Hypergraph is more powerful. Transform unstructured text into structured knowledge with LLMs. Graphs, hypergraphs, and spatio-temporal extractions — with one command.
feat: add Runcrate provider preset
Nirupam Bhowmick48a9baeb6295
diff --git a/docs/en/cli/commands/config.md b/docs/en/cli/commands/config.mdindex 57d8315..814697c 100644--- a/docs/en/cli/commands/config.md+++ b/docs/en/cli/commands/config.md@@ -31,6 +31,7 @@ Initialize configuration. This is the **lazy one-step setup** — if you pass `-- **Anthropic preset**: `claude-opus-4-8` (LLM only — no embedder preset, pair with an OpenAI-compatible embedder)- **OrcaRouter preset**: `orcarouter/auto` (OpenAI-compatible gateway; key `ORCAROUTER_API_KEY`)- **Atlas Cloud preset**: `deepseek-ai/deepseek-v4-flash` (LLM only — no embedder preset, pair with an OpenAI-compatible embedder; key `ATLASCLOUD_API_KEY`)+- **Runcrate preset**: `deepseek-ai/DeepSeek-V4.1-Flash` + `BAAI/bge-m3` (LLM and embedder on one key `RUNCRATE_API_KEY`)- **Google Gemini preset**: `gemini-3.8-flash` (LLM only — no embedder preset, pair with an OpenAI-compatible embedder; alias `gemini`)```bash@@ -41,7 +42,7 @@ he config init [OPTIONS]| Option | Short | Description ||--------|-------|-------------|-| `--provider` | `-p` | Provider preset (`openai` / `anthropic` / `google` / `orcarouter` / `atlascloud` / `deepseek` / `bailian` / `vllm`) |+| `--provider` | `-p` | Provider preset (`openai` / `anthropic` / `google` / `orcarouter` / `atlascloud` / `runcrate` / `deepseek` / `bailian` / `vllm`) || `--api-key` | `-k` | API key for both LLM and embedder || `--base-url` | `-u` | Custom API base URL (optional) |@@ -71,6 +72,9 @@ he config init -p orcarouter -k or-your-orcarouter-keyhe config llm -p atlascloud -k your-atlascloud-keyhe config embedder -p openai -k sk-your-openai-key+# Runcrate (LLM and embedder on one key)+he config init -p runcrate -k your-runcrate-key+# Google Gemini (LLM only — pair with an OpenAI-compatible embedder)he config llm -p google -k your-google-api-keyhe config embedder -p openai -k sk-your-openai-key@@ -128,7 +132,7 @@ he config llm [OPTIONS]| Option | Short | Description ||--------|-------|-------------|-| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `google`, `orcarouter`, `atlascloud`, `deepseek`, `bailian`, `vllm`) |+| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `google`, `orcarouter`, `atlascloud`, `runcrate`, `deepseek`, `bailian`, `vllm`) || `--api-key` | `-k` | LLM API key || `--model` | `-m` | LLM model name || `--base-url` | `-u` | Custom API base URL |@@ -171,7 +175,7 @@ he config embedder [OPTIONS]| Option | Short | Description ||--------|-------|-------------|-| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `google`, `orcarouter`, `atlascloud`, `deepseek`, `bailian`, `vllm`) |+| `--provider` | `-p` | Provider preset (e.g. `openai`, `anthropic`, `google`, `orcarouter`, `atlascloud`, `runcrate`, `deepseek`, `bailian`, `vllm`) || `--api-key` | `-k` | Embedder API key || `--model` | `-m` | Embedder model name || `--base-url` | `-u` | Custom API base URL |diff --git