haiku.rag 0.9.3__py3-none-any.whl → 0.10.0__py3-none-any.whl

haiku/rag/research/prompts.py

@@ -1,129 +1,113 @@
-ORCHESTRATOR_PROMPT = """You are a research orchestrator responsible for coordinating a comprehensive research workflow.
-
-Your role is to:
-1. Understand and decompose the research question
-2. Plan a systematic research approach
-3. Coordinate specialized agents to gather and analyze information
-4. Ensure comprehensive coverage of the topic
-5. Iterate based on findings and gaps
-
-Create a research plan that:
-- Breaks down the question into at most 3 focused sub-questions
-- Each sub-question should target a specific aspect of the research
-- Prioritize the most important aspects to investigate
-- Ensure comprehensive coverage within the 3-question limit
-- IMPORTANT: Make each sub-question a standalone, self-contained query that can
-  be executed without additional context. Include necessary entities, scope,
-  timeframe, and qualifiers. Avoid pronouns like "it/they/this"; write queries
-  that make sense in isolation."""
-
-SEARCH_AGENT_PROMPT = """You are a search and question-answering specialist.
-
-Your role is to:
-1. Search the knowledge base for relevant information
-2. Analyze the retrieved documents
-3. Provide an accurate answer strictly grounded in the retrieved context
-
-Output format:
-- You must return a SearchAnswer model with fields:
-  - query: the question being answered (echo the user query)
-  - answer: your final answer based only on the provided context
-  - context: list[str] of only the minimal set of verbatim snippet texts you
-    used to justify the answer (do not include unrelated text; do not invent)
-  - sources: list[str] of document_uri values corresponding to the snippets you
-    actually used in the answer (one URI per context snippet, order aligned)
+PLAN_PROMPT = """You are the research orchestrator for a focused, iterative
+workflow.
+
+Responsibilities:
+1. Understand and decompose the main question
+2. Propose a minimal, high‑leverage plan
+3. Coordinate specialized agents to gather evidence
+4. Iterate based on gaps and new findings
+
+Plan requirements:
+- Produce at most 3 sub_questions that together cover the main question.
+- Each sub_question must be a standalone, self‑contained query that can run
+  without extra context. Include concrete entities, scope, timeframe, and any
+  qualifiers. Avoid ambiguous pronouns (it/they/this/that).
+- Prioritize the highest‑value aspects first; avoid redundancy and overlap.
+- Prefer questions that are likely answerable from the current knowledge base;
+  if coverage is uncertain, make scopes narrower and specific.
+- Order sub_questions by execution priority (most valuable first)."""
+
+SEARCH_AGENT_PROMPT = """You are a search and question‑answering specialist.
+
+Tasks:
+1. Search the knowledge base for relevant evidence.
+2. Analyze retrieved snippets.
+3. Provide an answer strictly grounded in that evidence.
 
 Tool usage:
-- Always call the search_and_answer tool before drafting any answer.
-- The tool returns XML containing only a list of snippets, where each snippet
-  has the verbatim `text`, a `score` indicating relevance, and the
-  `document_uri` it came from.
+- Always call search_and_answer before drafting any answer.
+- The tool returns snippets with verbatim `text`, a relevance `score`, and the
+  originating `document_uri`.
 - You may call the tool multiple times to refine or broaden context, but do not
-  exceed 3 total tool calls per question. Prefer precision over volume.
+  exceed 3 total calls. Favor precision over volume.
 - Use scores to prioritize evidence, but include only the minimal subset of
-  snippet texts (verbatim) in SearchAnswer.context.
-- Set SearchAnswer.sources to the matching document_uris for the snippets you
-  used (one URI per snippet, aligned by order). Context must be text-only.
-- If no relevant information is found, say so and return an empty context list.
-
-Important:
-- Do not include any content in the answer that is not supported by the context.
-- Keep context snippets short (just the necessary lines), verbatim, and focused."""
-
-EVALUATION_AGENT_PROMPT = """You are an analysis and evaluation specialist for research workflows.
-
-You have access to:
-- The original research question
-- Question-answer pairs from search operations
-- Raw search results and source documents
+  snippet texts (verbatim) in SearchAnswer.context (typically 1‑4).
+- Set SearchAnswer.sources to the corresponding document_uris for the snippets
+  you used (one URI per snippet; same order as context). Context must be text‑only.
+- If no relevant information is found, clearly say so and return an empty
+  context list and sources list.
+
+Answering rules:
+- Be direct and specific; avoid meta commentary about the process.
+- Do not include any claims not supported by the provided snippets.
+- Prefer concise phrasing; avoid copying long passages.
+- When evidence is partial, state the limits explicitly in the answer."""
+
+EVALUATION_AGENT_PROMPT = """You are an analysis and evaluation specialist for
+the research workflow.
+
+Inputs available:
+- Original research question
+- Question–answer pairs produced by search
+- Raw search results and source metadata
 - Previously identified insights
 
