haiku.rag 0.9.3__tar.gz → 0.10.0__tar.gz

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/.pre-commit-config.yaml

@@ -20,13 +20,3 @@ repos:
     rev: v1.1.399
     hooks:
       - id: pyright
-
-  - repo: https://github.com/RodrigoGonzalez/check-mkdocs
-    rev: v1.2.0
-    hooks:
-      - id: check-mkdocs
-        name: check-mkdocs
-        args: ["--config", "mkdocs.yml"] # Optional, mkdocs.yml is the default
-        # If you have additional plugins or libraries that are not included in
-        # check-mkdocs, add them here
-        additional_dependencies: ["mkdocs-material"]

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/PKG-INFO

@@ -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 → haiku_rag-0.10.0}/README.md

@@ -11,6 +11,7 @@ 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
@@ -38,6 +39,14 @@ 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
 
@@ -53,6 +62,13 @@ 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
@@ -70,6 +86,25 @@ 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-0.10.0/docs/agents.md

@@ -0,0 +1,104 @@
+## Agents
+
+Two agentic flows are provided by haiku.rag:
+
+- Simple QA Agent — a focused question answering agent
+- Research Multi‑Agent — a multi‑step, analyzable research workflow
+
+
+### Simple QA Agent
+
+The simple QA agent answers a single question using the knowledge base. It retrieves relevant chunks, optionally expands context around them, and asks the model to answer strictly based on that context.
+
+Key points:
+
+- Uses a single `search_documents` tool to fetch relevant chunks
+- Can be run with or without inline citations in the prompt
+- Returns a plain string answer
+
+Python usage:
+
+```python
+from haiku.rag.client import HaikuRAG
+from haiku.rag.qa.agent import QuestionAnswerAgent
+
+client = HaikuRAG(path_to_db)
+
+# Choose a provider and model (see Configuration for env defaults)
+agent = QuestionAnswerAgent(
+    client=client,
+    provider="openai",  # or "ollama", "vllm", etc.
+    model="gpt-4o-mini",
+    use_citations=False,  # set True to bias prompt towards citing sources
+)
+
+answer = await agent.answer("What is climate change?")
+print(answer)
+```
+
+### Research Graph
+
+The research workflow is implemented as a typed pydantic‑graph. It plans, searches (in parallel batches), evaluates, and synthesizes into a final report — with clear stop conditions and shared state.
+
+```mermaid
+---
+title: Research graph
+---
+stateDiagram-v2
+  PlanNode --> SearchDispatchNode
+  SearchDispatchNode --> EvaluateNode
+  EvaluateNode --> SearchDispatchNode
+  EvaluateNode --> SynthesizeNode
+  SynthesizeNode --> [*]
+```
+
+Key nodes:
+
+- Plan: builds up to 3 standalone sub‑questions (uses an internal presearch tool)
+- Search (batched): answers sub‑questions using the KB with minimal, verbatim context
+- Evaluate: extracts insights, proposes new questions, and checks sufficiency/confidence
+- Synthesize: generates a final structured report
+
+Primary models:
+
+- `SearchAnswer` — one per sub‑question (query, answer, context, sources)
+- `EvaluationResult` — insights, new questions, sufficiency, confidence
+- `ResearchReport` — final report (title, executive summary, findings, conclusions, …)
+
+CLI usage:
+
+```bash
+haiku-rag research "How does haiku.rag organize and query documents?" \
+  --max-iterations 2 \
+  --confidence-threshold 0.8 \
+  --max-concurrency 3 \
+  --verbose
+```
+
+Python usage:
+
+```python
+from haiku.rag.client import HaikuRAG
+from haiku.rag.research import (
+    ResearchContext,
+    ResearchDeps,
+    ResearchState,
+    build_research_graph,
+    PlanNode,
+)
+
+async with HaikuRAG(path_to_db) as client:
+    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)
+    result = await graph.run(PlanNode(provider=None, model=None), state=state, deps=deps)
+    report = result.output
+    print(report.title)
+    print(report.executive_summary)
+```

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/docs/cli.md

@@ -84,6 +84,24 @@ haiku-rag ask "Who is the author of haiku.rag?" --cite
 
 The QA agent will search your documents for relevant information and provide a comprehensive answer. With `--cite`, responses include citations showing which documents were used.
 
