Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.
Rename search presets to provider-agnostic names (#737)
Louis Choquel7c128dec82c2
diff --git a/.pipelex-dev/test_profiles.toml b/.pipelex-dev/test_profiles.tomlindex fc185277c..7b1588627 100644--- a/.pipelex-dev/test_profiles.toml+++ b/.pipelex-dev/test_profiles.toml@@ -206,6 +206,10 @@ google = ["nano-banana", "nano-banana-pro"]# --- Qwen Models ---qwen = ["qwen-image"]+[collections.search]+# --- Search Models ---+linkup = ["linkup-standard", "linkup-deep"]+[collections.extract]# --- PDF Extraction Models ---from_pdf = [@@ -243,6 +247,7 @@ backends = ["azure_openai"]llm_models = ["gpt-4o-mini"]img_gen_models = []extract_models = []+search_models = []################################################################################# Dev Profile@@ -253,6 +258,7 @@ backends = ["pipelex_gateway", "internal"]llm_models = ["claude-4.5-haiku", "gpt-4o-mini", "gemini-2.5-flash-lite"]img_gen_models = ["gpt-image-1-mini"]extract_models = ["@from_pdf"]+search_models = ["linkup-standard"]################################################################################# Coverage Profile@@ -268,6 +274,7 @@ llm_models = []img_gen_models = ["gpt-image-1", "nano-banana"]extract_models = ["pypdfium2-extract-pdf"]+search_models = ["linkup-standard"]################################################################################# Claude Latest Profile@@ -278,6 +285,7 @@ backends = ["anthropic", "pipelex_gateway"]llm_models = ["claude-4.5-*"]img_gen_models = []extract_models = []+search_models = []################################################################################# GPT No Codex Profile@@ -288,6 +296,7 @@ backends = ["openai", "pipelex_gateway"]llm_models = ["gpt-*", "!*-codex", "!*-codex-*"]img_gen_models = ["gpt-image-*"]extract_models = []+search_models = []################################################################################# All Backends Profile - Test across all backends with select models@@ -298,6 +307,7 @@ backends = ["@all"]llm_models = ["claude-4.5-haiku", "gpt-4o-mini", "gemini-2.5-flash-lite"]img_gen_models = ["gpt-image-1-mini"]extract_models = ["@from_pdf"]+search_models = ["@linkup"]################################################################################# Full Profile - All available models (use with caution)diff --git a/.pipelex/inference/backends/linkup.toml b/.pipelex/inference/backends/linkup.tomlindex 9ff7d159f..184e324e9 100644--- a/.pipelex/inference/backends/linkup.toml+++ b/.pipelex/inference/backends/linkup.toml@@ -24,14 +24,14 @@ thinking_mode = "none"# SEARCH MODELS################################################################################-["linkup/standard"]+["linkup-standard"]model_id = "standard"inputs = ["text"]-outputs = ["structured"]-costs = {}+outputs = ["sourced-answers", "structured"]+costs = { input = 0.005, output = 0 }-["linkup/deep"]+["linkup-deep"]model_id = "deep"inputs = ["text"]-outputs = ["structured"]-costs = {}+outputs = ["sourced-answers", "structured"]+costs = { input = 0.05, output = 0 }diff --git a/.pipelex/inference/backends/pipelex_gateway_models.md b/.pipelex/inference/backends/pipelex_gateway_models.mdindex 28b91b15a..bc4605314 100644--- a/.pipelex/inference/backends/pipelex_gateway_models.md+++ b/.pipelex/inference/backends/pipelex_gateway_models.md@@ -446,13 +446,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td><td style="text-align:center;background-color:rgba(76,175,80,0.15)">❌</td></tr>-<tr>-<td>mistral-document-ai-2505</td>-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>-<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>-<td style="text-align:center;background-color:rgba(76,175,80,0.15)">❌</td>-</tr></tbody></table>@@ -522,6 +515,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late> **AUTO-GENERATED FILE** - Do not edit manually.-> Last updated: 2026-03-02T23:49:25Z+> Last updated: 2026-03-04T00:21:08Z>> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.\ No newline at end of filediff --git a/.pipelex/inference/backends/pipelex_gateway_models_plain.md b/.pipelex/inference/backends/pipelex_gateway_models_plain.mdindex d39ef8e6b..742c83039 100644--- a/.pipelex/inference/backends/pipelex_gateway_models_plain.md+++ b/.pipelex/inference/backends/pipelex_gateway_models_plain.md@@ -163,9 +163,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late- **deepseek-ocr**- inputs: image- outputs: pages-- **mistral-document-ai-2505**- - inputs: image, pdf- - outputs: pages**About extracted pages:** Each page contains Markdown text (based on AI-interpreted layout) and optional extracted images. A single image input is treated as one page. Pipelex also wraps the `pypdfium2` library for raw text (without any AI interpretation) and images extraction and page views rendering. All these elements can be used as inputs into downstream pipes, including LLM prompts.@@ -196,6 +193,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late> **AUTO-GENERATED FILE** - Do not edit manually.-> Last updated: 2026-03-02T23:49:25Z+> Last updated: 2026-03-04T00:21:08Z>> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.