feat: add ragflow integration for #859

agent/memory_manager.py

@@ -50,78 +50,6 @@ def sanitize_context(text: str) -> str:
     return _FENCE_TAG_RE.sub('', text)
 
 
-# ---------------------------------------------------------------------------
-# Prefetch filtering helpers
-# ---------------------------------------------------------------------------
-
-# Meta-instruction debris that memory providers sometimes echo back.
-# These are prompts/instructions, not user-generated content.
-_META_INSTRUCTION_PATTERNS = [
-    re.compile(r"^\s*[\-\*]?\s*>?\s*Focus on:\s*", re.IGNORECASE),
-    re.compile(r"^\s*[\-\*]?\s*>?\s*Note:\s*", re.IGNORECASE),
-    re.compile(r"^\s*[\-\*]?\s*>?\s*System\s+(note|prompt|instruction):", re.IGNORECASE),
-    re.compile(r"^\s*[\-\*]?\s*>?\s*You are\s+", re.IGNORECASE),
-    re.compile(r"^\s*[\-\*]?\s*>?\s*Please\s+(provide|respond|answer|write)", re.IGNORECASE),
-    re.compile(r"^\s*[\-\*]?\s*>?\s*Do not\s+", re.IGNORECASE),
-    re.compile(r"^\s*[\-\*]?\s*>?\s*Always\s+", re.IGNORECASE),
-    re.compile(r"^\s*[\-\*]?\s*>?\s*Consider\s+(the following|these|this)\b", re.IGNORECASE),
-    re.compile(r"^\s*[\-\*]?\s*>?\s*Here\s+(is|are)\s+(some|the|a few)\b", re.IGNORECASE),
-]
-
-
-def _is_meta_instruction_line(line: str) -> bool:
-    """Return True if the line looks like a prompt/template instruction, not memory content."""
-    for pat in _META_INSTRUCTION_PATTERNS:
-        if pat.search(line):
-            return True
-    return False
-
-
-def _is_low_signal_line(line: str) -> bool:
-    """Return True for very short or content-free lines."""
-    stripped = line.strip()
-    # Empty or just punctuation/list marker
-    if not stripped or stripped in {"-", "*", ">", "•", "—", "--"}:
-        return True
-    # Too short to be meaningful (< 15 chars after stripping markers)
-    cleaned = re.sub(r"^[\-\*•>\s]+", "", stripped)
-    if len(cleaned) < 15:
-        return True
-    return False
-
-
-def _filter_prefetch_lines(text: str) -> str:
-    """Filter and deduplicate prefetch result lines.
-
-    Removes:
-      - exact duplicate lines
-      - meta-instruction debris (prompts, templates)
-      - very short / content-free lines
-
-    Returns cleaned text, preserving original line grouping.
-    """
-    if not text or not text.strip():
-        return ""
-
-    seen: set = set()
-    kept: list = []
-    for line in text.splitlines(keepends=False):
-        stripped = line.strip()
-        # Deduplicate exact lines
-        if stripped in seen:
-            continue
-        # Skip meta-instructions
-        if _is_meta_instruction_line(line):
-            continue
-        # Skip low-signal lines
-        if _is_low_signal_line(line):
-            continue
-        seen.add(stripped)
-        kept.append(line)
-
-    return "\n".join(kept)
-
-
 def build_memory_context_block(raw_context: str) -> str:
     """Wrap prefetched memory in a fenced block with system note.
 
@@ -252,14 +180,7 @@ class MemoryManager:
                     "Memory provider '%s' prefetch failed (non-fatal): %s",
                     provider.name, e,
                 )
-        raw = "\n\n".join(parts)
-        if not raw:
-            return ""
-        # Apply line-level filtering: dedupe, strip meta-instructions,
-        # remove very short fragments.  This prevents noisy providers
-        # (e.g. MemPalace transcript recall) from bloating context.
-        filtered = _filter_prefetch_lines(raw)
-        return filtered
+        return "\n\n".join(parts)
 
     def queue_prefetch_all(self, query: str, *, session_id: str = "") -> None:
         """Queue background prefetch on all providers for the next turn."""