+## Research
+
+Run the multi-step research graph:
+
+```bash
+haiku-rag research "How does haiku.rag organize and query documents?" \
+  --max-iterations 2 \
+  --confidence-threshold 0.8 \
+  --max-concurrency 3 \
+  --verbose
+```
+
+Flags:
+- `--max-iterations, -n`: maximum search/evaluate cycles (default: 3)
+- `--confidence-threshold`: stop once evaluation confidence meets/exceeds this (default: 0.8)
+- `--max-concurrency`: number of sub-questions searched in parallel each iteration (default: 3)
+- `--verbose`: show planning, searching previews, evaluation summary, and stop reason
+
 ## Server
 
 Start the MCP server:

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/mkdocs.yml

@@ -76,4 +76,8 @@ markdown_extensions:
       use_pygments: true
   - pymdownx.inlinehilite
   - pymdownx.snippets
-  - pymdownx.superfences
+  - pymdownx.superfences:
+      custom_fences:
+        - name: mermaid
+          class: mermaid
+          format: !!python/name:pymdownx.superfences.fence_code_format

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/pyproject.toml

@@ -2,7 +2,7 @@
 
 name = "haiku.rag"
 description = "Agentic Retrieval Augmented Generation (RAG) with LanceDB"
-version = "0.9.3"
+version = "0.10.0"
 authors = [{ name = "Yiorgis Gozadinos", email = "ggozadinos@gmail.com" }]
 license = { text = "MIT" }
 readme = { file = "README.md", content-type = "text/markdown" }
@@ -29,6 +29,7 @@ dependencies = [
     "lancedb>=0.25.0",
     "pydantic>=2.11.9",
     "pydantic-ai>=1.0.8",
+    "pydantic-graph>=1.0.8",
     "python-dotenv>=1.1.1",
     "rich>=14.1.0",
     "tiktoken>=0.11.0",
@@ -90,6 +91,7 @@ line-ending = "auto"
 [tool.pyright]
 venvPath = "."
 venv = ".venv"
+pythonVersion = "3.12"
 
 [tool.pytest.ini_options]
 asyncio_default_fixture_loop_scope = "session"

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/src/haiku/rag/app.py

@@ -9,7 +9,13 @@ from haiku.rag.client import HaikuRAG
 from haiku.rag.config import Config
 from haiku.rag.mcp import create_mcp_server
 from haiku.rag.monitor import FileWatcher
-from haiku.rag.research.orchestrator import ResearchOrchestrator
+from haiku.rag.research.dependencies import ResearchContext
+from haiku.rag.research.graph import (
+    PlanNode,
+    ResearchDeps,
+    ResearchState,
+    build_research_graph,
+)
 from haiku.rag.store.models.chunk import Chunk
 from haiku.rag.store.models.document import Document
 
@@ -80,29 +86,54 @@ class HaikuRAGApp:
                 self.console.print(f"[red]Error: {e}[/red]")
 
     async def research(
-        self, question: str, max_iterations: int = 3, verbose: bool = False
+        self,
+        question: str,
+        max_iterations: int = 3,
+        confidence_threshold: float = 0.8,
+        max_concurrency: int = 1,
+        verbose: bool = False,
     ):
-        """Run multi-agent research on a question."""
+        """Run research via the pydantic-graph pipeline (default)."""
         async with HaikuRAG(db_path=self.db_path) as client:
             try:
-                # Create orchestrator with default config or fallback to QA
-                orchestrator = ResearchOrchestrator()
-
                 if verbose:
-                    self.console.print(
-                        f"[bold cyan]Starting research with {orchestrator.provider}:{orchestrator.model}[/bold cyan]"
-                    )
+                    self.console.print("[bold cyan]Starting research[/bold cyan]")
                     self.console.print(f"[bold blue]Question:[/bold blue] {question}")
                     self.console.print()
 
-                # Conduct research
-                report = await orchestrator.conduct_research(
+                graph = build_research_graph()
+                state = ResearchState(
                     question=question,
-                    client=client,
+                    context=ResearchContext(original_question=question),
                     max_iterations=max_iterations,
-                    verbose=verbose,
+                    confidence_threshold=confidence_threshold,
+                    max_concurrency=max_concurrency,
+                )
+                deps = ResearchDeps(
+                    client=client, console=self.console if verbose else None
                 )
 
