lfx-nightly 0.1.13.dev10__py3-none-any.whl → 0.1.13.dev12__py3-none-any.whl

lfx/components/docling/__init__.py

@@ -8,6 +8,7 @@ if TYPE_CHECKING:
     from .chunk_docling_document import ChunkDoclingDocumentComponent
     from .docling_inline import DoclingInlineComponent
     from .docling_remote import DoclingRemoteComponent
+    from .docling_remote_vlm import DoclingRemoteVLMComponent
     from .export_docling_document import ExportDoclingDocumentComponent
 
 _dynamic_imports = {
@@ -15,12 +16,14 @@ _dynamic_imports = {
     "DoclingInlineComponent": "docling_inline",
     "DoclingRemoteComponent": "docling_remote",
     "ExportDoclingDocumentComponent": "export_docling_document",
+    "DoclingRemoteVLMComponent": "docling_remote_vlm",
 }
 
 __all__ = [
     "ChunkDoclingDocumentComponent",
     "DoclingInlineComponent",
     "DoclingRemoteComponent",
+    "DoclingRemoteVLMComponent",
     "ExportDoclingDocumentComponent",
 ]
 

lfx/components/docling/docling_remote_vlm.py

@@ -0,0 +1,284 @@
+from typing import Any
+
+import requests
+from docling.datamodel.base_models import ConversionStatus, InputFormat
+from docling.datamodel.pipeline_options import (
+    ApiVlmOptions,
+    ResponseFormat,
+    VlmPipelineOptions,
+)
+from docling.document_converter import DocumentConverter, PdfFormatOption
+from docling.pipeline.vlm_pipeline import VlmPipeline
+from langflow.base.data import BaseFileComponent
+from langflow.inputs import DropdownInput, SecretStrInput, StrInput
+from langflow.schema import Data
+from langflow.schema.dotdict import dotdict
+
+from lfx.components.ibm.watsonx import WatsonxAIComponent
+from lfx.log.logger import logger
+
+
+class DoclingRemoteVLMComponent(BaseFileComponent):
+    display_name = "Docling Remote VLM"
+    description = (
+        "Uses Docling to process input documents running a VLM pipeline with a remote model"
+        "(OpenAI-compatible API or IBM Cloud)."
+    )
+    documentation = "https://docling-project.github.io/docling/examples/vlm_pipeline_api_model/"
+    trace_type = "tool"
+    icon = "Docling"
+    name = "DoclingRemoteVLM"
+
+    # https://docling-project.github.io/docling/usage/supported_formats/
+    VALID_EXTENSIONS = [
+        "adoc",
+        "asciidoc",
+        "asc",
+        "bmp",
+        "csv",
+        "dotx",
+        "dotm",
+        "docm",
+        "docx",
+        "htm",
+        "html",
+        "jpeg",
+        "json",
+        "md",
+        "pdf",
+        "png",
+        "potx",
+        "ppsx",
+        "pptm",
+        "potm",
+        "ppsm",
+        "pptx",
+        "tiff",
+        "txt",
+        "xls",
+        "xlsx",
+        "xhtml",
+        "xml",
+        "webp",
+    ]
+
+    inputs = [
+        *BaseFileComponent.get_base_inputs(),
+        DropdownInput(
+            name="provider",
+            display_name="Provider",
+            info="Select which remote VLM provider to use.",
+            options=["IBM Cloud", "OpenAI-Compatible"],
+            value="IBM Cloud",
+            real_time_refresh=True,
+        ),
+        # IBM Cloud inputs
+        SecretStrInput(
+            name="watsonx_api_key",
+            display_name="Watsonx API Key",
+            info="IBM Cloud API key used for authentication (leave blank to load from .env).",
+            required=False,
+        ),
+        StrInput(
+            name="watsonx_project_id",
+            display_name="Watsonx Project ID",
+            required=False,
+            info="The Watsonx project ID or deployment space ID associated with the model.",
+            value="",
+        ),
+        DropdownInput(
+            name="url",
+            display_name="Watsonx API Endpoint",
+            info="The base URL of the Watsonx API.",
+            options=[
+                "https://us-south.ml.cloud.ibm.com",
+                "https://eu-de.ml.cloud.ibm.com",
+                "https://eu-gb.ml.cloud.ibm.com",