docs/ragflow-integration.md

@@ -0,0 +1,68 @@
+# RAGFlow integration
+
+This repo-side slice adds:
+
+- `tools/ragflow_tool.py`
+  - `ragflow_ingest(document_url, dataset)`
+  - `ragflow_query(query, dataset, limit=5)`
+- `scripts/ragflow_bootstrap.py`
+  - fetches the upstream RAGFlow Docker bundle
+  - runs `docker compose --profile cpu up -d` or `gpu`
+
+## Deployment
+
+Bootstrap the upstream CPU stack locally:
+
+```bash
+python3 scripts/ragflow_bootstrap.py --profile cpu
+```
+
+Dry-run only:
+
+```bash
+python3 scripts/ragflow_bootstrap.py --profile cpu --dry-run
+```
+
+Fetch files without launching Docker:
+
+```bash
+python3 scripts/ragflow_bootstrap.py --no-up
+```
+
+Default bundle target:
+
+- `~/.hermes/services/ragflow`
+
+## Runtime configuration
+
+Optional environment variables:
+
+- `RAGFLOW_API_URL` — defaults to `http://localhost:9380`
+- `RAGFLOW_API_KEY` — Bearer token for authenticated RAGFlow APIs
+
+## Supported document types
+
+RAGFlow ingest accepts:
+
+- PDF: `.pdf`
+- Word: `.doc`, `.docx`
+- Presentations: `.ppt`, `.pptx`
+- Images via OCR: `.png`, `.jpg`, `.jpeg`, `.webp`, `.bmp`, `.tif`, `.tiff`, `.gif`
+- Text and codebase documents: `.txt`, `.md`, `.rst`, `.html`, `.json`, `.yaml`, `.yml`, `.toml`, `.ini`, `.py`, `.js`, `.ts`, `.tsx`, `.jsx`, `.java`, `.go`, `.rs`, `.c`, `.cpp`, `.h`, `.hpp`, `.rb`, `.php`, `.sql`, `.sh`
+
+## Example tool usage
+
+```json
+{"document_url":"https://arxiv.org/pdf/1706.03762.pdf","dataset":"research-papers"}
+```
+
+```json
+{"query":"What does the paper say about attention heads?","dataset":"research-papers","limit":5}
+```
+
+## Use cases
+
+- research papers
+- technical documentation
+- OCR-heavy image workflows
+- ingested codebases and architecture docs