-Your dual role is to:
-
 ANALYSIS:
-1. Extract key insights from all gathered information
-2. Identify patterns and connections across sources
-3. Synthesize findings into coherent understanding
-4. Focus on the most important discoveries
+1. Extract the most important, non‑obvious insights from the collected evidence.
+2. Identify patterns, agreements, and disagreements across sources.
+3. Note material uncertainties and assumptions.
 
 EVALUATION:
-1. Assess if we have sufficient information to answer the original question
-2. Calculate a confidence score (0-1) based on:
-   - Coverage of the main question's aspects
-   - Quality and consistency of sources
-   - Depth of information gathered
-3. Identify specific gaps that still need investigation
-4. Generate up to 3 new sub-questions that haven't been answered yet
-
-Be critical and thorough in your evaluation. Only mark research as sufficient when:
-- All major aspects of the question are addressed
-- Sources provide consistent, reliable information
-- The depth of coverage meets the question's requirements
-- No critical gaps remain
-
-Generate new sub-questions that:
-- Target specific unexplored aspects not covered by existing questions
-- Seek clarification on ambiguities
-- Explore important edge cases or exceptions
-- Are focused and actionable (max 3)
-- Do NOT repeat or rephrase questions that have already been answered (see qa_responses)
-- Should be genuinely new areas to explore
-- Must be standalone, self-contained queries: include entities, scope, and any
-  needed qualifiers (e.g., timeframe, region), and avoid ambiguous pronouns so
-  they can be executed independently."""
-
-SYNTHESIS_AGENT_PROMPT = """You are a synthesis specialist agent focused on creating comprehensive research reports.
-
-Your role is to:
-1. Synthesize all gathered information into a coherent narrative
-2. Present findings in a clear, structured format
-3. Draw evidence-based conclusions
-4. Acknowledge limitations and uncertainties
-5. Provide actionable recommendations
-6. Maintain academic rigor and objectivity
-
-Your report should be:
-- Comprehensive yet concise
-- Well-structured and easy to follow
-- Based solely on evidence from the research
-- Transparent about limitations
-- Professional and objective in tone
-
-Focus on creating a report that provides clear value to the reader by:
-- Answering the original research question thoroughly
-- Highlighting the most important findings
-- Explaining the implications of the research
-- Suggesting concrete next steps"""
+1. Decide if we have sufficient information to answer the original question.
+2. Provide a confidence_score in [0,1] considering:
+   - Coverage of the main question’s aspects
+   - Quality, consistency, and diversity of sources
+   - Depth and specificity of evidence
+3. List concrete gaps that still need investigation.
+4. Propose up to 3 new sub_questions that would close the highest‑value gaps.
+
+Strictness:
+- Only mark research as sufficient when all major aspects are addressed with
+  consistent, reliable evidence and no critical gaps remain.
+
+New sub_questions must:
+- Be genuinely new (not answered or duplicative; check qa_responses).
+- Be standalone and specific (entities, scope, timeframe/region if relevant).
+- Be actionable and scoped to the knowledge base (narrow if necessary).
+- Be ordered by expected impact (most valuable first)."""
+
+SYNTHESIS_AGENT_PROMPT = """You are a synthesis specialist producing the final
+research report.
+
+Goals:
+1. Synthesize all gathered information into a coherent narrative.
+2. Present findings clearly and concisely.
+3. Draw evidence‑based conclusions and recommendations.
+4. State limitations and uncertainties transparently.
+
+Report guidelines (map to output fields):
+- title: concise (5–12 words), informative.
+- executive_summary: 3–5 sentences summarizing the overall answer.
+- main_findings: 4–8 one‑sentence bullets; each reflects evidence from the
+  research (do not include inline citations or snippet text).
+- conclusions: 2–4 bullets that follow logically from findings.
+- recommendations: 2–5 actionable bullets tied to findings.
+- limitations: 1–3 bullets describing key constraints or uncertainties.
+- sources_summary: 2–4 sentences summarizing sources used and their reliability.
+
+Style:
+- Base all content solely on the collected evidence.
+- Be professional, objective, and specific.
+- Avoid meta commentary and refrain from speculation beyond the evidence."""
 