+                "https://au-syd.ml.cloud.ibm.com",
+                "https://jp-tok.ml.cloud.ibm.com",
+                "https://ca-tor.ml.cloud.ibm.com",
+            ],
+            real_time_refresh=True,
+        ),
+        DropdownInput(
+            name="model_name",
+            display_name="Model Name",
+            options=[],
+            value=None,
+            dynamic=True,
+            required=False,
+        ),
+        # OpenAI inputs
+        StrInput(
+            name="openai_base_url",
+            display_name="OpenAI-Compatible API Base URL",
+            info="Example: https://openrouter.ai/api/",
+            required=False,
+            show=False,
+        ),
+        SecretStrInput(
+            name="openai_api_key",
+            display_name="API Key",
+            info="API key for OpenAI-compatible endpoints (leave blank if not required).",
+            required=False,
+            show=False,
+        ),
+        StrInput(
+            name="openai_model",
+            display_name="OpenAI Model Name",
+            info="Model ID for OpenAI-compatible provider (e.g. gpt-4o-mini).",
+            required=False,
+            show=False,
+        ),
+        StrInput(name="vlm_prompt", display_name="Prompt", info="Prompt for VLM.", required=False),
+    ]
+
+    outputs = [*BaseFileComponent.get_base_outputs()]
+
+    @staticmethod
+    def fetch_models(base_url: str) -> list[str]:
+        """Fetch available models from the Watsonx.ai API."""
+        try:
+            endpoint = f"{base_url}/ml/v1/foundation_model_specs"
+            params = {"version": "2024-09-16", "filters": "function_text_chat,!lifecycle_withdrawn"}
+            response = requests.get(endpoint, params=params, timeout=10)
+            response.raise_for_status()
+            data = response.json()
+            models = [model["model_id"] for model in data.get("resources", [])]
+            return sorted(models)
+        except (requests.RequestException, requests.HTTPError, requests.Timeout, ConnectionError, ValueError):
+            logger.exception("Error fetching models. Using default models.")
+            return WatsonxAIComponent._default_models  # noqa: SLF001
+
+    def update_build_config(self, build_config: dotdict, field_value: Any, field_name: str | None = None):
+        """Update shown fields based on chosen provider."""
+        logger.info(f"update_build_config called: field_name={field_name}, field_value={field_value}")
+
+        if field_name == "provider":
+            provider_choice = field_value
+
+            if provider_choice == "IBM Cloud":
+                build_config.model_name.show = True
+                build_config.watsonx_api_key.show = True
+                build_config.watsonx_project_id.show = True
+                build_config.url.show = True
+
+                build_config.openai_base_url.show = False
+                build_config.openai_api_key.show = False
+                build_config.openai_model.show = False
+
+            elif provider_choice == "OpenAI-Compatible":
+                build_config.model_name.show = False
+                build_config.watsonx_api_key.show = False
+                build_config.watsonx_project_id.show = False
+                build_config.url.show = False
+
+                build_config.openai_base_url.show = True
+                build_config.openai_api_key.show = True
+                build_config.openai_model.show = True
+
+        if field_name == "url":
+            provider_value = build_config.provider.value if hasattr(build_config, "provider") else None
+            if provider_value == "IBM Cloud" and field_value:
+                models = self.fetch_models(base_url=field_value)
+                build_config.model_name.options = models
+                if models:
+                    build_config.model_name.value = models[0]
+                logger.info(f"Updated Watsonx model list: {len(models)} models found.")