scripts/ragflow_bootstrap.py

@@ -0,0 +1,79 @@
+#!/usr/bin/env python3
+"""Bootstrap an upstream RAGFlow Docker bundle for Hermes.
+
+This script fetches the upstream RAGFlow docker bundle into a local directory
+so operators can run `docker compose --profile cpu up -d` (or `gpu`) without
+manually assembling the required files.
+"""
+
+from __future__ import annotations
+
+import argparse
+import subprocess
+import urllib.request
+from pathlib import Path
+
+UPSTREAM_BASE = "https://raw.githubusercontent.com/infiniflow/ragflow/main/docker"
+UPSTREAM_FILES = {
+    "docker-compose.yml": f"{UPSTREAM_BASE}/docker-compose.yml",
+    "docker-compose-base.yml": f"{UPSTREAM_BASE}/docker-compose-base.yml",
+    ".env": f"{UPSTREAM_BASE}/.env",
+    "service_conf.yaml.template": f"{UPSTREAM_BASE}/service_conf.yaml.template",
+    "entrypoint.sh": f"{UPSTREAM_BASE}/entrypoint.sh",
+}
+
+
+def materialize_bundle(target_dir: str | Path, overwrite: bool = False) -> list[Path]:
+    target = Path(target_dir).expanduser()
+    target.mkdir(parents=True, exist_ok=True)
+    written: list[Path] = []
+    for name, url in UPSTREAM_FILES.items():
+        dest = target / name
+        if dest.exists() and not overwrite:
+            written.append(dest)
+            continue
+        with urllib.request.urlopen(url, timeout=60) as response:
+            dest.write_bytes(response.read())
+        if name == "entrypoint.sh":
+            dest.chmod(0o755)
+        written.append(dest)
+    return written
+
+
+def build_compose_command(target_dir: str | Path, profile: str = "cpu") -> list[str]:
+    return ["docker", "compose", "--profile", profile, "up", "-d"]
+
+
+def run_compose(target_dir: str | Path, profile: str = "cpu", dry_run: bool = False) -> dict:
+    target = Path(target_dir).expanduser()
+    command = build_compose_command(target, profile=profile)
+    if dry_run:
+        return {"target_dir": str(target), "command": command, "executed": False}
+    subprocess.run(command, cwd=target, check=True)
+    return {"target_dir": str(target), "command": command, "executed": True}
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description="Fetch and launch the upstream RAGFlow Docker bundle")
+    parser.add_argument("--target-dir", default=str(Path.home() / ".hermes" / "services" / "ragflow"))
+    parser.add_argument("--profile", choices=["cpu", "gpu"], default="cpu")
+    parser.add_argument("--overwrite", action="store_true")
+    parser.add_argument("--dry-run", action="store_true")
+    parser.add_argument("--no-up", action="store_true", help="Only fetch bundle files; do not run docker compose")
+    args = parser.parse_args(argv)
+
+    written = materialize_bundle(args.target_dir, overwrite=args.overwrite)
+    print(f"Fetched {len(written)} RAGFlow docker files into {Path(args.target_dir).expanduser()}")
+    if args.no_up:
+        return 0
+    result = run_compose(args.target_dir, profile=args.profile, dry_run=args.dry_run)
+    print("Command:", " ".join(result["command"]))
+    if result["executed"]:
+        print("RAGFlow docker stack launch requested.")
+    else:
+        print("Dry run only; docker compose not executed.")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

tests/agent/test_memory_provider.py

@@ -198,14 +198,14 @@ class TestMemoryManager:
     def test_prefetch_skips_empty(self):
         mgr = MemoryManager()
         p1 = FakeMemoryProvider("builtin")
-        p1._prefetch_result = "This provider has meaningful memories with enough length"
+        p1._prefetch_result = "Has memories"
         p2 = FakeMemoryProvider("external")
         p2._prefetch_result = ""
         mgr.add_provider(p1)
         mgr.add_provider(p2)
 
         result = mgr.prefetch_all("query")
-        assert result == "This provider has meaningful memories with enough length"
+        assert result == "Has memories"
 