 PRESEARCH_AGENT_PROMPT = """You are a rapid research surveyor.
 
 Task:
-- Call the gather_context tool once with the main question to obtain a
-  relevant texts from the Knowledge Base (KB).
-- Read that context and produce a brief natural-language summary describing
-  what the KB appears to contain relative to the question.
+- Call gather_context once on the main question to obtain relevant text from
+  the knowledge base (KB).
+- Read that context and produce a short natural‑language summary of what the
+  KB appears to contain relative to the question.
 
 Rules:
 - Base the summary strictly on the provided text; do not invent.
-- Output only the summary as plain text (one short paragraph).
-"""
+- Output only the summary as plain text (one short paragraph)."""

haiku/rag/research/state.py

@@ -0,0 +1,25 @@
+from dataclasses import dataclass, field
+
+from rich.console import Console
+
+from haiku.rag.client import HaikuRAG
+from haiku.rag.research.dependencies import ResearchContext
+from haiku.rag.research.models import EvaluationResult
+
+
+@dataclass
+class ResearchDeps:
+    client: HaikuRAG
+    console: Console | None = None
+
+
+@dataclass
+class ResearchState:
+    question: str
+    context: ResearchContext
+    sub_questions: list[str] = field(default_factory=list)
+    iterations: int = 0
+    max_iterations: int = 3
+    max_concurrency: int = 1
+    confidence_threshold: float = 0.8
+    last_eval: EvaluationResult | None = None

{haiku_rag-0.9.3.dist-info → haiku_rag-0.10.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: haiku.rag
-Version: 0.9.3
+Version: 0.10.0
 Summary: Agentic Retrieval Augmented Generation (RAG) with LanceDB
 Author-email: Yiorgis Gozadinos <ggozadinos@gmail.com>
 License: MIT
@@ -23,6 +23,7 @@ Requires-Dist: fastmcp>=2.12.3
 Requires-Dist: httpx>=0.28.1
 Requires-Dist: lancedb>=0.25.0
 Requires-Dist: pydantic-ai>=1.0.8
+Requires-Dist: pydantic-graph>=1.0.8
 Requires-Dist: pydantic>=2.11.9
 Requires-Dist: python-dotenv>=1.1.1
 Requires-Dist: rich>=14.1.0
@@ -48,6 +49,7 @@ Retrieval-Augmented Generation (RAG) library built on LanceDB.
 - **Local LanceDB**: No external servers required, supports also LanceDB cloud storage, S3, Google Cloud & Azure
 - **Multiple embedding providers**: Ollama, VoyageAI, OpenAI, vLLM
 - **Multiple QA providers**: Any provider/model supported by Pydantic AI
+- **Research graph (multi‑agent)**: Plan → Search → Evaluate → Synthesize with agentic AI
 - **Native hybrid search**: Vector + full-text search with native LanceDB RRF reranking
 - **Reranking**: Default search result reranking with MixedBread AI, Cohere, or vLLM
 - **Question answering**: Built-in QA agents on your documents
@@ -75,6 +77,14 @@ haiku-rag ask "Who is the author of haiku.rag?"
 # Ask questions with citations
 haiku-rag ask "Who is the author of haiku.rag?" --cite
 