+
+    def watsonx_vlm_options(self, model: str, prompt: str):
+        """Creates Docling ApiVlmOptions for a watsonx VLM."""
+        api_key = getattr(self, "watsonx_api_key", "")
+        project_id = getattr(self, "watsonx_project_id", "")
+        base_url = getattr(self, "url", "https://us-south.ml.cloud.ibm.com")
+
+        def _get_iam_access_token(api_key: str) -> str:
+            res = requests.post(
+                url="https://iam.cloud.ibm.com/identity/token",
+                headers={"Content-Type": "application/x-www-form-urlencoded"},
+                data=f"grant_type=urn:ibm:params:oauth:grant-type:apikey&apikey={api_key}",
+                timeout=90,
+            )
+            res.raise_for_status()
+            return res.json()["access_token"]
+
+        access_token = _get_iam_access_token(api_key)
+        return ApiVlmOptions(
+            url=f"{base_url}/ml/v1/text/chat?version=2023-05-29",
+            params={"model_id": model, "project_id": project_id, "parameters": {"max_new_tokens": 400}},
+            headers={"Authorization": f"Bearer {access_token}"},
+            prompt=prompt,
+            timeout=60,
+            response_format=ResponseFormat.MARKDOWN,
+        )
+
+    def openai_compatible_vlm_options(
+        self,
+        model: str,
+        prompt: str,
+        response_format: ResponseFormat,
+        url: str,
+        temperature: float = 0.7,
+        max_tokens: int = 4096,
+        api_key: str = "",
+        *,
+        skip_special_tokens: bool = False,
+    ):
+        """Create OpenAI-compatible Docling ApiVlmOptions options (e.g., LM Studio, vLLM, Ollama)."""
+        api_key = getattr(self, "openai_api_key", api_key)
+        model_override = getattr(self, "openai_model", model)
+
+        headers = {}
+        if api_key:
+            headers["Authorization"] = f"Bearer {api_key}"
+
+        return ApiVlmOptions(
+            url=f"{url}/v1/chat/completions",
+            params={"model": model_override, "max_tokens": max_tokens, "skip_special_tokens": skip_special_tokens},
+            headers=headers,
+            prompt=prompt,
+            timeout=90,
+            scale=2.0,
+            temperature=temperature,
+            response_format=response_format,
+        )
+
+    def process_files(self, file_list: list[BaseFileComponent.BaseFile]) -> list[BaseFileComponent.BaseFile]:
+        file_paths = [file.path for file in file_list if file.path]
+        if not file_paths:
+            logger.warning("No files to process.")
+            return file_list
+
+        provider = getattr(self, "provider", "IBM Cloud")
+        prompt = getattr(self, "vlm_prompt", "")
+
+        if provider == "IBM Cloud":
+            model = getattr(self, "model_name", "")
+            vlm_opts = self.watsonx_vlm_options(model=model, prompt=prompt)
+        else:
+            model = getattr(self, "openai_model", "") or getattr(self, "model_name", "")
+            base_url = getattr(self, "openai_base_url", "")
+            vlm_opts = self.openai_compatible_vlm_options(
+                model=model,
+                prompt=prompt,
+                response_format=ResponseFormat.MARKDOWN,
+                url=base_url,
+            )
+
+        pipeline_options = VlmPipelineOptions(enable_remote_services=True)
+        pipeline_options.vlm_options = vlm_opts
+
+        converter = DocumentConverter(
+            format_options={
+                InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options, pipeline_cls=VlmPipeline)
+            }
+        )
+
+        results = converter.convert_all(file_paths)
+        processed_data = [
+            Data(data={"doc": res.document, "file_path": str(res.input.file)})
+            if res.status == ConversionStatus.SUCCESS
+            else None
+            for res in results
+        ]
+        return self.rollup_data(file_list, processed_data)

