODELS.keys()).index(default_model_key), key=f"expert_model_{i}") + + experts_config.append({ + "name": expert_name, + "model": expert_model + }) + research_context = st.text_area("补充背景 (可选)", placeholder="任何额外的背景信息...", height=80) start_research_btn = st.button("🚀 开始多模型协作", type="primary", disabled=not research_topic) @@ -219,49 +235,48 @@ if mode == "Deep Research": st.session_state.research_output = "" st.session_state.research_steps_output = [] - manager = ResearchManager(api_key=api_key) + manager = ResearchManager( + api_key=api_key, + base_url=base_url, + provider=provider_id + ) config_obj = ResearchConfig( topic=research_topic, context=research_context, - expert_a_model=roles_config['expert_a'], - expert_b_model=roles_config['expert_b'], - expert_c_model=roles_config['expert_c'] + experts=experts_config ) manager.create_agents(config_obj) st.divider() - st.subheader("🧠 智囊团思考中...") + st.subheader("🗣️ 智囊团讨论中...") - # Collaborative Execution - current_step_name = "" - current_step_content = "" - step_placeholder = st.empty() - status_container = st.status("正在初始化...", expanded=True) + chat_container = st.container() try: - for event in manager.collaborate(research_topic, research_context): + for event in manager.collaborate(research_topic, research_context, max_rounds=max_rounds): if event["type"] == "step_start": current_step_name = event["step"] current_agent = event["agent"] current_model = event["model"] - status_container.update(label=f"🔄 {current_step_name} [{current_agent}] ({current_model})", state="running") - step_placeholder = st.empty() - current_step_content = "" + + # Create a chat message block + with chat_container: + st.markdown(f"#### {current_step_name}") + st.caption(f"🤖 {current_agent} ({current_model})") + message_placeholder = st.empty() + current_content = "" elif event["type"] == "content": - current_step_content += event["content"] - step_placeholder.markdown(f"**Thinking...**\n\n{current_step_content}") + current_content += event["content"] + message_placeholder.markdown(current_content) elif event["type"] == "step_end": - # Save step result + # Save step result for history st.session_state.research_steps_output.append({ "step": current_step_name, "output": event["output"] }) - status_container.write(f"### {current_step_name}\n{event['output']}") - status_container.update(label=f"✅ {current_step_name} 完成", state="running") - - status_container.update(label="✅ 所有步骤完成", state="complete", expanded=False) + st.divider() # Separator between turns # The last step output is the final plan if st.session_state.research_steps_output: @@ -423,9 +438,9 @@ elif mode == "Debate Workshop": try: # 初始化默认客户端 llm_client = LLMClient( - provider="aihubmix", + provider=provider_id, api_key=api_key, - base_url="https://aihubmix.com/v1", + base_url=base_url, model=model ) @@ -434,9 +449,9 @@ elif mode == "Debate Workshop": for ag_id, ag_model in agent_model_map.items(): if ag_model != model: # Only create new client if different from default agent_clients[ag_id] = LLMClient( - provider="aihubmix", + provider=provider_id, api_key=api_key, - base_url="https://aihubmix.com/v1", + base_url=base_url, model=ag_model ) diff --git a/config.py b/config.py index 15db778..78909a1 100644 --- a/config.py +++ b/config.py @@ -10,8 +10,39 @@ load_dotenv() ANTHROPIC_API_KEY = os.getenv("ANTHROPIC_API_KEY", "") OPENAI_API_KEY = os.getenv("OPENAI_API_KEY", "") AIHUBMIX_API_KEY = os.getenv("AIHUBMIX_API_KEY", "sk-yd8Tik0nFW5emKYcBdFc433b7c8b4dC182848f76819bBe73") +DEEPSEEK_API_KEY = os.getenv("DEEPSEEK_API_KEY", "") +SILICONFLOW_API_KEY = os.getenv("SILICONFLOW_API_KEY", "") -# AIHubMix 配置 +# LLM Providers