     def test_queue_prefetch_all(self):
         mgr = MemoryManager()
@@ -695,92 +695,3 @@ class TestMemoryContextFencing:
         fence_end = combined.index("</memory-context>")
         assert "Alice" in combined[fence_start:fence_end]
         assert combined.index("weather") < fence_start
-
-
-class TestPrefetchFiltering:
-    """Tests for _filter_prefetch_lines and related helpers."""
-
-    def test_deduplicates_exact_lines(self):
-        from agent.memory_manager import _filter_prefetch_lines
-        raw = "- This is line one with enough characters\n- This is line two with enough characters\n- This is line one with enough characters\n- This is line three with enough characters"
-        result = _filter_prefetch_lines(raw)
-        lines = [l for l in result.splitlines() if l.strip()]
-        assert len(lines) == 3
-        assert "- This is line one with enough characters" in result
-        assert "- This is line two with enough characters" in result
-        assert "- This is line three with enough characters" in result
-
-    def test_removes_meta_instruction_debris(self):
-        from agent.memory_manager import _filter_prefetch_lines
-        raw = (
-            "## Fleet Memories\n"
-            "- > Focus on: was a non-trivial approach used\n"
-            "- > Focus on: was a non-trivial approach used\n"
-            "- Actual memory content about fleet ops\n"
-            "- Note: this is just a note\n"
-        )
-        result = _filter_prefetch_lines(raw)
-        assert "Focus on" not in result
-        assert "Note:" not in result
-        assert "Actual memory content about fleet ops" in result
-        assert "Fleet Memories" in result
-
-    def test_removes_low_signal_short_lines(self):
-        from agent.memory_manager import _filter_prefetch_lines
-        raw = (
-            "- \n"
-            "- x\n"
-            "- This is a meaningful memory entry with enough length\n"
-        )
-        result = _filter_prefetch_lines(raw)
-        assert "- x" not in result
-        assert "meaningful memory entry" in result
-
-    def test_preserves_structured_facts(self):
-        from agent.memory_manager import _filter_prefetch_lines
-        raw = (
-            "## Local Facts (Hologram)\n"
-            "- ALEXANDER: Prefers Gitea for reports and deliverables.\n"
-            "- Telegram home channel is Timmy Time.\n"
-        )
-        result = _filter_prefetch_lines(raw)
-        assert "ALEXANDER" in result
-        assert "Gitea" in result
-        assert "Telegram" in result
-
-    def test_is_meta_instruction_line(self):
-        from agent.memory_manager import _is_meta_instruction_line
-        assert _is_meta_instruction_line("- > Focus on: something") is True
-        assert _is_meta_instruction_line("- Focus on: something") is True
-        assert _is_meta_instruction_line("* Focus on: something") is True
-        assert _is_meta_instruction_line("- Actual user memory content") is False
-        assert _is_meta_instruction_line("ALEXANDER: Prefers Gitea") is False
-
-    def test_is_low_signal_line(self):
-        from agent.memory_manager import _is_low_signal_line
-        assert _is_low_signal_line("- ") is True
-        assert _is_low_signal_line("*") is True
-        assert _is_low_signal_line("- x") is True
-        assert _is_low_signal_line("- Short line") is True
-        assert _is_low_signal_line("- This is a long meaningful memory entry") is False
-
-    def test_prefetch_all_applies_filtering(self):
-        from agent.memory_manager import MemoryManager
-        mgr = MemoryManager()
-        fake = FakeMemoryProvider(name="test")
-        fake._prefetch_result = (
-            "- > Focus on: was a non-trivial approach\n"
-            "- > Focus on: was a non-trivial approach\n"
-            "- Real memory fact\n"
-        )
-        mgr.add_provider(fake)
-        result = mgr.prefetch_all("query")
-        assert "Focus on" not in result
-        assert "Real memory fact" in result
-        assert result.count("Real memory fact") == 1
-
-    def test_empty_prefetch_returns_empty(self):
-        from agent.memory_manager import _filter_prefetch_lines
-        assert _filter_prefetch_lines("") == ""
-        assert _filter_prefetch_lines("   ") == ""
-        assert _filter_prefetch_lines("\n\n") == ""

tests/test_ragflow_bootstrap.py

@@ -0,0 +1,43 @@
+from __future__ import annotations
+
+import importlib.util
+import io
+from pathlib import Path
+from unittest.mock import patch
+
+
+ROOT = Path(__file__).resolve().parent.parent
+SCRIPT_PATH = ROOT / "scripts" / "ragflow_bootstrap.py"
+
+
+def _load_module():
+    spec = importlib.util.spec_from_file_location("ragflow_bootstrap", SCRIPT_PATH)
+    module = importlib.util.module_from_spec(spec)
+    assert spec.loader is not None
+    spec.loader.exec_module(module)
+    return module
+
+
+def test_materialize_bundle_downloads_required_upstream_artifacts(tmp_path):
+    module = _load_module()
+
+    def fake_urlopen(url, timeout=0):
+        name = url.rsplit("/", 1)[-1]
+        return io.BytesIO(f"# fetched {name}\n".encode())
+
+    with patch.object(module.urllib.request, "urlopen", side_effect=fake_urlopen):
+        written = module.materialize_bundle(tmp_path)
+
+    assert (tmp_path / "docker-compose.yml").exists()
+    assert (tmp_path / "docker-compose-base.yml").exists()
+    assert (tmp_path / ".env").exists()
+    assert any(path.name == "entrypoint.sh" for path in written)
+
+
+def test_build_compose_command_respects_profile_and_directory(tmp_path):
+    module = _load_module()
+
+    command = module.build_compose_command(tmp_path, profile="gpu")
+
+    assert command[:4] == ["docker", "compose", "--profile", "gpu"]
+    assert command[-2:] == ["up", "-d"]