lfx/components/models/embedding_model.py

@@ -31,7 +31,7 @@ class EmbeddingModelComponent(LCEmbeddingsModel):
         DropdownInput(
             name="provider",
             display_name="Model Provider",
-            options=["OpenAI", "Ollama", "WatsonX"],
+            options=["OpenAI", "Ollama", "IBM watsonx.ai"],
             value="OpenAI",
             info="Select the embedding model provider",
             real_time_refresh=True,
@@ -62,7 +62,7 @@ class EmbeddingModelComponent(LCEmbeddingsModel):
         MessageTextInput(
             name="project_id",
             display_name="Project ID",
-            info="Watson AI Project ID (required for WatsonX)",
+            info="IBM watsonx.ai Project ID (required for IBM watsonx.ai)",
             show=False,
         ),
         IntInput(
@@ -128,7 +128,7 @@ class EmbeddingModelComponent(LCEmbeddingsModel):
                 **model_kwargs,
             )
 
-        if provider == "WatsonX":
+        if provider == "IBM watsonx.ai":
             try:
                 from langchain_ibm import WatsonxEmbeddings
             except ImportError:
@@ -136,13 +136,13 @@ class EmbeddingModelComponent(LCEmbeddingsModel):
                 raise ImportError(msg) from None
 
             if not api_key:
-                msg = "Watson AI API key is required when using WatsonX provider"
+                msg = "IBM watsonx.ai API key is required when using IBM watsonx.ai provider"
                 raise ValueError(msg)
 
             project_id = self.project_id
 
             if not project_id:
-                msg = "Project ID is required for WatsonX"
+                msg = "Project ID is required for IBM watsonx.ai provider"
                 raise ValueError(msg)
 
             params = {
@@ -167,6 +167,7 @@ class EmbeddingModelComponent(LCEmbeddingsModel):
                 build_config["api_key"]["required"] = True
                 build_config["api_key"]["show"] = True
                 build_config["api_base"]["display_name"] = "OpenAI API Base URL"
+                build_config["api_base"]["advanced"] = True
                 build_config["project_id"]["show"] = False
 
             elif field_value == "Ollama":
@@ -177,16 +178,18 @@ class EmbeddingModelComponent(LCEmbeddingsModel):
                 build_config["api_key"]["show"] = False
                 build_config["api_base"]["display_name"] = "Ollama Base URL"
                 build_config["api_base"]["value"] = "http://localhost:11434"
+                build_config["api_base"]["advanced"] = True
                 build_config["project_id"]["show"] = False
 
-            elif field_value == "WatsonX":
+            elif field_value == "IBM watsonx.ai":
                 build_config["model"]["options"] = WATSONX_EMBEDDING_MODEL_NAMES
                 build_config["model"]["value"] = WATSONX_EMBEDDING_MODEL_NAMES[0]
-                build_config["api_key"]["display_name"] = "Watson AI API Key"
+                build_config["api_key"]["display_name"] = "IBM watsonx.ai API Key"
                 build_config["api_key"]["required"] = True
                 build_config["api_key"]["show"] = True
-                build_config["api_base"]["display_name"] = "Watson AI URL"
+                build_config["api_base"]["display_name"] = "IBM watsonx.ai URL"
                 build_config["api_base"]["value"] = "https://us-south.ml.cloud.ibm.com"
+                build_config["api_base"]["advanced"] = False
                 build_config["project_id"]["show"] = True
 
         return build_config

lfx/components/processing/parser.py

@@ -122,7 +122,12 @@ class ParserComponent(Component):
                 formatted_text = self.pattern.format(**row.to_dict())
                 lines.append(formatted_text)
         elif data is not None:
-            formatted_text = self.pattern.format(**data.data)
+            # Use format_map with a dict that returns default_value for missing keys
+            class DefaultDict(dict):
+                def __missing__(self, key):
+                    return data.default_value or ""
+
+            formatted_text = self.pattern.format_map(DefaultDict(data.data))
             lines.append(formatted_text)
 
         combined_text = self.sep.join(lines)

{lfx_nightly-0.1.13.dev10.dist-info → lfx_nightly-0.1.13.dev12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lfx-nightly
-Version: 0.1.13.dev10
+Version: 0.1.13.dev12
 Summary: Langflow Executor - A lightweight CLI tool for executing and serving Langflow AI flows
 Author-email: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>
 Requires-Python: <3.14,>=3.10