+                start = PlanNode(
+                    provider=Config.RESEARCH_PROVIDER or Config.QA_PROVIDER,
+                    model=Config.RESEARCH_MODEL or Config.QA_MODEL,
+                )
+                # Prefer graph.run; fall back to iter if unavailable
+                report = None
+                try:
+                    result = await graph.run(start, state=state, deps=deps)
+                    report = result.output
+                except Exception:
+                    from pydantic_graph import End
+
+                    async with graph.iter(start, state=state, deps=deps) as run:
+                        node = run.next_node
+                        while not isinstance(node, End):
+                            node = await run.next(node)
+                        if run.result:
+                            report = run.result.output
+                if report is None:
+                    raise RuntimeError("Graph did not produce a report")
+
                 # Display the report
                 self.console.print("[bold green]Research Report[/bold green]")
                 self.console.rule()
@@ -114,6 +145,12 @@ class HaikuRAGApp:
                 self.console.print(report.executive_summary)
                 self.console.print()
 
+                # Confidence (from last evaluation)
+                if state.last_eval:
+                    conf = state.last_eval.confidence_score  # type: ignore[attr-defined]
+                    self.console.print(f"[bold cyan]Confidence:[/bold cyan] {conf:.1%}")
+                    self.console.print()
+
                 # Main Findings
                 if report.main_findings:
                     self.console.print("[bold cyan]Main Findings:[/bold cyan]")

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/src/haiku/rag/cli.py

@@ -13,10 +13,10 @@ from haiku.rag.logging import configure_cli_logging
 from haiku.rag.migration import migrate_sqlite_to_lancedb
 from haiku.rag.utils import is_up_to_date
 
-logfire.configure(send_to_logfire="if-token-present")
-logfire.instrument_pydantic_ai()
-
-if not Config.ENV == "development":
+if Config.ENV == "development":
+    logfire.configure(send_to_logfire="if-token-present")
+    logfire.instrument_pydantic_ai()
+else:
     warnings.filterwarnings("ignore")
 
 cli = typer.Typer(
@@ -250,6 +250,16 @@ def research(
         "-n",
         help="Maximum search/analyze iterations",
     ),
+    confidence_threshold: float = typer.Option(
+        0.8,
+        "--confidence-threshold",
+        help="Minimum confidence (0-1) to stop",
+    ),
+    max_concurrency: int = typer.Option(
+        1,
+        "--max-concurrency",
+        help="Max concurrent searches per iteration (planned)",
+    ),
     db: Path = typer.Option(
         Config.DEFAULT_DATA_DIR / "haiku.rag.lancedb",
         "--db",
@@ -266,6 +276,8 @@ def research(
         app.research(
             question=question,
             max_iterations=max_iterations,
+            confidence_threshold=confidence_threshold,
+            max_concurrency=max_concurrency,
             verbose=verbose,
         )
     )

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/src/haiku/rag/reranking/mxbai.py

@@ -1,4 +1,4 @@
-from mxbai_rerank import MxbaiRerankV2
+from mxbai_rerank import MxbaiRerankV2  # pyright: ignore[reportMissingImports]
 
 from haiku.rag.config import Config
 from haiku.rag.reranking.base import RerankerBase

haiku_rag-0.10.0/src/haiku/rag/research/__init__.py

@@ -0,0 +1,20 @@
+from haiku.rag.research.dependencies import ResearchContext, ResearchDependencies
+from haiku.rag.research.graph import (
+    PlanNode,
+    ResearchDeps,
+    ResearchState,
+    build_research_graph,
+)
+from haiku.rag.research.models import EvaluationResult, ResearchReport, SearchAnswer
+
+__all__ = [
+    "ResearchDependencies",
+    "ResearchContext",
+    "SearchAnswer",
+    "EvaluationResult",
+    "ResearchReport",
+    "ResearchDeps",
+    "ResearchState",
+    "PlanNode",
+    "build_research_graph",
+]