tests/tools/test_ragflow_tool.py

@@ -0,0 +1,122 @@
+from __future__ import annotations
+
+import importlib
+import json
+import sys
+from pathlib import Path
+from unittest.mock import patch
+
+from tools.registry import registry
+
+
+class _Response:
+    def __init__(self, payload: dict, status_code: int = 200):
+        self._payload = payload
+        self.status_code = status_code
+        self.text = json.dumps(payload)
+
+    def json(self):
+        return self._payload
+
+    def raise_for_status(self):
+        if self.status_code >= 400:
+            raise RuntimeError(f"HTTP {self.status_code}")
+
+
+def _reload_module():
+    registry.deregister("ragflow_ingest")
+    registry.deregister("ragflow_query")
+    sys.modules.pop("tools.ragflow_tool", None)
+    module = importlib.import_module("tools.ragflow_tool")
+    return importlib.reload(module)
+
+
+def test_ragflow_tools_register_and_support_document_formats():
+    module = _reload_module()
+
+    assert registry.get_entry("ragflow_ingest") is not None
+    assert registry.get_entry("ragflow_query") is not None
+    assert ".pdf" in module.SUPPORTED_EXTENSIONS
+    assert ".docx" in module.SUPPORTED_EXTENSIONS
+    assert ".png" in module.SUPPORTED_EXTENSIONS
+    assert ".md" in module.SUPPORTED_EXTENSIONS
+
+
+def test_ragflow_ingest_creates_dataset_uploads_and_starts_parse(tmp_path):
+    module = _reload_module()
+    document = tmp_path / "paper.pdf"
+    document.write_bytes(b"%PDF-1.7\n")
+    calls: list[tuple[str, str, dict | None, dict | None]] = []
+
+    def fake_request(method, url, *, headers=None, params=None, json=None, files=None, timeout=None):
+        calls.append((method, url, params, json))
+        if method == "GET" and url.endswith("/api/v1/datasets"):
+            return _Response({"code": 0, "data": []})
+        if method == "POST" and url.endswith("/api/v1/datasets"):
+            assert json["name"] == "research-papers"
+            assert json["chunk_method"] == "paper"
+            return _Response({"code": 0, "data": {"id": "ds-1", "name": "research-papers"}})
+        if method == "POST" and url.endswith("/api/v1/datasets/ds-1/documents"):
+            assert files and files[0][0] == "file"
+            return _Response({"code": 0, "data": [{"id": "doc-1", "name": "paper.pdf"}]})
+        if method == "POST" and url.endswith("/api/v1/datasets/ds-1/chunks"):
+            assert json == {"document_ids": ["doc-1"]}
+            return _Response({"code": 0})
+        raise AssertionError(f"Unexpected request: {method} {url}")
+
+    with patch("tools.ragflow_tool.requests.request", side_effect=fake_request):
+        result = json.loads(module.ragflow_ingest_tool(str(document), dataset="research-papers"))
+
+    assert result["dataset_id"] == "ds-1"
+    assert result["document_ids"] == ["doc-1"]
+    assert result["parse_started"] is True
+    assert result["chunk_method"] == "paper"
+    assert calls[0][0] == "GET"
+
+
+def test_ragflow_query_retrieves_chunks_for_named_dataset():
+    module = _reload_module()
+
+    def fake_request(method, url, *, headers=None, params=None, json=None, files=None, timeout=None):
+        if method == "GET" and url.endswith("/api/v1/datasets"):
+            assert params == {"name": "tech-docs"}
+            return _Response({"code": 0, "data": [{"id": "ds-9", "name": "tech-docs"}]})
+        if method == "POST" and url.endswith("/api/v1/retrieval"):
+            assert json["question"] == "How does parsing work?"
+            assert json["dataset_ids"] == ["ds-9"]
+            assert json["page_size"] == 2
+            return _Response(
+                {
+                    "code": 0,
+                    "data": {
+                        "chunks": [
+                            {
+                                "content": "Parsing starts by uploading documents.",
+                                "document_id": "doc-9",
+                                "document_keyword": "guide.md",
+                                "similarity": 0.98,
+                            }
+                        ],
+                        "total": 1,
+                    },
+                }
+            )
+        raise AssertionError(f"Unexpected request: {method} {url}")
+
+    with patch("tools.ragflow_tool.requests.request", side_effect=fake_request):
+        result = json.loads(module.ragflow_query_tool("How does parsing work?", "tech-docs", limit=2))
+
+    assert result["dataset_id"] == "ds-9"
+    assert result["total"] == 1
+    assert result["chunks"][0]["content"] == "Parsing starts by uploading documents."
+
+
+def test_ragflow_ingest_rejects_unsupported_document_types(tmp_path):
+    module = _reload_module()
+    document = tmp_path / "binary.exe"
+    document.write_bytes(b"MZ")
+
+    result = json.loads(module.ragflow_ingest_tool(str(document), dataset="ignored"))
+
+    assert "error" in result
+    assert "Unsupported document type" in result["error"]