{lfx_nightly-0.1.13.dev10.dist-info → lfx_nightly-0.1.13.dev12.dist-info}/RECORD

@@ -4,7 +4,7 @@ lfx/constants.py,sha256=Ert_SpwXhutgcTKEvtDArtkONXgyE5x68opMoQfukMA,203
 lfx/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lfx/settings.py,sha256=wnx4zkOLQ8mvampYsnnvVV9GvEnRUuWQpKFSbFTCIp4,181
 lfx/type_extraction.py,sha256=eCZNl9nAQivKdaPv_9BK71N0JV9Rtr--veAht0dnQ4A,2921
-lfx/_assets/component_index.json,sha256=zHM0opm5e8efaCHaiGBVeICiycRH9Gs1MqBZOgk9ves,3572362
+lfx/_assets/component_index.json,sha256=WxdnXtEx5ZLGCM7ef5jLrw1-n6gDHT6bkS1KbKhZ3GY,3592770
 lfx/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 lfx/base/constants.py,sha256=v9vo0Ifg8RxDu__XqgGzIXHlsnUFyWM-SSux0uHHoz8,1187
 lfx/base/agents/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -285,10 +285,11 @@ lfx/components/deactivated/vectara_self_query.py,sha256=nlRFL-FIdecgpaR70ohC8Tsl
 lfx/components/deactivated/vector_store.py,sha256=7L1Z8Nl0RZjEGAj1O2tMhb6I6jUNNc5MBOui4a2FkXE,728
 lfx/components/deepseek/__init__.py,sha256=gmyOcLeNEcnwSeowow0N0UhBDlSuZ_8x-DMUjwkNRFM,935
 lfx/components/deepseek/deepseek.py,sha256=yNrHoljXOMScKng-oSB-ceWhVZeuh11lmrAY7WiB2H0,4702
-lfx/components/docling/__init__.py,sha256=O4utz9GHFpTVe_Wy0PR80yA1irJQRnAFQWkoLCVj888,1424
+lfx/components/docling/__init__.py,sha256=UPtKdQKonYMQZCmE-zuBhJwNbSKIoddgB_WTl0Yp7oM,1574
 lfx/components/docling/chunk_docling_document.py,sha256=OX-jj4nX3UZgopViMAGAnFgtLql0sgs6cVmU8p9QbqA,7600
 lfx/components/docling/docling_inline.py,sha256=12s4U860c-wkpmd2JYi6qxK1Wx_PF9j9BARLhXCL0E0,8496
 lfx/components/docling/docling_remote.py,sha256=Ju61E93tLBq6KsRRGVA1_ySWzEOdOFj9jS9kJ7gc3H4,6980
+lfx/components/docling/docling_remote_vlm.py,sha256=aAEk2vepXzB9aHWEfgbmOrfRuLa2sEh4T1dVyGwIN-A,10538
 lfx/components/docling/export_docling_document.py,sha256=TeFt3TesCxSqW57nv-30gf2dX8qMDUHLRhwU-1ciq08,4681
 lfx/components/documentloaders/__init__.py,sha256=LNl2hG2InevQCUREFKhF9ylaTf_kwPsdjiDbx2ElX3M,69
 lfx/components/duckduckgo/__init__.py,sha256=Y4zaOLVOKsD_qwF7KRLek1pcaKKHa6lGUHObuQTR9iY,104
@@ -416,7 +417,7 @@ lfx/components/mistral/__init__.py,sha256=EABXqA45Tz50vZRmhEisbIIPEcRCvV9j-Y9Hf2
 lfx/components/mistral/mistral.py,sha256=4heAlIFEeq_ljUZDPpNGyK_VRkWjwCfPbBaQK1mV4NY,3718
 lfx/components/mistral/mistral_embeddings.py,sha256=QuqS_S3yHWCacs-Nc3qalpUsb-OACRWFZenUtCD_rLQ,1963
 lfx/components/models/__init__.py,sha256=hhfj70MkcRATzAjJnntAg1A4E7kHlQn8GT0bizkB7L4,1113