a/docs/en/concepts/provider-system.md b/docs/en/concepts/provider-system.mdindex c5c2629..0cb094a 100644--- a/docs/en/concepts/provider-system.md+++ b/docs/en/concepts/provider-system.md@@ -1,6 +1,6 @@# Provider System-Hyper-Extract supports these ways to connect to LLMs: **OpenAI**, **Anthropic**, **Google Gemini**, **Alibaba Bailian**, **DeepSeek**, **OrcaRouter**, **Atlas Cloud**, **Cheaper Inference**, and **local vLLM**. All use the same `create_client()` interface — only the first line changes.+Hyper-Extract supports these ways to connect to LLMs: **OpenAI**, **Anthropic**, **Google Gemini**, **Alibaba Bailian**, **DeepSeek**, **OrcaRouter**, **Atlas Cloud**, **Runcrate**, **Cheaper Inference**, and **local vLLM**. All use the same `create_client()` interface — only the first line changes.---@@ -17,6 +17,7 @@ Hyper-Extract supports these ways to connect to LLMs: **OpenAI**, **Anthropic**,| **OrcaRouter** | `orcarouter/auto`, `openai/gpt-4o-mini`, `anthropic/claude-haiku-4-5`, `deepseek/...`, `gemini/...` | ✅ | ✅ | OpenAI-compatible gateway routing 150+ models from OpenAI, Anthropic, Google, DeepSeek, Qwen, MiniMax, xAI behind one endpoint and key. Keys: `ORCAROUTER_API_KEY` || **Cheaper Inference** | gpt-5.4-mini | ✅ | ✅ | OpenAI-compatible gateway. One key gives access to models from several labs. LLM only — no embeddings API (pair with an OpenAI-compatible embedder). Keys: `CHEAPER_INFERENCE_API_KEY` || **Atlas Cloud** | `deepseek-ai/deepseek-v4-flash`, `deepseek-ai/deepseek-v4-pro`, `moonshotai/kimi-k3`, `qwen/qwen3.5-plus`, `openai/gpt-5.5`, `anthropic/claude-sonnet-4.6` | ✅ | ✅ | OpenAI-compatible gateway serving DeepSeek, Z.ai, Moonshot, Qwen, MiniMax, OpenAI, Anthropic and Google models under vendor-prefixed ids. LLM only — no embeddings API. `glm-5.x` models reject the forced `tool_choice` structured extraction uses; pick another model. Keys: `ATLASCLOUD_API_KEY` |+| **Runcrate** | `deepseek-ai/DeepSeek-V4.1-Flash`, `openai/gpt-oss-120b` | ✅ | ✅ | OpenAI-compatible API for open models under vendor-prefixed ids. Also serves embeddings (`BAAI/bge-m3`, 1024 dims), so one key covers the LLM and the embedder. Open models are free with your GitHub account. `zai-org/GLM-5.x` returned an empty graph in testing; pick another model. Keys: `RUNCRATE_API_KEY` || **Alibaba Bailian** | qwen-plus / qwen-turbo / qwen3.6-plus / deepseek-r1 | ✅ | ✅ | Works out of the box || **Alibaba Bailian** | qwen-max / deepseek-v3 | ❌ | ❌ | Only `json_object`; not compatible with function-calling structured output |@@ -91,6 +92,14 @@ llm, emb = create_client(embedder="openai:text-embedding-3-small",)+# Runcrate — OpenAI-compatible API for open models with vendor-prefixed ids.+# Serves embeddings too, so one key covers both.+# Key: RUNCRATE_API_KEY. Override model with "runcrate:openai/gpt-oss-120b".+llm, emb = create_client(+ llm="runcrate", # default model: deepseek-ai/DeepSeek-V4.1-Flash+ embedder="runcrate", # default embedder: BAAI/bge-m3+)+# Cheaper Inference — OpenAI-compatible gateway, one key for models from# several labs. No embeddings API, so pair it with an OpenAI-compatible embedder.