\ No newline at end of filediff --git a/.pipelex/inference/deck/4_search_deck.toml b/.pipelex/inference/deck/4_search_deck.tomlindex 9c5433936..6cc955d7e 100644--- a/.pipelex/inference/deck/4_search_deck.toml+++ b/.pipelex/inference/deck/4_search_deck.toml@@ -19,7 +19,6 @@####################################################################################################[search]-default_depth = "standard"choice_default = "@default-search"####################################################################################################@@ -27,12 +26,12 @@ choice_default = "@default-search"####################################################################################################[search.aliases]-default-search = "linkup/standard"+default-search = "linkup-standard"##################################################################################################### Search Presets####################################################################################################[search.presets]-linkup-standard = { model = "linkup/standard", depth = "standard", include_images = false, include_inline_citations = true }-linkup-deep = { model = "linkup/deep", depth = "deep", include_images = false, include_inline_citations = true }+standard = { model = "linkup-standard", include_images = false, include_inline_citations = true }+deep = { model = "linkup-deep", include_images = false, include_inline_citations = true }diff --git a/.pipelex/inference/routing_profiles.toml b/.pipelex/inference/routing_profiles.tomlindex 612338ae7..090d2d4be 100644--- a/.pipelex/inference/routing_profiles.toml+++ b/.pipelex/inference/routing_profiles.toml@@ -27,8 +27,6 @@ active = "all_pipelex_gateway"[profiles.all_pipelex_gateway]description = "Use Pipelex Gateway for all its supported models"default = "pipelex_gateway"-[profiles.all_pipelex_gateway.routes]-"linkup/*" = "linkup"[profiles.all_anthropic]description = "Use Anthropic backend for all its supported models"@@ -62,6 +60,10 @@ default = "groq"description = "Use HuggingFace backend for all its supported models"default = "huggingface"+[profiles.all_linkup]+description = "Use Linkup backend for all its supported models"+default = "linkup"+[profiles.all_mistral]description = "Use Mistral backend for all its supported models"default = "mistral"diff --git a/.pipelex/pipelex.toml b/.pipelex/pipelex.tomlindex 6b594bceb..0fa16c4ac 100644--- a/.pipelex/pipelex.toml+++ b/.pipelex/pipelex.toml@@ -59,6 +59,10 @@ ranksep = 30 # Vertical spacing between ranks/levelsinitial_zoom = 1.0 # Initial zoom level (1.0 = 100%)pan_to_top = true # Pan to show top of graph on load+[pipelex.pipeline_execution_config.graph_config.reactflow_config.style]+theme = "dark"+palette = "dracula"+##################################################################################################### Storage Config####################################################################################################diff --git a/CHANGELOG.md b/CHANGELOG.mdindex e031e8fc8..804e99d95 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -10,7 +10,7 @@## [v0.19.0] - 2026-03-02### Added- - **Web Search Integration**: Introduced a new `PipeSearch` operator, native support for Linkup as a search backend provider, `SearchResult` and `SearchResultContent` concepts for handling answers with citations, and Model Deck support for search models with presets (e.g., `$linkup-standard`, `$linkup-deep`), aliases, and waterfalls.+ - **Web Search Integration**: Introduced a new `PipeSearch` operator, native support for Linkup as a search backend provider, `SearchResult` and `SearchResultContent` concepts for handling answers with citations, and Model Deck support for search models.- **Graph View Generation**: Added a `--view` option to `pipelex validate bundle` that generates a `ViewSpec` JSON (compatible with ReactFlow) for client-side graph rendering without writing files to disk.### Changeddiff --git a/Makefile b/Makefileindex c0efe06e8..a98f10331 100644--- a/Makefile+++ b/Makefile@@ -171,8 +171,8 @@ export HELPmerge-check-ruff-lint merge-check-ruff-format merge-check-mypy merge-check-pyright merge-check-plxt-format merge-check-plxt-lint \li check-unused-imports fix-unused-imports check-TODOs check-uv \docs docs-check docs-serve-versioned docs-list docs-deploy docs-deploy-stable docs-deploy-specific-version docs-delete \- generate-mthds-schema gms check-mthds-schema cms \- update-gateway-models ugm check-gateway-models cgm up \+ generate-mthds-schema generate-mthds-schema-quiet gms check-mthds-schema cms \+ update-gateway-models update-gateway-models-quiet ugm check-gateway-models cgm up \test-count check-test-badge \serve-graph serve-graph-bg stop-graph-server view-graph sg vg \docs-deploy-root@@ -300,6 +300,9 @@ generate-mthds-schema: env$(call PRINT_TITLE,"Generating MTHDS JSON Schema")$(VENV_PIPELEX_DEV) generate-mthds-schema+generate-mthds-schema-quiet: env+ $(VENV_PIPELEX_DEV) generate-mthds-schema --quiet+gms: generate-mthds-schema@echo "> done: gms = generate-mthds-schema"@@ -314,6 +317,9 @@ update-gateway-models: env$(call PRINT_TITLE,"Updating