+# Multi‑agent research (iterative plan/search/evaluate)
+haiku-rag research \
+  "What are the main drivers and trends of global temperature anomalies since 1990?" \
+  --max-iterations 2 \
+  --confidence-threshold 0.8 \
+  --max-concurrency 3 \
+  --verbose
+
 # Rebuild database (re-chunk and re-embed all documents)
 haiku-rag rebuild
 
@@ -90,6 +100,13 @@ haiku-rag serve
 
 ```python
 from haiku.rag.client import HaikuRAG
+from haiku.rag.research import (
+    ResearchContext,
+    ResearchDeps,
+    ResearchState,
+    build_research_graph,
+    PlanNode,
+)
 
 async with HaikuRAG("database.lancedb") as client:
     # Add document
@@ -107,6 +124,25 @@ async with HaikuRAG("database.lancedb") as client:
     # Ask questions with citations
     answer = await client.ask("Who is the author of haiku.rag?", cite=True)
     print(answer)
+
+    # Multi‑agent research pipeline (Plan → Search → Evaluate → Synthesize)
+    graph = build_research_graph()
+    state = ResearchState(
+        question=(
+            "What are the main drivers and trends of global temperature "
+            "anomalies since 1990?"
+        ),
+        context=ResearchContext(original_question="…"),
+        max_iterations=2,
+        confidence_threshold=0.8,
+        max_concurrency=3,
+    )
+    deps = ResearchDeps(client=client)
+    start = PlanNode(provider=None, model=None)
+    result = await graph.run(start, state=state, deps=deps)
+    report = result.output
+    print(report.title)
+    print(report.executive_summary)
 ```
 