tools/ragflow_tool.py

@@ -0,0 +1,344 @@
+#!/usr/bin/env python3
+"""RAGFlow tool integration for document understanding.
+
+Provides two tools:
+- ragflow_ingest(document_url, dataset): upload and parse a document into RAGFlow
+- ragflow_query(query, dataset): retrieve relevant chunks from a dataset
+
+Default deployment target is a local RAGFlow server on http://localhost:9380.
+"""
+
+from __future__ import annotations
+
+import json
+import mimetypes
+import os
+import tempfile
+from pathlib import Path
+from typing import Any
+from urllib.parse import urlparse
+
+import requests
+
+from tools.registry import registry, tool_error, tool_result
+
+RAGFLOW_INGEST_SCHEMA = {
+    "name": "ragflow_ingest",
+    "description": (
+        "Upload a document into a RAGFlow dataset, creating the dataset if needed, "
+        "then trigger parsing so Hermes can query the content later. Supports PDF, "
+        "Word, images via OCR, plus text and code documents."
+    ),
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "document_url": {
+                "type": "string",
+                "description": "HTTP(S) URL, file:// URL, or local filesystem path to the document.",
+            },
+            "dataset": {
+                "type": "string",
+                "description": "Dataset name or id to ingest into. Created automatically when absent.",
+            },
+        },
+        "required": ["document_url", "dataset"],
+    },
+}
+
+RAGFLOW_QUERY_SCHEMA = {
+    "name": "ragflow_query",
+    "description": (
+        "Query a RAGFlow dataset for relevant chunks. Useful for research papers, "
+        "technical docs, OCR-processed images, and ingested codebase documents."
+    ),
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "query": {
+                "type": "string",
+                "description": "Question or search query to run against RAGFlow.",
+            },
+            "dataset": {
+                "type": "string",
+                "description": "Dataset name or id to search.",
+            },
+            "limit": {
+                "type": "integer",
+                "description": "Maximum number of chunks to return.",
+                "default": 5,
+                "minimum": 1,
+                "maximum": 25,
+            },
+        },
+        "required": ["query", "dataset"],
+    },
+}
+
+SUPPORTED_EXTENSIONS = {
+    ".pdf": "paper",
+    ".doc": "paper",
+    ".docx": "paper",
+    ".ppt": "presentation",
+    ".pptx": "presentation",
+    ".png": "picture",
+    ".jpg": "picture",
+    ".jpeg": "picture",
+    ".webp": "picture",
+    ".bmp": "picture",
+    ".tif": "picture",
+    ".tiff": "picture",
+    ".gif": "picture",
+    ".txt": "naive",
+    ".md": "naive",
+    ".rst": "naive",
+    ".html": "naive",
+    ".htm": "naive",
+    ".csv": "table",
+    ".tsv": "table",
+    ".json": "naive",
+    ".yaml": "naive",
+    ".yml": "naive",
+    ".toml": "naive",
+    ".ini": "naive",
+    ".py": "naive",
+    ".js": "naive",
+    ".ts": "naive",
+    ".tsx": "naive",
+    ".jsx": "naive",
+    ".java": "naive",
+    ".go": "naive",
+    ".rs": "naive",
+    ".c": "naive",
+    ".cc": "naive",
+    ".cpp": "naive",
+    ".h": "naive",
+    ".hpp": "naive",
+    ".rb": "naive",
+    ".php": "naive",
+    ".sql": "naive",
+    ".sh": "naive",
+}
+
+
+def _ragflow_base_url() -> str:
+    return os.getenv("RAGFLOW_API_URL", "http://localhost:9380").rstrip("/")
+
+
+def _ragflow_headers(json_body: bool = True) -> dict[str, str]:
+    headers: dict[str, str] = {}
+    api_key = os.getenv("RAGFLOW_API_KEY", "").strip()