# Key: CHEAPER_INFERENCE_API_KEY. Override model with "cheaperinference:gpt-5.4".diff --git a/docs/en/python/guides/provider-configuration.md b/docs/en/python/guides/provider-configuration.mdindex cbe1dd1..6b95960 100644--- a/docs/en/python/guides/provider-configuration.md+++ b/docs/en/python/guides/provider-configuration.md@@ -1,6 +1,6 @@# Provider Configuration Guide-Configure Hyper-Extract to work with OpenAI, Bailian (Alibaba Cloud), DeepSeek, OrcaRouter, Atlas Cloud, Cheaper Inference, or local vLLM deployments.+Configure Hyper-Extract to work with OpenAI, Bailian (Alibaba Cloud), DeepSeek, OrcaRouter, Atlas Cloud, Runcrate, Cheaper Inference, or local vLLM deployments.---@@ -78,7 +78,21 @@ llm, emb = create_client(embedder="openai:text-embedding-3-small",)# Or override the model: create_client(llm="atlascloud:moonshotai/kimi-k3", ...)-# Avoid glm-5.x here: it rejects the forced tool_choice that extraction uses.+```++### Runcrate++```python+from hyperextract import create_client++# Runcrate is an OpenAI-compatible API for open models with vendor-prefixed ids.+# It also serves embeddings, so one key covers the LLM and the embedder.+# Key: RUNCRATE_API_KEY.+llm, emb = create_client(+ llm="runcrate", # default model: deepseek-ai/DeepSeek-V4.1-Flash+ embedder="runcrate", # default embedder: BAAI/bge-m3+)+# Or override the model: create_client(llm="runcrate:openai/gpt-oss-120b", ...)```### Cheaper Inference@@ -137,6 +151,7 @@ print(f"Nodes: {len(graph.nodes)}, Edges: {len(graph.edges)}")| **OrcaRouter** | `he config init -p orcarouter -k sk-orca-xxx` || **Cheaper Inference** | `he config llm -p cheaperinference -m gpt-5.4-mini -k ci_live_xxx` + `he config embedder -p openai -k sk-xxx` || **Atlas Cloud** | `he config llm -p atlascloud -k xxx` + `he config embedder -p openai -k sk-xxx` |+| **Runcrate** | `he config init -p runcrate -k rc_live_xxx` || **vLLM** | `he config init` → select "local vLLM" || **Mixed** (LLM=Bailian, Embedder=vLLM) | `he config llm -p bailian -k sk-xxx` + `he config embedder -p vllm -u http://localhost:8001/v1 -k dummy` |diff --git a/docs/zh/cli/commands/config.md b/docs/zh/cli/commands/config.mdindex 837662f..857a3a0 100644--- a/docs/zh/cli/commands/config.md+++ b/docs/zh/cli/commands/config.md@@ -31,6 +31,7 @@ he config [COMMAND] [OPTIONS]- **Anthropic preset**: `claude-opus-4-8`(仅 LLM —— 无嵌入预设,请搭配 OpenAI 兼容嵌入器)- **OrcaRouter preset**: `orcarouter/auto`(OpenAI 兼容网关;密钥 `ORCAROUTER_API_KEY`)- **Atlas Cloud preset**: `deepseek-ai/deepseek-v4-flash`(仅 LLM —— 无嵌入预设,请搭配 OpenAI 兼容嵌入器;密钥 `ATLASCLOUD_API_KEY`)+- **Runcrate preset**: `deepseek-ai/DeepSeek-V4.1-Flash` + `BAAI/bge-m3`(LLM 与嵌入器共用一个密钥 `RUNCRATE_API_KEY`)- **Google Gemini preset**: `gemini-3.8-flash`(仅 LLM —— 无嵌入预设,请搭配 OpenAI 兼容嵌入器;别名 `gemini`)```bash@@ -41,7 +42,7 @@ he config init [OPTIONS]| 选项 | 简写 | 描述 ||--------|-------|-------------|-| `--provider` | `-p` | 提供商 preset (`openai` / `anthropic` / `google` / `orcarouter` / `atlascloud` / `deepseek` / `bailian` / `vllm`) |+| `--provider` | `-p` | 提供商 preset (`openai` / `anthropic` / `google` / `orcarouter` / `atlascloud` / `runcrate` / `deepseek` / `bailian` / `vllm`) || `--api-key` | `-k` | LLM 和嵌入模型的 API 密钥 || `--base-url` | `-u` | 自定义 API 基础 URL(可选) |@@ -71,6 +72,9 @@ he config init -p orcarouter -k or-your-orcarouter-keyhe config llm -p atlascloud -k your-atlascloud-keyhe config embedder -p openai -k sk-your-openai-key+# Runcrate(LLM 与嵌入器共用一个密钥)+he config init -p runcrate -k your-runcrate-key+# Google Gemini(仅 LLM —— 请搭配 OpenAI 兼容嵌入器)he config llm -p google -k your-google-api-keyhe config embedder -p openai -k sk-your-openai-key@@ -128,7 +132,7 @@ he config llm [OPTIONS]| 选项 | 简写 | 描述 ||--------|-------|-------------|-| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`google`、`orcarouter`、`atlascloud`、`deepseek`、`bailian`、`vllm`) |+| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`google`、`orcarouter`、`atlascloud`、`runcrate`、`deepseek`、`bailian`、`vllm`) || `--api-key` | `-k` | LLM API 密钥 || `--model` | `-m` | LLM 模型名称 || `--base-url` | `-u` | 自定义 API 基础 URL |@@ -171,7 +175,7 @@ he config embedder [OPTIONS]| 选项 | 简写 | 描述 ||--------|-------|-------------|-| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`google`、`orcarouter`、`atlascloud`、`deepseek`、`bailian`、`vllm`) |+| `--provider` | `-p` | 提供商 preset(如 `openai`、`anthropic`、`google`、`orcarouter`、`atlascloud`、`runcrate`、`deepseek`、`bailian`、`vllm`) || `--api-key` | `-k` | 嵌入模型 API 密钥 || `--model` | `-m` | 嵌入模型名称 || `--base-url` | `-u` | 自定义 API 基础 URL |diff --git a/docs/zh/concepts/provider-system.md b/docs/zh/concepts/provider-system.mdindex 6de2305..9e52fc4 100644--- a/docs/zh/concepts/provider-system.md+++ b/docs/zh/concepts/provider-system.md@@ -1,6 +1,6 @@# Provider 系统-Hyper-Extract 支持以下接入方式:**OpenAI**、**Anthropic**、**Google Gemini**、**阿里云百炼**、**DeepSeek**、**OrcaRouter**、**Atlas Cloud**、**本地 vLLM**。统一使用 `create_client()` 接口,仅需修改第一行。+Hyper-Extract 支持以下接入方式:**OpenAI**、**Anthropic**、**Google Gemini**、**阿里云百炼**、**DeepSeek**、**OrcaRouter**、**Atlas Cloud**、**Runcrate**、**本地 vLLM**。统一使用 `create_client()` 接口,仅需修改第一行。---@@ -16,6 +16,7 @@ Hyper-Extract 支持以下接入方式:**OpenAI**、**Anthropic**、**Google G| **DeepSeek** | deepseek-v4-flash / deepseek-v4-pro | ✅ | ✅ | OpenAI 兼容。V4 模型默认开启"thinking"模式,Hyper-Extract 会自动关闭以保证结构化抽取可用。仅 LLM——无嵌入接口。密钥:`DEEPSEEK_API_KEY` || **OrcaRouter** | `orcarouter/auto`、`openai/gpt-4o-mini`、`anthropic/claude-haiku-4-5`、`deepseek/...`、`gemini/...` | ✅ | ✅ | OpenAI 兼容网关,用同一端点和密钥路由 OpenAI、Anthropic、Google、DeepSeek、Qwen、MiniMax、xAI 等 150+ 模型。密钥:`ORCAROUTER_API_KEY` || **Atlas Cloud** | `deepseek-ai/deepseek-v4-flash`、`deepseek-ai/deepseek-v4-pro`、`moonshotai/kimi-k3`、`qwen/qwen3.5-plus`、`openai/gpt-5.5`、`anthropic/claude-sonnet-4.6` | ✅ | ✅ | OpenAI 兼容网关,模型 id 带厂商前缀,覆盖 DeepSeek、智谱、月之暗面、Qwen、MiniMax、OpenAI、Anthropic、Google 等。仅 LLM —— 无嵌入 API。`glm-5.x` 不接受结构化抽取使用的强制 `tool_choice`,请换其他模型。密钥:`ATLASCLOUD_API_KEY` |+| **Runcrate** | `deepseek-ai/DeepSeek-V4.1-Flash`、`openai/gpt-oss-120b` | ✅ | ✅ | OpenAI 兼容 API,提供带厂商前缀 id 的开放模型。同时提供嵌入(`BAAI/bge-m3`,1024 维),一个密钥即可覆盖 LLM 与嵌入器。开放模型可通过 GitHub 账号免费使用。测试中 `zai-org/GLM-5.x` 抽取结果为空,请选择其他模型。