Spaces:
Running
Running
Shoufa Zhang
Deploy DocMorph & SeekMorph interactive Studio and 5-layer production benchmark
66227f0 Download docmorph/agent.py from zhangshoufa/DocMorph: direct link, hf CLI and curl.
- Browser
- Download file 5.75 kB
-
https://huggingface.co/spaces/zhangshoufa/DocMorph/resolve/main/docmorph/agent.py
- Command line
-
hf download hf://spaces/zhangshoufa/DocMorph/docmorph/agent.py
-
curl -L -o agent.py https://huggingface.co/spaces/zhangshoufa/DocMorph/resolve/main/docmorph/agent.py
5.75 kB
| """Agent function-calling schema, RAG tool executor, and parallel tool-call message normalizer.""" | |
| from __future__ import annotations | |
| import copy | |
| import json | |
| from typing import Any | |
| from docmorph.index import HybridIndex | |
| class DocMorphAgentToolkit: | |
| """Exposes a HybridIndex as an OpenAI / Qwen / MCP compatible function-calling tool.""" | |
| def __init__(self, index: HybridIndex, default_namespace: str | None = None) -> None: | |
| self.index = index | |
| self.default_namespace = default_namespace | |
| def tool_schema(name: str = "search_knowledge_base") -> dict[str, Any]: | |
| """Return an OpenAI-compatible function tool schema for searching the DocMorph index.""" | |
| return { | |
| "type": "function", | |
| "function": { | |
| "name": name, | |
| "description": ( | |
| "Search structured technical documents, tables, and code blocks in the DocMorph knowledge base " | |
| "and return section-cited passages." | |
| ), | |
| "parameters": { | |
| "type": "object", | |
| "properties": { | |
| "query": { | |
| "type": "string", | |
| "description": "Search query keywords or natural-language question.", | |
| }, | |
| "top_k": { | |
| "type": "integer", | |
| "description": "Maximum number of chunks to return (default: 5).", | |
| "default": 5, | |
| }, | |
| "namespace": { | |
| "type": "string", | |
| "description": "Optional project/tenant namespace filter.", | |
| }, | |
| "expand_window": { | |
| "type": "integer", | |
| "description": "Number of neighboring chunks in the same section to include (default: 0).", | |
| "default": 0, | |
| }, | |
| }, | |
| "required": ["query"], | |
| }, | |
| }, | |
| } | |
| def execute_tool_call(self, arguments: str | dict[str, Any]) -> str: | |
| """Execute a search tool call and format the results with section breadcrumbs.""" | |
| if isinstance(arguments, str): | |
| try: | |
| args = json.loads(arguments) if arguments.strip() else {} | |
| except json.JSONDecodeError as exc: | |
| return f"(invalid JSON arguments: {exc.msg})" | |
| else: | |
| args = dict(arguments) | |
| query = str(args.get("query") or "").strip() | |
| if not query: | |
| return "(missing required argument: 'query')" | |
| top_k = int(args.get("top_k", 5)) | |
| namespace = args.get("namespace") or self.default_namespace | |
| expand_window = int(args.get("expand_window", 0)) | |
| hits = self.index.search( | |
| query, | |
| top_k=top_k, | |
| namespace=namespace, | |
| expand_window=expand_window, | |
| ) | |
| if not hits: | |
| return f"No matching documents found for query: {query!r}" | |
| return "\n\n---\n\n".join(hit.format_citation(rank=i + 1) for i, hit in enumerate(hits)) | |
| def normalize_parallel_tool_calls(messages: list[dict[str, Any]]) -> list[dict[str, Any]]: | |
| """Ensure every parallel tool call in an OpenAI-formatted conversation has a unique ID and bound response.""" | |
| normalized: list[dict[str, Any]] = [] | |
| used_ids: set[str] = set() | |
| counter = 1 | |
| pending_calls: list[dict[str, str]] = [] | |
| for raw in messages: | |
| msg = copy.deepcopy(raw) | |
| role = msg.get("role") | |
| if role == "assistant" and isinstance(msg.get("tool_calls"), list): | |
| pending_calls = [] | |
| for tc in msg["tool_calls"]: | |
| raw_id = str(tc.get("id") or "").strip() | |
| fn_name = str((tc.get("function") or {}).get("name") or "") | |
| if not raw_id or raw_id in used_ids: | |
| while f"call_{counter}" in used_ids: | |
| counter += 1 | |
| assigned_id = f"call_{counter}" | |
| counter += 1 | |
| else: | |
| assigned_id = raw_id | |
| used_ids.add(assigned_id) | |
| tc["id"] = assigned_id | |
| pending_calls.append({"raw_id": raw_id, "assigned_id": assigned_id, "name": fn_name}) | |
| normalized.append(msg) | |
| elif role in ("tool", "function"): | |
| raw_id = str(msg.get("tool_call_id") or msg.get("id") or "").strip() | |
| fn_name = str(msg.get("name") or "") | |
| matched_idx: int | None = None | |
| if raw_id: | |
| for i, item in enumerate(pending_calls): | |
| if item["assigned_id"] == raw_id or item["raw_id"] == raw_id: | |
| matched_idx = i | |
| break | |
| if matched_idx is None and fn_name: | |
| for i, item in enumerate(pending_calls): | |
| if item["name"] == fn_name: | |
| matched_idx = i | |
| break | |
| if matched_idx is None and pending_calls: | |
| matched_idx = 0 | |
| if matched_idx is not None: | |
| bound = pending_calls.pop(matched_idx)["assigned_id"] | |
| else: | |
| while f"call_{counter}" in used_ids: | |
| counter += 1 | |
| bound = f"call_{counter}" | |
| counter += 1 | |
| used_ids.add(bound) | |
| msg["tool_call_id"] = bound | |
| normalized.append(msg) | |
| else: | |
| normalized.append(msg) | |
| return normalized | |