-lfx/components/models/embedding_model.py,sha256=Tk-P9K5DanE0YuXauWMW_nOi08rnAaspiqJHbNYjoeA,7543
+lfx/components/models/embedding_model.py,sha256=Q38BxC4xklLOAxS1Vam0EGP0g6cu0Dm7-uf679XImAc,7795
 lfx/components/models/language_model.py,sha256=TA24DMAXrlruY3mNsfI9qGltfQ2h9cQpxe8DW8HLdeE,5992
 lfx/components/mongodb/__init__.py,sha256=nFOQgiIvDnWGiWDSqZ0ERQme5DpA-cQgzybUiqXQtGw,953
 lfx/components/mongodb/mongodb_atlas.py,sha256=OlAstNMToHuvGI-8djkiGr7kdGBr927O0SE5cnVd0O0,8594
@@ -471,7 +472,7 @@ lfx/components/processing/message_to_data.py,sha256=0K8SIq6vuAvQ3K7siXstNint6R1-
 lfx/components/processing/parse_data.py,sha256=P6xEqbs3geWP0gYMdS9QIVJiIREEgDjxzENRLwiNgE0,2463
 lfx/components/processing/parse_dataframe.py,sha256=nUsFzxVkBXJhoPP9f6NmmKmwXSKs9IjaIvrr7DeLSSY,2518
 lfx/components/processing/parse_json_data.py,sha256=OdmZ2Kqdfb0uBCA5FdKSv4y_3OqfWY56Mesg1iO666Q,3160
-lfx/components/processing/parser.py,sha256=vxnub-7jUTAtMgcLTdZGzHuRby_B1d1HOntsxM3KU_E,5414
+lfx/components/processing/parser.py,sha256=F1FJU8foJvj8AwlKBPlDhuhqEr4I_6XqDgJ0h1iBbpw,5648
 lfx/components/processing/prompt.py,sha256=c4LQPOQSvz1Z1e73uyOm8TaTxWDpCGcujBd-a6AxL1A,2761
 lfx/components/processing/python_repl_core.py,sha256=6kOu64pWyBwBpTqOTM9LPnSsnTX6q_J-Hqhmoxp0wFs,3472
 lfx/components/processing/regex.py,sha256=9n171_Ze--5gpKFJJyJlYafuEOwbPQPiyjhdLY3SUrY,2689
@@ -730,7 +731,7 @@ lfx/utils/schemas.py,sha256=NbOtVQBrn4d0BAu-0H_eCTZI2CXkKZlRY37XCSmuJwc,3865
 lfx/utils/util.py,sha256=Ww85wbr1-vjh2pXVtmTqoUVr6MXAW8S7eDx_Ys6HpE8,20696
 lfx/utils/util_strings.py,sha256=nU_IcdphNaj6bAPbjeL-c1cInQPfTBit8mp5Y57lwQk,1686
 lfx/utils/version.py,sha256=cHpbO0OJD2JQAvVaTH_6ibYeFbHJV0QDHs_YXXZ-bT8,671
-lfx_nightly-0.1.13.dev10.dist-info/METADATA,sha256=zAEy_d1dQWrDneWNhhmrFz20gFgfoGE7k_3FgKKB7Yk,8290
-lfx_nightly-0.1.13.dev10.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-lfx_nightly-0.1.13.dev10.dist-info/entry_points.txt,sha256=1724p3RHDQRT2CKx_QRzEIa7sFuSVO0Ux70YfXfoMT4,42
-lfx_nightly-0.1.13.dev10.dist-info/RECORD,,
+lfx_nightly-0.1.13.dev12.dist-info/METADATA,sha256=pTwMBq4ciOBRLatxElSZFMwuB46Vhpm14_4k-aYNrNE,8290
+lfx_nightly-0.1.13.dev12.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+lfx_nightly-0.1.13.dev12.dist-info/entry_points.txt,sha256=1724p3RHDQRT2CKx_QRzEIa7sFuSVO0Ux70YfXfoMT4,42
+lfx_nightly-0.1.13.dev12.dist-info/RECORD,,