Configuration +LLM_PROVIDERS = { + "AIHubMix": { + "base_url": "https://aihubmix.com/v1", + "api_key_var": "AIHUBMIX_API_KEY", + "default_model": "gpt-4o" + }, + "DeepSeek": { + "base_url": "https://api.deepseek.com", + "api_key_var": "DEEPSEEK_API_KEY", + "default_model": "deepseek-chat" + }, + "SiliconFlow": { + "base_url": "https://api.siliconflow.cn/v1", + "api_key_var": "SILICONFLOW_API_KEY", + "default_model": "deepseek-ai/DeepSeek-V3" # SiliconFlow often uses full path + }, + "OpenAI": { + "base_url": "https://api.openai.com/v1", + "api_key_var": "OPENAI_API_KEY", + "default_model": "gpt-4o" + }, + "Custom": { + "base_url": "http://localhost:8000/v1", + "api_key_var": "CUSTOM_API_KEY", + "default_model": "local-model" + } +} + +# AIHubMix 配置 (Legacy, keeping for backward compatibility if needed, but main logic will use LLM_PROVIDERS) AIHUBMIX_BASE_URL = "https://aihubmix.com/v1" # 模型配置 @@ -20,17 +51,42 @@ LLM_PROVIDER = "aihubmix" # 默认使用 AIHubMix # 支持的模型列表 AVAILABLE_MODELS = { + # OpenAI "gpt-4o": "GPT-4o (OpenAI)", "gpt-4o-mini": "GPT-4o Mini (OpenAI)", + "gpt-4-turbo": "GPT-4 Turbo (OpenAI)", + + # Anthropic "claude-3-5-sonnet-20241022": "Claude 3.5 Sonnet (Anthropic)", "claude-3-opus-20240229": "Claude 3 Opus (Anthropic)", + "claude-3-haiku-20240307": "Claude 3 Haiku (Anthropic)", + + # Google "gemini-1.5-pro": "Gemini 1.5 Pro (Google)", "gemini-1.5-flash": "Gemini 1.5 Flash (Google)", + "gemini-2.0-flash-exp": "Gemini 2.0 Flash Exp (Google)", + + # DeepSeek "deepseek-chat": "DeepSeek V3 (DeepSeek)", "deepseek-reasoner": "DeepSeek R1 (DeepSeek)", + "deepseek-coder": "DeepSeek Coder (DeepSeek)", + "deepseek-v2.5": "DeepSeek V2.5 (DeepSeek)", + "deepseek-coder-v2": "DeepSeek Coder V2 (DeepSeek)", + + # Meta "llama-3.3-70b-instruct": "Llama 3.3 70B (Meta)", + "llama-3.1-405b-instruct": "Llama 3.1 405B (Meta)", + + # Alibaba "qwen-2.5-72b-instruct": "Qwen 2.5 72B (Alibaba)", + "qwen-plus": "Qwen Plus (Alibaba)", + "qwen-turbo": "Qwen Turbo (Alibaba)", + + # Mistral "mistral-large-latest": "Mistral Large (Mistral)", + + # Perplexity + "llama-3.1-sonar-huge-128k-online": "Sonar Huge Online (Perplexity)", } # 辩论配置 diff --git a/orchestrator/__pycache__/research_manager.cpython-313.pyc b/orchestrator/__pycache__/research_manager.cpython-313.pyc index 7c0fd17..700302d 100644 Binary files a/orchestrator/__pycache__/research_manager.cpython-313.pyc and b/orchestrator/__pycache__/research_manager.cpython-313.pyc differ diff --git a/orchestrator/research_manager.py b/orchestrator/research_manager.py index 79f3c67..34df206 100644 --- a/orchestrator/research_manager.py +++ b/orchestrator/research_manager.py @@ -8,9 +8,8 @@ import config class ResearchConfig: topic: str context: str = "" - expert_a_model: str = "gpt-4o" - expert_b_model: str = "gemini-1.5-pro" - expert_c_model: str = "claude-3-5-sonnet-20241022" + # Dynamic list of experts: [{"name": "Expert 1", "model": "gpt-4o", "role": "analyst"}, ...] + experts: List[Dict[str, str]] = None class ResearchManager: """Manages the Multi-Model Council workflow""" @@ -19,62 +18,88 @@ class ResearchManager: self.api_key = api_key self.base_url = base_url self.provider = provider - self.agents = {} + self.agents = [] def _get_client(self, model: str) -> LLMClient: return LLMClient( - provider=self.provider, + provider=self.provider, # Configured to respect provider or default to aihubmix logic inside client api_key=self.api_key, base_url=self.base_url, model=model ) def create_agents(self, config: ResearchConfig): - """Initialize agents with specific