haiku_rag-0.10.0/src/haiku/rag/research/common.py

@@ -0,0 +1,53 @@
+from typing import Any
+
+from pydantic_ai import format_as_xml
+from pydantic_ai.models.openai import OpenAIChatModel
+from pydantic_ai.providers.ollama import OllamaProvider
+from pydantic_ai.providers.openai import OpenAIProvider
+
+from haiku.rag.config import Config
+from haiku.rag.research.dependencies import ResearchContext
+
+
+def get_model(provider: str, model: str) -> Any:
+    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:
+        return f"{provider}:{model}"
+
+
+def log(console, msg: str) -> None:
+    if console:
+        console.print(msg)
+
+
+def format_context_for_prompt(context: ResearchContext) -> str:
+    """Format the research context as XML for inclusion in prompts."""
+
+    context_data = {
+        "original_question": context.original_question,
+        "unanswered_questions": context.sub_questions,
+        "qa_responses": [
+            {
+                "question": qa.query,
+                "answer": qa.answer,
+                "context_snippets": qa.context,
+                "sources": qa.sources,  # pyright: ignore[reportAttributeAccessIssue]
+            }
+            for qa in context.qa_responses
+        ],
+        "insights": context.insights,
+        "gaps": context.gaps,
+    }
+    return format_as_xml(context_data, root_tag="research_context")

{haiku_rag-0.9.3 → haiku_rag-0.10.0}/src/haiku/rag/research/dependencies.py

@@ -1,9 +1,8 @@
 from pydantic import BaseModel, Field
-from pydantic_ai import format_as_xml
 from rich.console import Console
 
 from haiku.rag.client import HaikuRAG
-from haiku.rag.research.base import SearchAnswer
+from haiku.rag.research.models import SearchAnswer
 
 
 class ResearchContext(BaseModel):
@@ -13,7 +12,7 @@ class ResearchContext(BaseModel):
     sub_questions: list[str] = Field(
         default_factory=list, description="Decomposed sub-questions"
     )
-    qa_responses: list["SearchAnswer"] = Field(
+    qa_responses: list[SearchAnswer] = Field(
         default_factory=list, description="Structured QA pairs used during research"
     )
     insights: list[str] = Field(
@@ -23,7 +22,7 @@ class ResearchContext(BaseModel):
         default_factory=list, description="Identified information gaps"
     )
 
-    def add_qa_response(self, qa: "SearchAnswer") -> None:
+    def add_qa_response(self, qa: SearchAnswer) -> None:
         """Add a structured QA response (minimal context already included)."""
         self.qa_responses.append(qa)
 
@@ -46,24 +45,3 @@ class ResearchDependencies(BaseModel):
     client: HaikuRAG = Field(description="RAG client for document operations")
     context: ResearchContext = Field(description="Shared research context")
     console: Console | None = None
-
-
-def _format_context_for_prompt(context: ResearchContext) -> str:
-    """Format the research context as XML for inclusion in prompts."""
-
-    context_data = {
-        "original_question": context.original_question,
-        "unanswered_questions": context.sub_questions,
-        "qa_responses": [
-            {
-                "question": qa.query,
-                "answer": qa.answer,
-                "context_snippets": qa.context,
-                "sources": qa.sources,
-            }
-            for qa in context.qa_responses
-        ],
-        "insights": context.insights,
-        "gaps": context.gaps,
-    }
-    return format_as_xml(context_data, root_tag="research_context")

haiku_rag-0.10.0/src/haiku/rag/research/graph.py

@@ -0,0 +1,29 @@
+from pydantic_graph import Graph
+
+from haiku.rag.research.models import ResearchReport
+from haiku.rag.research.nodes.evaluate import EvaluateNode
+from haiku.rag.research.nodes.plan import PlanNode
+from haiku.rag.research.nodes.search import SearchDispatchNode
+from haiku.rag.research.nodes.synthesize import SynthesizeNode
+from haiku.rag.research.state import ResearchDeps, ResearchState
+
+__all__ = [
+    "PlanNode",
+    "SearchDispatchNode",
+    "EvaluateNode",
+    "SynthesizeNode",
+    "ResearchState",
+    "ResearchDeps",
+    "build_research_graph",
+]
+
+
+def build_research_graph() -> Graph[ResearchState, ResearchDeps, ResearchReport]:
+    return Graph(
+        nodes=[
+            PlanNode,
+            SearchDispatchNode,
+            EvaluateNode,
+            SynthesizeNode,
+        ]
+    )