 ## MCP Server

{haiku_rag-0.9.3.dist-info → haiku_rag-0.10.0.dist-info}/RECORD

@@ -1,7 +1,7 @@
 haiku/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-haiku/rag/app.py,sha256=nkud-OHic3HIgEEiNOKVvhmW98DPpDe6HokBSz-xV7w,11420
+haiku/rag/app.py,sha256=m5agkPrJhbzEbdC01CU_GR2Gj4voFuAGmxR7DS2K9is,12934
 haiku/rag/chunker.py,sha256=PVe6ysv8UlacUd4Zb3_8RFWIaWDXnzBAy2VDJ4TaUsE,1555
-haiku/rag/cli.py,sha256=3nlzrT5FPCyfnu51KHchLG4Cj2eVv9YsuGHMShBnVb0,9845
+haiku/rag/cli.py,sha256=oXEQoRTlzrrJ9hC27_Dht9ElBb9q_wTEESnXdNy3eW8,10257
 haiku/rag/client.py,sha256=QgJQu7g7JjAzWN6R10NeDqpFf89Dml_LiWce4QRHLHc,21177
 haiku/rag/config.py,sha256=SPEIv2IElZmZh4Wsp8gk7ViRW5ZzD-UGmIqRAXscDdI,2134
 haiku/rag/logging.py,sha256=dm65AwADpcQsH5OAPtRA-4hsw0w5DK-sGOvzYkj6jzw,1720
@@ -22,17 +22,19 @@ haiku/rag/qa/prompts.py,sha256=LhRfDtO8Pb06lpr4PpwEaKUYItZ5OiIkeqcCogcssHY,3347
 haiku/rag/reranking/__init__.py,sha256=IRXHs4qPu6VbGJQpzSwhgtVWWumURH_vEoVFE-extlo,894
 haiku/rag/reranking/base.py,sha256=LM9yUSSJ414UgBZhFTgxGprlRqzfTe4I1vgjricz2JY,405
 haiku/rag/reranking/cohere.py,sha256=1iTdiaa8vvb6oHVB2qpWzUOVkyfUcimVSZp6Qr4aq4c,1049
-haiku/rag/reranking/mxbai.py,sha256=46sVTsTIkzIX9THgM3u8HaEmgY7evvEyB-N54JTHvK8,867
+haiku/rag/reranking/mxbai.py,sha256=uveGFIdmNmepd2EQsvYr64wv0ra2_wB845hdSZXy5Cw,908
 haiku/rag/reranking/vllm.py,sha256=xVGH9ss-ISWdJ5SKUUHUbTqBo7PIEmA_SQv0ScdJ6XA,1479
-haiku/rag/research/__init__.py,sha256=qLF41YayAxW_VeHhuTceVuz9hw1FNbuRV9VMhonUMW0,1078
-haiku/rag/research/base.py,sha256=X5n6myUG_Oz4i8WGfyKZ39YzK13rOkyvwGKwSBfL50k,4043
-haiku/rag/research/dependencies.py,sha256=N7mnFwa_uyWYH0NtbEHp5JJvNGN64Q8HHfY41E8Irx0,2362
-haiku/rag/research/evaluation_agent.py,sha256=VMegemd9Vln3jfZbeHzMfb7rUPFNzNxi5Y_l1zrddl8,2994
-haiku/rag/research/orchestrator.py,sha256=nvSRdIs77kSb1CZaQUYZM_Zl5xLP8K6noVgnixpeLJI,6329
-haiku/rag/research/presearch_agent.py,sha256=MpakZ9HSynv73EnWakwUuytfKpiN_8lEqZlVc3zZjGU,1427
-haiku/rag/research/prompts.py,sha256=pVRB7_b_p3JaLF1bC3ANTbSFY78ypSjDhoq6peoU6jo,5685
-haiku/rag/research/search_agent.py,sha256=xn2MlEyL9te_dtZqTzW81lGw7fYmyUzn26mvzX52hNA,2599
-haiku/rag/research/synthesis_agent.py,sha256=FQCt8wbaaKOwgIOQazTNAmohBMZRUDoVzHkByYhbGg8,2182
+haiku/rag/research/__init__.py,sha256=t4JAmIXcKaWqvpFGX5yaehsNrfblskEMn-4mDmdKn9c,502
+haiku/rag/research/common.py,sha256=EUnsA6VZ3-WMweXESuUYezH1ALit8N38064bsZFqtBE,1688
+haiku/rag/research/dependencies.py,sha256=ZiSQdV6jHti4DuUp4WCaJL73TqYDr5vC8ppB34M2cNg,1639
+haiku/rag/research/graph.py,sha256=m3vDP1nPXWzfS7VeTQzmTOk-lFpoaTvKHvRIF2mbxvs,798
+haiku/rag/research/models.py,sha256=klE2qGF5fom5gJRQzQUbnoGYaXusNKeJ9veeXoYDD5Q,2308
+haiku/rag/research/prompts.py,sha256=v_DZNaKk88CDEF8qt9c-puO6QF-NyBQKnl_mO1pMauY,5013
+haiku/rag/research/state.py,sha256=vFwO8c2JmwwfkELE5Mwjt9Oat-bHn5tayf31MIG2SRs,623
+haiku/rag/research/nodes/evaluate.py,sha256=Cp2J-jXYZothiQV3zRZFaCsBLaUU0Tm_-ri-hlgQQII,2897
+haiku/rag/research/nodes/plan.py,sha256=9AkTls01Q3zTLKGgIgSCX9X4VYC8IWjEWii8A_f77YQ,2439
+haiku/rag/research/nodes/search.py,sha256=lHgDCCL7hQdpQeMK-HVzsF_hH_pIv44xxSIiv1JuvYo,3513
+haiku/rag/research/nodes/synthesize.py,sha256=4acKduqWnE11ML7elUksKLozxzWJTkBLSJ2li_YMxgY,1736
 haiku/rag/store/__init__.py,sha256=hq0W0DAC7ysqhWSP2M2uHX8cbG6kbr-sWHxhq6qQcY0,103
 haiku/rag/store/engine.py,sha256=-3MZJYft2XTWaLuyKha8DKhWQeU5E5CBeskXXF5fXso,9555
 haiku/rag/store/models/__init__.py,sha256=s0E72zneGlowvZrFWaNxHYjOAUjgWdLxzdYsnvNRVlY,88
@@ -44,8 +46,8 @@ haiku/rag/store/repositories/document.py,sha256=m11SamQoGYs5ODfmarJGU1yIcqtgmnba
 haiku/rag/store/repositories/settings.py,sha256=7XMBMavU8zRgdBoQzQg0Obfa7UKjuVnBugidTC6sEW0,5548
 haiku/rag/store/upgrades/__init__.py,sha256=gDOxiq3wdZPr3JoenjNYxx0cpgZJhbaFKNX2fzXRq1Q,1852
 haiku/rag/store/upgrades/v0_9_3.py,sha256=NrjNilQSgDtFWRbL3ZUtzQzJ8tf9u0dDRJtnDFwwbdw,3322
-haiku_rag-0.9.3.dist-info/METADATA,sha256=iCae4YtZ0meIQTZLUNree_-74F3irXvArPvdSxVz8ZM,4681
-haiku_rag-0.9.3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-haiku_rag-0.9.3.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
-haiku_rag-0.9.3.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
-haiku_rag-0.9.3.dist-info/RECORD,,
+haiku_rag-0.10.0.dist-info/METADATA,sha256=QLc8BBJ4WCNEvseyYpWNfkuUfmdxGywD6Jtn0OTsrc0,5879
+haiku_rag-0.10.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+haiku_rag-0.10.0.dist-info/entry_points.txt,sha256=G1U3nAkNd5YDYd4v0tuYFbriz0i-JheCsFuT9kIoGCI,48
+haiku_rag-0.10.0.dist-info/licenses/LICENSE,sha256=eXZrWjSk9PwYFNK9yUczl3oPl95Z4V9UXH7bPN46iPo,1065
+haiku_rag-0.10.0.dist-info/RECORD,,