+    if api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
+    if json_body:
+        headers["Content-Type"] = "application/json"
+    return headers
+
+
+def _ragflow_check_requirements() -> bool:
+    return True
+
+
+def _request_json(method: str, path: str, *, params=None, json_payload=None, files=None) -> dict[str, Any]:
+    response = requests.request(
+        method,
+        f"{_ragflow_base_url()}{path}",
+        headers=_ragflow_headers(json_body=files is None),
+        params=params,
+        json=json_payload,
+        files=files,
+        timeout=120,
+    )
+    response.raise_for_status()
+    payload = response.json()
+    if payload.get("code", 0) != 0:
+        message = payload.get("message") or payload.get("error") or "RAGFlow request failed"
+        raise RuntimeError(message)
+    return payload
+
+
+def _is_probable_dataset_id(dataset: str) -> bool:
+    compact = dataset.replace("-", "")
+    return len(compact) >= 16 and all(ch.isalnum() for ch in compact)
+
+
+def _resolve_dataset(dataset: str) -> tuple[str, str] | None:
+    dataset = dataset.strip()
+    if not dataset:
+        return None
+    params = {"id": dataset} if _is_probable_dataset_id(dataset) else {"name": dataset}
+    payload = _request_json("GET", "/api/v1/datasets", params=params)
+    data = payload.get("data") or []
+    if not data:
+        return None
+    match = data[0]
+    return match["id"], match.get("name", dataset)
+
+
+def _ensure_dataset(dataset: str, chunk_method: str) -> tuple[str, str]:
+    resolved = _resolve_dataset(dataset)
+    if resolved:
+        return resolved
+    payload = _request_json(
+        "POST",
+        "/api/v1/datasets",
+        json_payload={"name": dataset, "chunk_method": chunk_method},
+    )
+    data = payload.get("data") or {}
+    return data["id"], data.get("name", dataset)
+
+
+def _prepare_document(document_url: str) -> tuple[Path, bool]:
+    parsed = urlparse(document_url)
+    if parsed.scheme in {"http", "https"}:
+        response = requests.get(document_url, timeout=120)
+        response.raise_for_status()
+        suffix = Path(parsed.path).suffix or ".bin"
+        tmp = tempfile.NamedTemporaryFile(delete=False, suffix=suffix)
+        tmp.write(response.content)
+        tmp.flush()
+        tmp.close()
+        return Path(tmp.name), True
+    if parsed.scheme == "file":
+        return Path(parsed.path), False
+    return Path(document_url).expanduser(), False
+
+
+def _detect_chunk_method(path: Path) -> str:
+    extension = path.suffix.lower()
+    if extension not in SUPPORTED_EXTENSIONS:
+        supported = ", ".join(sorted(SUPPORTED_EXTENSIONS))
+        raise ValueError(f"Unsupported document type '{extension or path.name}'. Supported document types: {supported}")
+    return SUPPORTED_EXTENSIONS[extension]
+
+
+def _upload_document(dataset_id: str, path: Path) -> list[str]:
+    mime = mimetypes.guess_type(path.name)[0] or "application/octet-stream"
+    with path.open("rb") as handle:
+        payload = _request_json(
+            "POST",
+            f"/api/v1/datasets/{dataset_id}/documents",
+            files=[("file", (path.name, handle, mime))],
+        )
+    documents = payload.get("data") or []
+    ids = [item["id"] for item in documents if item.get("id")]
+    if not ids:
+        raise RuntimeError("RAGFlow upload did not return any document ids")
+    return ids
+
+
+def ragflow_ingest_tool(document_url: str, dataset: str) -> str:
+    local_path = None
+    should_cleanup = False
+    try:
+        local_path, should_cleanup = _prepare_document(document_url)