gateway models reference")$(VENV_PIPELEX_DEV) update-gateway-models+update-gateway-models-quiet: env+ $(VENV_PIPELEX_DEV) update-gateway-models --quiet+ugm: update-gateway-models@echo "> done: ugm = update-gateway-models"@@ -928,10 +934,10 @@ vg: view-graphc: format lint pyright mypy@echo "> done: c = check"-cc: cleanderived regenerate-test-models-quiet generate-mthds-schema c- @echo "> done: cc = cleanderived regenerate-test-models generate-mthds-schema format lint pyright pylint mypy"+cc: cleanderived regenerate-test-models-quiet generate-mthds-schema-quiet update-gateway-models-quiet c+ @echo "> done: cc = cleanderived regenerate-test-models generate-mthds-schema update-gateway-models format lint pyright mypy"-up: generate-mthds-schema update-gateway-models up-kit-configs rules+up: generate-mthds-schema-quiet update-gateway-models-quiet up-kit-configs rules@echo "> done: up = generate-mthds-schema update-gateway-models up-kit-configs rules"check: cc check-unused-imports check-config-sync check-rules check-urls check-gateway-models check-mthds-schema pylintdiff --git a/docs/home/6-build-reliable-ai-workflows/concepts/native-concepts.md b/docs/home/6-build-reliable-ai-workflows/concepts/native-concepts.mdindex 9b2629c99..264255cb6 100644--- a/docs/home/6-build-reliable-ai-workflows/concepts/native-concepts.md+++ b/docs/home/6-build-reliable-ai-workflows/concepts/native-concepts.md@@ -310,7 +310,7 @@ type = "PipeSearch"description = "Search the web for information"inputs = { topic = "Text" }output = "SearchResult"-model = "$linkup-standard"+model = "$standard"prompt = "What is $topic?"```diff --git a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md b/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.mdindex e690e169f..5b16495f9 100644--- a/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md+++ b/docs/home/6-build-reliable-ai-workflows/pipes/pipe-operators/PipeSearch.md@@ -25,8 +25,8 @@ PipeSearch uses the unified inference backend system to manage search providers.Common search presets:-- `$linkup-standard`: Standard web search with fast results-- `$linkup-deep`: Deep web search for more thorough results+- `$standard`: Standard web search with fast results+- `$deep`: Deep web search for more thorough results### MTHDS Parameters@@ -36,7 +36,7 @@ Common search presets:| `description` | string | A description of the search operation. | Yes || `inputs` | dictionary | The input concept(s) for the search query, as a dictionary mapping input names to concept codes. Required when the prompt references variables. | No || `output` | string | The output concept produced by the search. Must be `SearchResult` or a concept that refines `SearchResult`. | Yes |-| `model` | string | The search model preset to use (e.g., `"$linkup-standard"`, `"$linkup-deep"`). Defaults to the model specified in the global config. | No |+| `model` | string | The search model preset to use (e.g., `"$standard"`, `"$deep"`). Defaults to the model specified in the global config. | No || `prompt` | string | The search query. Can be a static string or reference input variables using `$` prefix (e.g., `"What is $topic?"`). | Yes |### Example: Static search query@@ -48,7 +48,7 @@ This pipe performs a fixed search query without any inputs.type = "PipeSearch"description = "Search for the latest AI news"output = "SearchResult"-model = "$linkup-standard"+model = "$standard"prompt = "What are the latest developments in artificial intelligence?"```@@ -62,7 +62,7 @@ type = "PipeSearch"description = "Search the web for information about a topic"inputs = { topic = "Text" }output = "SearchResult"-model = "$linkup-standard"+model = "$standard"prompt = "What is $topic?"```@@ -76,7 +76,7 @@ type = "PipeSearch"description = "Perform deep research on a topic"inputs = { topic = "Text" }output = "SearchResult"-model = "$linkup-deep"+model = "$deep"prompt = "What are the main details about $topic?"```diff --git a/pipelex/builder/pipe/pipe_search_spec.py b/pipelex/builder/pipe/pipe_search_spec.pyindex c69d73417..cc65ed109 100644--- a/pipelex/builder/pipe/pipe_search_spec.py+++ b/pipelex/builder/pipe/pipe_search_spec.py@@ -80,7 +80,6 @@ class PipeSearchSpec(PipeSpec):output=base_blueprint.output,prompt=self.prompt,model=search_choice,- depth=None,include_images=None,max_results=None,from_date=None,diff --git a/pipelex/cli/commands/login/command.py b/pipelex/cli/commands/login/command.pyindex 7c5d7481b..43b99facd 100644--- a/pipelex/cli/commands/login/command.py+++ b/pipelex/cli/commands/login/command.py@@ -25,7 +25,7 @@ class CallbackHandler(BaseHTTPRequestHandler):self._result = resultsuper().