haiku/rag/research/base.py

@@ -1,130 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import TYPE_CHECKING, Any
-
-from pydantic import BaseModel, Field
-from pydantic_ai import Agent
-from pydantic_ai.models.openai import OpenAIChatModel
-from pydantic_ai.output import ToolOutput
-from pydantic_ai.providers.ollama import OllamaProvider
-from pydantic_ai.providers.openai import OpenAIProvider
-from pydantic_ai.run import AgentRunResult
-
-from haiku.rag.config import Config
-
-if TYPE_CHECKING:
-    from haiku.rag.research.dependencies import ResearchDependencies
-
-
-class BaseResearchAgent[T](ABC):
-    """Base class for all research agents."""
-
-    def __init__(
-        self,
-        provider: str,
-        model: str,
-        output_type: type[T],
-    ):
-        self.provider = provider
-        self.model = model
-        self.output_type = output_type
-
-        model_obj = self._get_model(provider, model)
-
-        # Import deps type lazily to avoid circular import during module load
-        from haiku.rag.research.dependencies import ResearchDependencies
-
-        # If the agent is expected to return plain text, pass `str` directly.
-        # Otherwise, wrap the model with ToolOutput for robust tool-handling retries.
-        agent_output_type: Any
-        if self.output_type is str:  # plain text output
-            agent_output_type = str
-        else:
-            agent_output_type = ToolOutput(self.output_type, max_retries=3)
-
-        self._agent = Agent(
-            model=model_obj,
-            deps_type=ResearchDependencies,
-            output_type=agent_output_type,
-            instructions=self.get_system_prompt(),
-            retries=3,
-        )
-
-        # Register tools
-        self.register_tools()
-
-    def _get_model(self, provider: str, model: str):
-        """Get the appropriate model object for the provider."""
-        if provider == "ollama":
-            return OpenAIChatModel(
-                model_name=model,
-                provider=OllamaProvider(base_url=f"{Config.OLLAMA_BASE_URL}/v1"),
-            )
-        elif provider == "vllm":
-            return OpenAIChatModel(
-                model_name=model,
-                provider=OpenAIProvider(
-                    base_url=f"{Config.VLLM_RESEARCH_BASE_URL or Config.VLLM_QA_BASE_URL}/v1",
-                    api_key="none",
-                ),
-            )
-        else:
-            # For all other providers, use the provider:model format
-            return f"{provider}:{model}"
-
-    @abstractmethod
-    def get_system_prompt(self) -> str:
-        """Return the system prompt for this agent."""
-        pass
-
-    def register_tools(self) -> None:
-        """Register agent-specific tools."""
-        pass
-
-    async def run(
-        self, prompt: str, deps: "ResearchDependencies", **kwargs
-    ) -> AgentRunResult[T]:
-        """Execute the agent."""
-        return await self._agent.run(prompt, deps=deps, **kwargs)
-
-    @property
-    def agent(self) -> Agent[Any, T]:
-        """Access the underlying Pydantic AI agent."""
-        return self._agent
-
-
-class SearchResult(BaseModel):
-    """Standard search result format."""
-
-    content: str
-    score: float
-    document_uri: str
-    metadata: dict[str, Any] = Field(default_factory=dict)
-
-
-class ResearchOutput(BaseModel):
-    """Standard research output format."""
-
-    summary: str
-    detailed_findings: list[str]
-    sources: list[str]
-    confidence: float
-
-
-class SearchAnswer(BaseModel):
-    """Structured output for the SearchSpecialist agent."""
-
-    query: str = Field(description="The search query that was performed")
-    answer: str = Field(description="The answer generated based on the context")
-    context: list[str] = Field(
-        description=(
-            "Only the minimal set of relevant snippets (verbatim) that directly "
-            "support the answer"
-        )
-    )
-    sources: list[str] = Field(
-        description=(
-            "Document URIs corresponding to the snippets actually used in the"
-            " answer (one URI per snippet; omit if none)"
-        ),
-        default_factory=list,
-    )