+        if not local_path.exists():
+            return tool_error(f"Document not found: {document_url}")
+        chunk_method = _detect_chunk_method(local_path)
+        dataset_id, dataset_name = _ensure_dataset(dataset, chunk_method)
+        document_ids = _upload_document(dataset_id, local_path)
+        _request_json(
+            "POST",
+            f"/api/v1/datasets/{dataset_id}/chunks",
+            json_payload={"document_ids": document_ids},
+        )
+        return tool_result(
+            success=True,
+            dataset_id=dataset_id,
+            dataset_name=dataset_name,
+            document_ids=document_ids,
+            parse_started=True,
+            chunk_method=chunk_method,
+            source=document_url,
+            filename=local_path.name,
+        )
+    except ValueError as exc:
+        return tool_error(str(exc))
+    except Exception as exc:
+        return tool_error(f"RAGFlow ingest failed: {exc}")
+    finally:
+        if should_cleanup and local_path is not None:
+            try:
+                local_path.unlink(missing_ok=True)
+            except Exception:
+                pass
+
+
+def _normalize_chunks(chunks: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    normalized = []
+    for chunk in chunks:
+        normalized.append(
+            {
+                "content": chunk.get("content", ""),
+                "document_id": chunk.get("document_id", ""),
+                "document_name": chunk.get("document_keyword", ""),
+                "similarity": chunk.get("similarity"),
+                "highlight": chunk.get("highlight", ""),
+            }
+        )
+    return normalized
+
+
+def ragflow_query_tool(query: str, dataset: str, limit: int = 5) -> str:
+    try:
+        resolved = _resolve_dataset(dataset)
+        if not resolved:
+            return tool_error(f"RAGFlow dataset not found: {dataset}")
+        dataset_id, dataset_name = resolved
+        payload = _request_json(
+            "POST",
+            "/api/v1/retrieval",
+            json_payload={
+                "question": query,
+                "dataset_ids": [dataset_id],
+                "page_size": max(1, min(int(limit), 25)),
+                "highlight": True,
+                "keyword": True,
+            },
+        )
+        data = payload.get("data") or {}
+        chunks = data.get("chunks") or []
+        return tool_result(
+            success=True,
+            dataset_id=dataset_id,
+            dataset_name=dataset_name,
+            total=data.get("total", len(chunks)),
+            chunks=_normalize_chunks(chunks),
+        )
+    except Exception as exc:
+        return tool_error(f"RAGFlow query failed: {exc}")
+
+
+def _handle_ragflow_ingest(args, **_kwargs):
+    return ragflow_ingest_tool(
+        document_url=args.get("document_url", ""),
+        dataset=args.get("dataset", ""),
+    )
+
+
+def _handle_ragflow_query(args, **_kwargs):
+    return ragflow_query_tool(
+        query=args.get("query", ""),
+        dataset=args.get("dataset", ""),
+        limit=args.get("limit", 5),
+    )
+
+
+registry.register(
+    name="ragflow_ingest",
+    toolset="web",
+    schema=RAGFLOW_INGEST_SCHEMA,
+    handler=_handle_ragflow_ingest,
+    check_fn=_ragflow_check_requirements,
+    requires_env=["RAGFLOW_API_URL", "RAGFLOW_API_KEY"],
+    emoji="📚",
+)
+
+registry.register(
+    name="ragflow_query",
+    toolset="web",
+    schema=RAGFLOW_QUERY_SCHEMA,
+    handler=_handle_ragflow_query,
+    check_fn=_ragflow_check_requirements,
+    requires_env=["RAGFLOW_API_URL", "RAGFLOW_API_KEY"],
+    emoji="🧠",
+)