__init__(*args, **kwargs) # type: ignore[arg-type]- def do_GET(self) -> None:+ def do_GET(self) -> None: # pylint: disable=invalid-name"""Handle GET /callback?api_key=xxx."""parsed = urlparse(self.path)params = parse_qs(parsed.query)diff --git a/pipelex/cli/dev_cli/commands/preprocess_test_models_cmd.py b/pipelex/cli/dev_cli/commands/preprocess_test_models_cmd.pyindex 1e18c9011..2b4c409a2 100644--- a/pipelex/cli/dev_cli/commands/preprocess_test_models_cmd.py+++ b/pipelex/cli/dev_cli/commands/preprocess_test_models_cmd.py@@ -32,7 +32,7 @@ TEST_PROFILES_PATH = Path(ConfigPaths.DEV_CONFIG_DIR_PATH) / "test_profiles.tomlTEST_PROFILES_OVERRIDE_PATH = Path(ConfigPaths.DEV_CONFIG_DIR_PATH) / "test_profiles_override.toml"# Model types we care about-MODEL_TYPES = ["llm", "img_gen", "text_extractor"]+MODEL_TYPES = ["llm", "img_gen", "text_extractor", "search"]# Default model type from backend configDEFAULT_MODEL_TYPE = "llm"@@ -60,6 +60,7 @@ def _extract_models_from_backend_toml(backend_path: Path) -> dict[str, list[str]"llm": [],"img_gen": [],"text_extractor": [],+ "search": [],}for key, value in config.items():@@ -97,7 +98,7 @@ def _fetch_gateway_models() -> dict[str, list[str]]:remote_config = RemoteConfigFetcher.fetch_remote_config()model_specs = dict(remote_config.backend_model_specs)except (RemoteConfigFetchError, RemoteConfigValidationError):- return {"llm": [], "img_gen": [], "text_extractor": []}+ return {"llm": [], "img_gen": [], "text_extractor": [], "search": []}# Get defaultsdefaults = model_specs.get("defaults", {})@@ -112,6 +113,7 @@ def _fetch_gateway_models() -> dict[str, list[str]]:"llm": [],"img_gen": [],"text_extractor": [],+ "search": [],}for key, value in model_specs.items():@@ -156,6 +158,7 @@ def _collect_all_model_availability() -> dict[str, Any]:"llm": {},"img_gen": {},"text_extractor": {},+ "search": {},}backends_dir = Path(config_manager.backends_dir_path)@@ -377,6 +380,7 @@ def _filter_models_by_profile("llm": [],"img_gen": [],"text_extractor": [],+ "search": [],}# If include_all is set, return all valid pairs@@ -426,6 +430,7 @@ def _filter_models_by_profile("llm_models": "llm","img_gen_models": "img_gen","extract_models": "text_extractor",+ "search_models": "search",}# Model type to collection type mapping (internal name -> TOML section name)@@ -433,6 +438,7 @@ def _filter_models_by_profile("llm": "llm","img_gen": "img_gen","text_extractor": "extract",+ "search": "search",}# Resolve model lists from profile using advanced specifiers@@ -529,6 +535,14 @@ def _generate_fixtures_python(lines.append("]")lines.append("")+ # Search combos+ search_pairs = combo_pairs.get("search", [])+ lines.append("SEARCH_COMBOS: list[ModelCombo] = [")+ for model, backend in sorted(search_pairs):+ lines.append(f" ModelCombo({model!r}, {backend!r}),")+ lines.append("]")+ lines.append("")+return "\n".join(lines)@@ -568,10 +582,12 @@ def _display_summary(llm_total = sum(len(models) for models in availability.get("llm", {}).values())img_gen_total = sum(len(models) for models in availability.get("img_gen", {}).values())extract_total = sum(len(models) for models in availability.get("text_extractor", {}).values())+ search_total = sum(len(models) for models in availability.get("search", {}).values())table.add_row("LLM Models", str(llm_total), str(len(combo_pairs.get("llm", []))))table.add_row("Image Gen Models", str(img_gen_total), str(len(combo_pairs.get("img_gen", []))))table.add_row("Extract Models", str(extract_total), str(len(combo_pairs.get("text_extractor", []))))+ table.add_row("Search Models", str(search_total), str(len(combo_pairs.get("search", []))))table.add_row("", "", "")table.add_row("Total Backends", str(len(total_backends)), "-")table.add_row("Total Model/Backend Pairs", str(total_models), str(filtered_models))diff --git a/pipelex/cogt/models/model_deck.py b/pipelex/cogt/models/model_deck.pyindex cd411538b..08a4f3ce5 100644--- a/pipelex/cogt/models/model_deck.py+++ b/pipelex/cogt/models/model_deck.py@@ -30,7 +30,6 @@ from pipelex.cogt.model_backends.constraints import ValuedConstraintfrom pipelex.cogt.model_backends.model_spec import InferenceModelSpecfrom pipelex.cogt.model_backends.model_type import ModelTypefrom pipelex.cogt.models.model_reference import ModelReference, ModelReferenceKind, ModelReferenceParseError, ensure_model_reference-from pipelex.cogt.search.search_depth import SearchDepthfrom pipelex.cogt.search.search_setting import SearchModelChoice, SearchSettingfrom pipelex.system.configuration.config_model import ConfigModelfrom pipelex.system.exceptions import ConfigValidationError@@ -69,7 +68,6 @@ class ImgGenDeckBlueprint(ConfigModel):class SearchDeckBlueprint(ConfigModel):- default_depth: SearchDepth = Field(strict=False)aliases: dict[str, str] = Field(default_factory=dict)waterfalls: dict[str, list[str]] = Field(default_factory=dict)presets: dict[str, SearchSetting] = Field(default_factory=dict)@@ -115,7 +113,6 @@ class ModelDeck(ConfigModel):img_gen_choice_default: ImgGenModelChoice# Search-specific- search_default_depth: SearchDepth = Field(strict=False)search_aliases: dict[str, str] = Field(default_factory=dict)search_waterfalls: dict[str, list[str]] = Field(default_factory=dict)search_presets: dict[str, SearchSetting] = Field(default_factory=dict)@@ -426,7 +423,7 @@ class ModelDeck(ConfigModel):)case ModelReferenceKind.ALIAS:if alias_target := self.search_aliases.get(ref.name):- return SearchSetting(model=alias_target, depth=self.search_default_depth)+ return SearchSetting(model=alias_target)msg = f"Alias '{ref.name}' was not found in the model deck"raise ModelChoiceNotFoundError(message=msg,@@ -437,7 +434,7 @@ class ModelDeck(ConfigModel):)case ModelReferenceKind.WATERFALL:if ref.name in self.search_waterfalls:- return SearchSetting(model=ref.name, depth=self.search_default_depth)+ return SearchSetting(model=ref.name)msg = f"Waterfall '{ref.name}' was not found in the model deck"raise ModelChoiceNotFoundError(message=msg,@@ -449,7 +446,7 @@ class ModelDeck(ConfigModel):case ModelReferenceKind.HANDLE:self._warn_if_ambiguous_search(ref.name)if self.is_model_handle_defined(model_handle=ref.name, model_type=ModelType.SEARCH):- return SearchSetting(model=ref.name, depth=self.search_default_depth)+ return SearchSetting(model=ref.name)self._raise_handle_not_found_error(ref=ref,model_type=ModelType.SEARCH,diff --git a/pipelex/cogt/models/model_manager.py b/pipelex/cogt/models/model_manager.pyindex fc3d4c9f1..1a636f78f 100644--- a/pipelex/cogt/models/model_manager.py+++ b/pipelex/cogt/models/model_manager.py@@ -168,7 +168,6 @@ class ModelManager(ModelManagerAbstract):img_gen_presets=model_deck_blueprint.img_gen.presets,img_gen_choice_default=model_deck_blueprint.img_gen.choice_default,# Search- search_default_depth=model_deck_blueprint.search.default_depth,search_aliases=model_deck_blueprint.search.aliases,search_waterfalls=model_deck_blueprint.search.waterfalls,search_presets=model_deck_blueprint.search.presets,diff --git a/pipelex/cogt/search/fetch_job.py b/pipelex/cogt/search/fetch_job.pynew file mode 100644index 000000000..1beac53b7--- /dev/null+++ b/pipelex/cogt/search/fetch_job.py@@ -0,0 +1,35 @@+from datetime import datetime++from pydantic import BaseModel+from typing_extensions import override++from pipelex.cogt.inference.inference_job_abstract import InferenceJobAbstract+from pipelex.cogt.model_backends.model_spec import InferenceModelSpec+from pipelex.cogt.search.fetch_report import FetchTokensUsage+++class FetchJobReport(BaseModel):+ fetch_tokens_usage: FetchTokensUsage | None = None+++class FetchJob(InferenceJobAbstract):+ job_report: FetchJobReport = FetchJobReport()++ @override+ def validate_before_execution(self):+ pass++ def fetch_job_before_start(self, inference_model: InferenceModelSpec):+ self.job_metadata.started_at = datetime.now()++ self.job_report = FetchJobReport()+ self.job_report.fetch_tokens_usage = FetchTokensUsage(+ job_metadata=self.job_metadata,+ inference_model_name=inference_model.name,+ unit_costs=inference_model.costs,+ inference_model_id=inference_model.model_id,+ nb_tokens_by_category={},+ )++ def fetch_job_after_complete(self):+ self.job_metadata.completed_at = datetime.now()diff --git a/pipelex/cogt/search/fetch_report.py b/pipelex/cogt/search/fetch_report.pynew file mode 100644index 000000000..0a68e8287--- /dev/null+++ b/pipelex/cogt/search/fetch_report.py@@ -0,0 +1,72 @@+from typing import Any++from pydantic import BaseModel++from pipelex.cogt.usage.cost_category import CostCategory, CostsByCategoryDict+from pipelex.cogt.usage.token_category import NbTokensByCategoryDict, TokenCategory+from pipelex.pipeline.job_metadata import JobMetadata+from pipelex.types import StrEnum+++class FetchTokenCostReportField(StrEnum):+ MODEL_TYPE = "model_type"+ FETCH_NAME = "fetch_name"+ PLATFORM_FETCH_ID = "platform_fetch_id"+ NB_TOKENS_INPUT = "nb_tokens_input"+ NB_TOKENS_INPUT_CACHED = "nb_tokens_input_cached"+ NB_TOKENS_INPUT_NON_CACHED = "nb_tokens_input_non_cached"+ NB_TOKENS_INPUT_JOINED = "nb_tokens_input_joined"+ NB_TOKENS_OUTPUT = "nb_tokens_output"+ COST_INPUT_CACHED = "cost_input_cached"+ COST_INPUT_NON_CACHED = "cost_input_non_cached"+ COST_INPUT_JOINED = "cost_input_joined"+ COST_OUTPUT = "cost_output"++ @staticmethod+ def report_field_for_nb_tokens_by_category(token_category: TokenCategory) -> str:+ return f"nb_tokens_{token_category}"++ @staticmethod+ def report_field_for_cost_by_category(token_category: CostCategory) -> str:+ return f"cost_{token_category}"+++class FetchTokenCostReport(BaseModel):+ model_type: str = "fetch"+ job_metadata: JobMetadata+ inference_model_name: str+ platform_model_id: str++ nb_tokens_by_category: NbTokensByCategoryDict+ costs_by_token_category: CostsByCategoryDict++ def as_flat_dictionary(self) -> dict[str, Any]:+ the_dict: dict[str, Any] = {}+ dict_for_job_metadata = self.job_metadata.model_dump(serialize_as_any=True)+ the_dict.update(dict_for_job_metadata)+ dict_for_model: dict[str, Any] = {+ FetchTokenCostReportField.MODEL_TYPE: self.model_type,+ FetchTokenCostReportField.FETCH_NAME: self.inference_model_name,+ FetchTokenCostReportField.PLATFORM_FETCH_ID: self.platform_model_id,+ }+ the_dict.update(dict_for_model)+ dict_for_nb_tokens = {+ FetchTokenCostReportField.report_field_for_nb_tokens_by_category(token_category): nb_tokens+ for token_category, nb_tokens in self.nb_tokens_by_category.items()+ }+ the_dict.update(dict_for_nb_tokens)+ dict_for_costs = {+ FetchTokenCostReportField.report_field_for_cost_by_category(token_category): cost+ for token_category, cost in self.costs_by_token_category.items()+ }+ the_dict.update(dict_for_costs)+ return the_dict+++class FetchTokensUsage(BaseModel):+ model_type: str = "fetch"+ job_metadata: JobMetadata+ inference_model_name: str+ unit_costs: CostsByCategoryDict+ inference_model_id: str+ nb_tokens_by_category: NbTokensByCategoryDictdiff --git a/pipelex/cogt/search/fetch_worker_abstract.py b/pipelex/cogt/search/fetch_worker_abstract.pynew file mode 100644index 000000000..f19e387d7--- /dev/null+++ b/pipelex/cogt/search/fetch_worker_abstract.py@@ -0,0 +1,34 @@+from abc import ABC, abstractmethod++from pipelex.core.stuffs.text_and_images_content import TextAndImagesContent+from pipelex.pipeline.job_metadata import JobMetadata+from pipelex.reporting.reporting_protocol import ReportingProtocol+++class FetchWorkerAbstract(ABC):+ def __init__(self, reporting_delegate: ReportingProtocol | None = None):+ self.reporting_delegate = reporting_delegate++ @abstractmethod+ async def fetch_url(+ self,+ url: str,+ job_metadata: JobMetadata,+ include_raw_html: bool | None = None,+ render_js: bool | None = None,+ extract_images: bool | None = None,+ timeout: float | None = None, # noqa: ASYNC109+ ) -> TextAndImagesContent:+ """Fetch and clean the content of a web page, returning text and optionally images.++ Args:+ url: The URL of the web page to fetch+ job_metadata: Job metadata for cost reporting+ include_raw_html: Whether to include the raw HTML of the webpage in the response+ render_js: Whether to render the JavaScript of the webpage before fetching+ extract_images: Whether to extract images from the webpage+ timeout: The timeout for the HTTP request, in seconds++ Returns:+ TextAndImagesContent with the fetched page content+ """diff --git a/pipelex/cogt/search/search_job.py b/pipelex/cogt/search/search_job.pynew file mode 100644index 000000000..7977987a5--- /dev/null+++ b/pipelex/cogt/search/search_job.py@@ -0,0 +1,35 @@+from datetime import datetime++from pydantic import BaseModel+from typing_extensions import override++from pipelex.cogt.inference.inference_job_abstract import InferenceJobAbstract+from pipelex.cogt.model_backends.model_spec import InferenceModelSpec+from pipelex.cogt.search.search_report import SearchTokensUsage+++class SearchJobReport(BaseModel):+ search_tokens_usage: SearchTokensUsage | None = None+++class SearchJob(InferenceJobAbstract):+ job_report: SearchJobReport = SearchJobReport()++ @override+ def validate_before_execution(self):+ pass++ def search_job_before_start(self, inference_model: InferenceModelSpec):+ self.job_metadata.started_at = datetime.now()++ self.job_report = SearchJobReport()+ self.job_report.search_tokens_usage = SearchTokensUsage(+ job_metadata=self.job_metadata,+ inference_model_name=inference_model.name,+ unit_costs=inference_model.costs,+ inference_model_id=inference_model.model_id,+ nb_tokens_by_category={},+ )++ def search_job_after_complete(self):+ self.job_metadata.completed_at = datetime.now()diff --git a/pipelex/cogt/search/search_job_factory.py b/pipelex/cogt/search/search_job_factory.pynew file mode 100644index 000000000..6f5efeabe--- /dev/null+++ b/pipelex/cogt/search/search_job_factory.py@@ -0,0 +1,17 @@+from pipelex.cogt.search.fetch_job import FetchJob+from pipelex.cogt.search.search_job import SearchJob+from pipelex.pipeline.job_metadata import JobCategory, JobMetadata+++class SearchJobFactory:+ @classmethod+ def make_search_job(cls, job_metadata: JobMetadata) -> SearchJob:+ job_metadata.job_category = JobCategory.SEARCH_JOB+ return SearchJob(job_metadata=job_metadata)+++class FetchJobFactory:+ @classmethod+ def make_fetch_job(cls, job_metadata: JobMetadata) -> FetchJob:+ job_metadata.job_category = JobCategory.FETCH_JOB+ return FetchJob(job_metadata=job_metadata)diff --git a/pipelex/cogt/search/search_report.py b/pipelex/cogt/search/search_report.pynew file mode 100644index 000000000..5b57784eb--- /dev/null+++ b/pipelex/cogt/search/search_report.py@@ -0,0 +1,72 @@+from typing import Any++from pydantic import BaseModel++from pipelex.cogt.usage.cost_category import CostCategory, CostsByCategoryDict+from pipelex.cogt.usage.token_category import NbTokensByCategoryDict, TokenCategory+from pipelex.pipeline.job_metadata import JobMetadata+from pipelex.types import StrEnum+++class SearchTokenCostReportField(StrEnum):+ MODEL_TYPE = "model_type"+ SEARCH_NAME = "search_name"+ PLATFORM_SEARCH_ID = "platform_search_id"+ NB_TOKENS_INPUT = "nb_tokens_input"+ NB_TOKENS_INPUT_CACHED = "nb_tokens_input_cached"+ NB_TOKENS_INPUT_NON_CACHED = "nb_tokens_input_non_cached"+ NB_TOKENS_INPUT_JOINED = "nb_tokens_input_joined"+ NB_TOKENS_OUTPUT = "nb_tokens_output"+ COST_INPUT_CACHED = "cost_input_cached"+ COST_INPUT_NON_CACHED = "cost_input_non_cached"+ COST_INPUT_JOINED = "cost_input_joined"+ COST_OUTPUT = "cost_output"++ @staticmethod+ def report_field_for_nb_tokens_by_category(token_category: TokenCategory) -> str:+ return f"nb_tokens_{token_category}"++ @staticmethod+ def report_field_for_cost_by_category(token_category: CostCategory) -> str:+ return f"cost_{token_category}"+++class SearchTokenCostReport(BaseModel):+ model_type: str = "search"+ job_metadata: JobMetadata+ inference_model_name: str+ platform_model_id: str++ nb_tokens_by_category: NbTokensByCategoryDict+ costs_by_token_category: CostsByCategoryDict++ def as_flat_dictionary(self) -> dict[str, Any]:+ the_dict: dict[str, Any] = {}+ dict_for_job_metadata = self.job_metadata.model_dump(serialize_as_any=True)+ the_dict.update(dict_for_job_metadata)+ dict_for_model: dict[str, Any] = {+ SearchTokenCostReportField.MODEL_TYPE: self.model_type,+ SearchTokenCostReportField.SEARCH_NAME: self.inference_model_name,+ SearchTokenCostReportField.PLATFORM_SEARCH_ID: self.platform_model_id,+ }+ the_dict.update(dict_for_model)+ dict_for_nb_tokens = {+ SearchTokenCostReportField.report_field_for_nb_tokens_by_category(token_category): nb_tokens+ for token_category, nb_tokens in self.nb_tokens_by_category.items()+ }+ the_dict.update(dict_for_nb_tokens)+ dict_for_costs = {+ SearchTokenCostReportField.report_field_for_cost_by_category(token_category): cost+ for token_category, cost in self.costs_by_token_category.items()+ }+ the_dict.update(dict_for_costs)+ return the_dict+++class SearchTokensUsage(BaseModel):+ model_type: str = "search"+ job_metadata: JobMetadata+ inference_model_name: str+ unit_costs: CostsByCategoryDict+ inference_model_id: str+ nb_tokens_by_category: NbTokensByCategoryDictdiff --git a/pipelex/cogt/search/search_setting.py b/pipelex/cogt/search/search_setting.pyindex 64acb78b8..a37eac148 100644--- a/pipelex/cogt/search/search_setting.py+++ b/pipelex/cogt/search/search_setting.py@@ -3,20 +3,18 @@ from typing import Annotated, Unionfrom pydantic import BeforeValidator, Fieldfrom pipelex.cogt.models.model_reference import ModelReference, parse_model_reference-from pipelex.cogt.search.search_depth import SearchDepthfrom pipelex.system.configuration.config_model import ConfigModelclass SearchSetting(ConfigModel):model: str- depth: SearchDepth = Field(strict=False)include_images: bool = Falseinclude_inline_citations: bool = Truemax_results: int | None = Field(default=None, ge=1)description: str | None = Nonedef desc(self) -> str:- return f"SearchSetting(model={self.model}, depth={self.depth}, max_results={self.max_results})"+ return f"SearchSetting(model={self.model}, max_results={self.max_results})"# SearchModelChoice accepts SearchSetting, ModelReference, or a string (which gets parsed to ModelReference)diff --git a/pipelex/cogt/search/search_worker_abstract.py b/pipelex/cogt/search/search_worker_abstract.pyindex e6ae6a225..de70b2564 100644--- a/pipelex/cogt/search/search_worker_abstract.py+++ b/pipelex/cogt/search/search_worker_abstract.py@@ -3,14 +3,20 @@ from typing import Anyfrom pipelex.cogt.search.search_setting import SearchSettingfrom pipelex.core.stuffs.search_result_content import SearchResultContent+from pipelex.pipeline.job_metadata import JobMetadata+from pipelex.reporting.reporting_protocol import ReportingProtocolclass SearchWorkerAbstract(ABC):+ def __init__(self, reporting_delegate: ReportingProtocol | None = None):+ self.reporting_delegate = reporting_delegate+@abstractmethodasync def search_sourced_answer(self,query: str,search_setting: SearchSetting,+ job_metadata: JobMetadata,include_domains: list[str] | None = None,exclude_domains: list[str] | None = None,from_date: str | None = None,@@ -21,6 +27,7 @@ class SearchWorkerAbstract(ABC):Args:query: The search query textsearch_setting: Search configuration including model, depth, etc.+ job_metadata: Job metadata for cost reportinginclude_domains: Optional list of domains to restrict search toexclude_domains: Optional list of domains to exclude from searchfrom_date: Optional start date filter (YYYY-MM-DD)@@ -36,6 +43,7 @@ class SearchWorkerAbstract(ABC):query: str,search_setting: SearchSetting,output_schema: type,+ job_metadata: JobMetadata,include_domains: list[str] | None = None,exclude_domains: list[str] | None = None,from_date: str | None = None,@@ -47,6 +55,7 @@ class SearchWorkerAbstract(ABC):query: The search query textsearch_setting: Search configuration including model, depth, etc.output_schema: Pydantic model class defining the expected output structure+ job_metadata: Job metadata for cost reportinginclude_domains: Optional list of domains to restrict search toexclude_domains: Optional list of domains to exclude from searchfrom_date: Optional start date filter (YYYY-MM-DD)diff --git a/pipelex/cogt/search/search_worker_factory.py b/pipelex/cogt/search/search_worker_factory.pyindex 985d8a2e8..811435198 100644--- a/pipelex/cogt/search/search_worker_factory.py+++ b/pipelex/cogt/search/search_worker_factory.py@@ -1,35 +1,89 @@+from pipelex.cogt.model_backends.model_spec import InferenceModelSpec+from pipelex.cogt.search.fetch_worker_abstract import FetchWorkerAbstractfrom pipelex.cogt.search.search_worker_abstract import SearchWorkerAbstract+from pipelex.hub import get_models_manager, get_plugin_manager, get_report_delegate+from pipelex.plugins.plugin import Plugin-# Cache of search worker instances by provider prefix-_search_workers: dict[str, SearchWorkerAbstract] = {}+class SearchWorkerFactory:+ @classmethod+ def make_search_worker(+ cls,+ inference_model: InferenceModelSpec,+ ) -> SearchWorkerAbstract:+ """Create a search worker for the given inference model.