models""" - self.agents["expert_a"] = ResearchAgent("expert_a", self._get_client(config.expert_a_model)) - self.agents["expert_b"] = ResearchAgent("expert_b", self._get_client(config.expert_b_model)) - self.agents["expert_c"] = ResearchAgent("expert_c", self._get_client(config.expert_c_model)) + """Initialize agents with specific models from config""" + self.agents = [] + if config.experts: + for idx, expert_conf in enumerate(config.experts): + # Assign role based on position or config + # First agents are discussion members, last one is Synthesizer usually, + # but for equality we treat them all as members until the end. + # We'll assign a generic "member" role or specific if provided. + + role_type = "council_member" + # If it's the last one, maybe give them synthesizer duty? + # For now, all are members, and we explicitly pick one for synthesis. + + agent = ResearchAgent( + role=role_type, + llm_client=self._get_client(expert_conf["model"]), + name=expert_conf.get("name", f"Expert {idx+1}") + ) + self.agents.append(agent) - def collaborate(self, topic: str, context: str) -> Generator[Dict[str, str], None, None]: + def collaborate(self, topic: str, context: str, max_rounds: int = 3) -> Generator[Dict[str, str], None, None]: """ - Execute the collaborative research process: - 1. Expert A: Propose Analysis - 2. Expert B: Critique - 3. Expert C: Synthesis & Final Plan + Execute the collaborative research process with multi-round discussion: + 1. Conversation Loop (All Experts Round Robin) + 2. Final Synthesis (Last Expert) """ - # Step 1: Expert A Analysis - findings_a = "" - yield {"type": "step_start", "step": "Expert A Analysis", "agent": self.agents["expert_a"].name, "model": self.agents["expert_a"].model_name} - prompt_a = f"Please provide a comprehensive analysis and initial proposal for the topic: '{topic}'.\nContext: {context}" - for chunk in self.agents["expert_a"].generate(prompt_a, context): - findings_a += chunk - yield {"type": "content", "content": chunk} - yield {"type": "step_end", "output": findings_a} + conversation_history = [] + discussion_context = f"Topic: '{topic}'\nBackground Context: {context}\n\n" + + # Round-Robin Discussion + for round_num in range(1, max_rounds + 1): + for agent in self.agents: + yield {"type": "step_start", "step": f"Round {round_num}: {agent.name}", "agent": agent.name, "model": agent.model_name} + + # Construct prompt + if round_num == 1 and not conversation_history: + prompt = f"You are {agent.name}. You are starting the discussion on '{topic}'. Provide your initial analysis and key points. Be conversational but substantive." + else: + prompt = f"You are {agent.name}. Review the discussion so far. Respond to previous points. Defend your views or refine them. Keep the discussion moving towards a solution.\n\nDiscussion History:\n{_format_history(conversation_history)}" + + response = "" + for chunk in agent.generate(prompt, context=discussion_context): + response += chunk + yield {"type": "content", "content": chunk} + + conversation_history.append({"agent": agent.name, "content": response}) + yield {"type": "step_end", "output": response} - # Step 2: Expert B Critique - findings_b = "" - yield {"type": "step_start", "step": "Expert B Critique", "agent": self.agents["expert_b"].name, "model": self.agents["expert_b"].model_name} - prompt_b = f"Review Expert A's proposal on '{topic}'. Critique it, find gaps, and suggest improvements.