密钥:`RUNCRATE_API_KEY` || **阿里云百炼** | qwen-plus / qwen-turbo / qwen3.6-plus / deepseek-r1 | ✅ | ✅ | 直接使用,无需修改 || **阿里云百炼** | qwen-max / deepseek-v3 | ❌ | ❌ | 仅支持 `json_object`,不兼容 function calling 结构化输出 |@@ -88,6 +89,13 @@ llm, emb = create_client(embedder="openai:text-embedding-3-small",)+# Runcrate —— OpenAI 兼容 API,模型 id 带厂商前缀,同时提供嵌入+# 密钥:RUNCRATE_API_KEY。可用 "runcrate:openai/gpt-oss-120b" 覆盖模型。+llm, emb = create_client(+ llm="runcrate", # 默认模型:deepseek-ai/DeepSeek-V4.1-Flash+ embedder="runcrate", # 默认嵌入器:BAAI/bge-m3+)+# 本地 vLLMllm, emb = create_client(llm="vllm:Qwen3.5-9B@http://localhost:8000/v1",diff --git a/hyperextract/cli/commands/config.py b/hyperextract/cli/commands/config.pyindex 48b56a4..8f59182 100644--- a/hyperextract/cli/commands/config.py+++ b/hyperextract/cli/commands/config.py@@ -160,7 +160,7 @@ def llm(None,"--provider","-p",- help="Provider preset: openai, anthropic, google, deepseek, bailian, orcarouter, atlascloud, vllm",+ help="Provider preset: openai, anthropic, google, deepseek, bailian, orcarouter, atlascloud, runcrate, vllm",),api_key: str | None = typer.Option(None,@@ -221,7 +221,7 @@ def embedder(None,"--provider","-p",- help="Provider preset: openai, anthropic, google, deepseek, bailian, orcarouter, atlascloud, vllm",+ help="Provider preset: openai, anthropic, google, deepseek, bailian, orcarouter, atlascloud, runcrate, vllm",),api_key: str | None = typer.Option(None,@@ -284,7 +284,7 @@ def init(None,"--provider","-p",- help="Provider preset: openai, anthropic, google, deepseek, bailian, orcarouter, atlascloud, vllm",+ help="Provider preset: openai, anthropic, google, deepseek, bailian, orcarouter, atlascloud, runcrate, vllm",),api_key: str | None = typer.Option(None,@@ -397,6 +397,7 @@ def init(("anthropic", "Anthropic (Claude)", "native SDK"),("google", "Google Gemini", "native SDK"),("atlascloud", "Atlas Cloud", "https://api.atlascloud.ai/v1"),+ ("runcrate", "Runcrate", "https://api.runcrate.ai/v1"),("vllm", "本地 vLLM", "自定义地址"),("custom", "其他 OpenAI 兼容接口", "自定义地址"),]diff --git a/hyperextract/utils/client.py b/hyperextract/utils/client.pyindex 47e089d..351a853 100644--- a/hyperextract/utils/client.py+++ b/hyperextract/utils/client.py@@ -82,6 +82,14 @@ PROVIDER_PRESETS: dict[str, dict[str, str | None]] = {"default_llm": "deepseek-ai/deepseek-v4-flash","default_embedder": None,},+ # Runcrate. OpenAI-compatible API for open models under vendor-prefixed ids+ # such as "deepseek-ai/DeepSeek-V4.1-Flash". It also serves embeddings, so+ # one key covers both the LLM and the embedder ("BAAI/bge-m3", 1024 dims).+ "runcrate": {+ "base_url": "https://api.runcrate.ai/v1",+ "default_llm": "deepseek-ai/DeepSeek-V4.1-Flash",+ "default_embedder": "BAAI/bge-m3",+ },# Anthropic (Claude). Uses the native ChatAnthropic client, so base_url is# left empty (the SDK targets api.anthropic.com by default). Anthropic has# no embeddings API, hence default_embedder is None — pair it with an@@ -134,6 +142,7 @@ PROVIDER_API_KEY_ENV: dict[str, tuple[str, ...]] = {"orcarouter": ("ORCAROUTER_API_KEY",),"cheaperinference": ("CHEAPER_INFERENCE_API_KEY",),"atlascloud": ("ATLASCLOUD_API_KEY",),+ "runcrate": ("RUNCRATE_API_KEY",),}diff --git a/tests/cli/test_config.py b/tests/cli/test_config.pyindex cbc5011..5ee80cd 100644--- a/tests/cli/test_config.py+++ b/tests/cli/test_config.py@@ -380,3 +380,21 @@ def test_interactive_init_lists_atlascloud():assert '"atlascloud"' in inspect.getsource(init)++def test_get_llm_and_embedder_config_read_runcrate_env_key(tmp_path, monkeypatch):+ """Empty toml api_key must resolve RUNCRATE_API_KEY, ahead of OPENAI_API_KEY."""