haiku/rag/research/evaluation_agent.py

@@ -1,85 +0,0 @@
-from pydantic import BaseModel, Field
-from pydantic_ai.run import AgentRunResult
-
-from haiku.rag.research.base import BaseResearchAgent
-from haiku.rag.research.dependencies import (
-    ResearchDependencies,
-    _format_context_for_prompt,
-)
-from haiku.rag.research.prompts import EVALUATION_AGENT_PROMPT
-
-
-class EvaluationResult(BaseModel):
-    """Result of analysis and evaluation."""
-
-    key_insights: list[str] = Field(
-        description="Main insights extracted from the research so far"
-    )
-    new_questions: list[str] = Field(
-        description="New sub-questions to add to the research (max 3)",
-        max_length=3,
-        default=[],
-    )
-    confidence_score: float = Field(
-        description="Confidence level in the completeness of research (0-1)",
-        ge=0.0,
-        le=1.0,
-    )
-    is_sufficient: bool = Field(
-        description="Whether the research is sufficient to answer the original question"
-    )
-    reasoning: str = Field(
-        description="Explanation of why the research is or isn't complete"
-    )
-
-
-class AnalysisEvaluationAgent(BaseResearchAgent[EvaluationResult]):
-    """Agent that analyzes findings and evaluates research completeness."""
-
-    def __init__(self, provider: str, model: str) -> None:
-        super().__init__(provider, model, output_type=EvaluationResult)
-
-    async def run(
-        self, prompt: str, deps: ResearchDependencies, **kwargs
-    ) -> AgentRunResult[EvaluationResult]:
-        console = deps.console
-        if console:
-            console.print(
-                "\n[bold cyan]📊 Analyzing and evaluating research progress...[/bold cyan]"
-            )
-
-        # Format context for the evaluation agent
-        context_xml = _format_context_for_prompt(deps.context)
-        evaluation_prompt = f"""Analyze all gathered information and evaluate the completeness of research.
-
-{context_xml}
-
-Evaluate the research progress for the original question and identify any remaining gaps."""
-
-        result = await super().run(evaluation_prompt, deps, **kwargs)
-        output = result.output
-
-        # Store insights
-        for insight in output.key_insights:
-            deps.context.add_insight(insight)
-
-        # Add new questions to the sub-questions list
-        for new_q in output.new_questions:
-            if new_q not in deps.context.sub_questions:
-                deps.context.sub_questions.append(new_q)
-
-        if console:
-            if output.key_insights:
-                console.print("   [bold]Key insights:[/bold]")
-                for insight in output.key_insights:
-                    console.print(f"   • {insight}")
-            console.print(
-                f"   Confidence: [yellow]{output.confidence_score:.1%}[/yellow]"
-            )
-            status = "[green]Yes[/green]" if output.is_sufficient else "[red]No[/red]"
-            console.print(f"   Sufficient: {status}")
-
-        return result
-
-    def get_system_prompt(self) -> str:
-        return EVALUATION_AGENT_PROMPT