\nExpert A's Proposal:\n{findings_a}" - for chunk in self.agents["expert_b"].generate(prompt_b, context): - findings_b += chunk - yield {"type": "content", "content": chunk} - yield {"type": "step_end", "output": findings_b} + # Final Synthesis by the LAST agent (or a specific designated one) + synthesizer = self.agents[-1] + yield {"type": "step_start", "step": f"Final Synthesis ({synthesizer.name})", "agent": synthesizer.name, "model": synthesizer.model_name} + + prompt_syn = f"""Synthesize the entire discussion into a final comprehensive plan for '{topic}'. + +Discussion History: +{_format_history(conversation_history)} - # Step 3: Expert A Refinement (Innovative Optimization) - findings_a_refined = "" - yield {"type": "step_start", "step": "Expert A Refinement", "agent": self.agents["expert_a"].name, "model": self.agents["expert_a"].model_name} - prompt_a_refine = f"Expert B has critiqued your initial proposal.\nCritique: {findings_b}\n\nPlease refine your proposal to address these points. Strengthen your arguments and fix the gaps." - for chunk in self.agents["expert_a"].generate(prompt_a_refine, context): - findings_a_refined += chunk - yield {"type": "content", "content": chunk} - yield {"type": "step_end", "output": findings_a_refined} +IMPORTANT: +1. Reconcile the different viewpoints from all experts. +2. Provide a concrete action plan. +3. You MUST include a Mermaid.js diagram (using ```mermaid code block) to visualize the roadmap or process.""" - # Step 4: Expert C Synthesis & Visualization - findings_c = "" - yield {"type": "step_start", "step": "Expert C Synthesis & Visualization", "agent": self.agents["expert_c"].name, "model": self.agents["expert_c"].model_name} - prompt_c = f"Synthesize a final comprehensive plan for '{topic}' based on the refined proposal.\nRefined Proposal:\n{findings_a_refined}\nCritique Reference:\n{findings_b}\n\nIMPORTANT: Include a Mermaid.js diagram (sequenceDiagram, gantt, or flowchart) to visualize the roadmap or process at the end of your report." - for chunk in self.agents["expert_c"].generate(prompt_c, context): - findings_c += chunk + findings_syn = "" + for chunk in synthesizer.generate(prompt_syn, context=discussion_context): + findings_syn += chunk yield {"type": "content", "content": chunk} - yield {"type": "step_end", "output": findings_c} + yield {"type": "step_end", "output": findings_syn} + +def _format_history(history: List[Dict[str, str]]) -> str: + formatted = "" + for turn in history: + formatted += f"[{turn['agent']}]: {turn['content']}\n\n" + return formatted diff --git a/utils/__pycache__/llm_client.cpython-313.pyc b/utils/__pycache__/llm_client.cpython-313.pyc index 73d5602..1a8cdb0 100644 Binary files a/utils/__pycache__/llm_client.cpython-313.pyc and b/utils/__pycache__/llm_client.cpython-313.pyc differ diff --git a/utils/llm_client.py b/utils/llm_client.py index 6495d0f..f3881d8 100644 --- a/utils/llm_client.py +++ b/utils/llm_client.py @@ -36,24 +36,25 @@ class LLMClient: self.client = OpenAI(api_key=api_key) self.model = model or "gpt-4o" - elif self.provider == "aihubmix": - # AIHubMix 兼容 OpenAI API 格式 + elif self.provider in ["aihubmix", "deepseek", "siliconflow", "custom"]: + # OpenAI 兼容接口 Providers from openai import OpenAI + + default_urls = { + "aihubmix": "https://aihubmix.com/v1", + "deepseek": "https://api.deepseek.com", + "siliconflow": "https://api.siliconflow.cn/v1", + "custom": "http://localhost:8000/v1" + } + + final_base_url = base_url or default_urls.get(self.provider) + self.client = OpenAI( api_key=api_key, - base_url=base_url or "https://aihubmix.com/v1" + base_url=final_base_url ) self.model = model or "gpt-4o" - elif self.provider == "custom": - # 自定义 OpenAI 兼容接口（vLLM、Ollama、TGI 等） - from openai import OpenAI - self.client = OpenAI( - api_key=api_key or "not-needed", - base_url=base_url or "http://localhost:8000/v1" - ) - self.model = model or "local-model" - else: raise ValueError(f"不支持的 provider: {self.provider}")