+ monkeypatch.delenv("OPENAI_BASE_URL", raising=False)+ monkeypatch.setenv("OPENAI_API_KEY", "sk-openai-must-not-win")+ monkeypatch.setenv("RUNCRATE_API_KEY", "rc-from-env")++ cm = ConfigManager(tmp_path / "config.toml")+ cm.set_llm(provider="runcrate", model="deepseek-ai/DeepSeek-V4.1-Flash", api_key="")+ cm.set_embedder(provider="runcrate", model="BAAI/bge-m3", api_key="")++ llm_cfg = cm.get_llm_config()+ assert llm_cfg.api_key == "rc-from-env"+ assert llm_cfg.base_url == "https://api.runcrate.ai/v1"+ emb_cfg = cm.get_embedder_config()+ assert emb_cfg.api_key == "rc-from-env"+ assert emb_cfg.base_url == "https://api.runcrate.ai/v1"+diff --git a/tests/utils/test_client.py b/tests/utils/test_client.pyindex c1b6527..37643a7 100644--- a/tests/utils/test_client.py+++ b/tests/utils/test_client.py@@ -159,6 +159,25 @@ class TestCreateLLM:llm = create_llm("atlascloud")assert llm.openai_api_key.get_secret_value() == "apikey-from-env"+ def test_create_llm_runcrate(self):+ """Create LLM with runcrate preset (OpenAI-compatible API)."""+ llm = create_llm("runcrate", api_key="rc-test")+ assert llm.model_name == "deepseek-ai/DeepSeek-V4.1-Flash"+ assert llm.openai_api_base == "https://api.runcrate.ai/v1"++ def test_create_llm_runcrate_model_override(self):+ """A vendor-prefixed Runcrate model id after the colon is kept whole."""+ llm = create_llm("runcrate:openai/gpt-oss-120b", api_key="rc-test")+ assert llm.model_name == "openai/gpt-oss-120b"+ assert llm.openai_api_base == "https://api.runcrate.ai/v1"++ def test_create_llm_runcrate_env_key(self, monkeypatch):+ """Runcrate key is read from RUNCRATE_API_KEY, ahead of OPENAI_API_KEY."""+ monkeypatch.setenv("OPENAI_API_KEY", "sk-openai-test")+ monkeypatch.setenv("RUNCRATE_API_KEY", "rc-from-env")+ llm = create_llm("runcrate")+ assert llm.openai_api_key.get_secret_value() == "rc-from-env"+def test_create_llm_orcarouter(self):"""Create LLM with orcarouter preset (OpenAI-compatible gateway)."""llm = create_llm("orcarouter", api_key="sk-test")@@ -644,6 +663,14 @@ class TestProviderPresets:assert preset["default_llm"] == "deepseek-ai/deepseek-v4-flash"assert preset["default_embedder"] is None+ def test_runcrate_provider(self):+ """Runcrate has its own preset with an embedder on the same endpoint."""+ assert "runcrate" in PROVIDER_PRESETS+ preset = PROVIDER_PRESETS["runcrate"]+ assert preset["base_url"] == "https://api.runcrate.ai/v1"+ assert preset["default_llm"] == "deepseek-ai/DeepSeek-V4.1-Flash"+ assert preset["default_embedder"] == "BAAI/bge-m3"+def test_orcarouter_provider(self):"""OrcaRouter has its own preset (OpenAI-compatible, named models)."""assert "orcarouter" in PROVIDER_PRESETS