-def get_search_worker(model_handle: str) -> SearchWorkerAbstract:- """Get a search worker instance for the given model handle.+ Discriminates on plugin.sdk to select the appropriate implementation.- The model handle format is "provider/variant" (e.g., "linkup/standard", "linkup/deep").- The provider prefix determines which worker implementation to use.+ Args:+ inference_model: The model spec from the backend configuration.- Args:- model_handle: The search model handle (e.g., "linkup/standard")+ Returns:+ A SearchWorkerAbstract instance.+ """+ plugin = Plugin.make_for_inference_model(inference_model=inference_model)+ backend = get_models_manager().get_required_inference_backend(inference_model.backend_name)+ plugin_sdk_registry = get_plugin_manager().plugin_sdk_registry+ search_worker: SearchWorkerAbstract+ match plugin.sdk:+ case "linkup":+ from pipelex.plugins.linkup.linkup_worker import LinkupWorker # noqa: PLC0415- Returns:- A SearchWorkerAbstract instance for the provider- """- provider = model_handle.split("/", maxsplit=1)[0] if "/" in model_handle else model_handle+ search_worker = LinkupWorker(inference_model=inference_model, reporting_delegate=get_report_delegate())+ case "gateway_search":+ from pipelex.plugins.gateway.gateway_factory import GatewayFactory # noqa: PLC0415+ from pipelex.plugins.gateway.gateway_search_worker import GatewaySearchWorker # noqa: PLC0415- if provider in _search_workers:- return _search_workers[provider]+ sdk_instance = plugin_sdk_registry.get_sdk_instance(plugin=plugin) or plugin_sdk_registry.set_sdk_instance(+ plugin=plugin,+ sdk_instance=GatewayFactory.make_portkey_client(backend=backend),+ )+ search_worker = GatewaySearchWorker(+ sdk_instance=sdk_instance, inference_model=inference_model, reporting_delegate=get_report_delegate()+ )+ case _:+ msg = f"Plugin '{plugin}' is not supported for search"+ raise NotImplementedError(msg)- worker: SearchWorkerAbstract- match provider:- case "linkup":- from pipelex.plugins.linkup.linkup_search_worker import LinkupSearchWorker # noqa: PLC0415+ return search_worker- worker = LinkupSearchWorker()- case _:- msg = f"Unknown search provider: '{provider}' (from model handle '{model_handle}')"- raise ValueError(msg)+ @classmethod+ def make_fetch_worker(+ cls,+ inference_model: InferenceModelSpec,+ ) -> FetchWorkerAbstract:+ """Create a fetch worker for the given inference model.- _search_workers[provider] = worker- return worker+ Discriminates on plugin.sdk to select the appropriate implementation.++ Args:+ inference_model: The model spec from the backend configuration.++ Returns:+ A FetchWorkerAbstract instance.+ """+ plugin = Plugin.make_for_inference_model(inference_model=inference_model)+ backend = get_models_manager().get_required_inference_backend(inference_model.backend_name)+ plugin_sdk_registry = get_plugin_manager().plugin_sdk_registry+ fetch_worker: FetchWorkerAbstract+ match plugin.sdk:+ case "linkup":+ from pipelex.plugins.linkup.linkup_worker import LinkupWorker # noqa: PLC0415++ fetch_worker = LinkupWorker(inference_model=inference_model, reporting_delegate=get_report_delegate())+ case "gateway_search":+ from pipelex.plugins.gateway.gateway_factory import GatewayFactory # noqa: PLC0415+ from pipelex.plugins.gateway.gateway_fetch_worker import GatewayFetchWorker # noqa: PLC0415++ sdk_instance = plugin_sdk_registry.get_sdk_instance(plugin=plugin) or plugin_sdk_registry.set_sdk_instance(+ plugin=plugin,+ sdk_instance=GatewayFactory.make_portkey_client(backend=backend),+ )+ fetch_worker = GatewayFetchWorker(+ sdk_instance=sdk_instance, inference_model=inference_model, reporting_delegate=get_report_delegate()+ )+ case _:+ msg = f"Plugin '{plugin}' is not supported for fetch"+ raise NotImplementedError(msg)++ return fetch_workerdiff --git a/pipelex/cogt/usage/cost_registry.py b/pipelex/cogt/usage/cost_registry.pyindex 6d523ca9c..91b3abe43 100644--- a/pipelex/cogt/usage/cost_registry.py+++ b/pipelex/cogt/usage/cost_registry.py@@ -12,14 +12,16 @@ from pipelex.cogt.exceptions import CostRegistryErrorfrom pipelex.cogt.extract.extract_report import ExtractTokenCostReport, ExtractTokenCostReportField, ExtractTokensUsagefrom pipelex.cogt.img_gen.img_gen_report import ImgGenTokenCostReport, ImgGenTokenCostReportField, ImgGenTokensUsagefrom pipelex.cogt.llm.llm_report import LLMTokenCostReport, LLMTokenCostReportField, LLMTokensUsage+from pipelex.cogt.search.fetch_report import FetchTokenCostReport, FetchTokenCostReportField, FetchTokensUsage+from pipelex.cogt.search.search_report import SearchTokenCostReport, SearchTokenCostReportField, SearchTokensUsagefrom pipelex.cogt.usage.cost_category import CostCategory, CostsByCategoryDictfrom pipelex.cogt.usage.costs_per_token import model_cost_per_tokenfrom pipelex.cogt.usage.token_category import TokenCategoryfrom pipelex.hub import get_consolefrom pipelex.tools.typing.pydantic_utils import empty_list_factory_of-TokensUsage = LLMTokensUsage | ImgGenTokensUsage | ExtractTokensUsage-TokenCostReport = LLMTokenCostReport | ImgGenTokenCostReport | ExtractTokenCostReport+TokensUsage = LLMTokensUsage | ImgGenTokensUsage | ExtractTokensUsage | SearchTokensUsage | FetchTokensUsage+TokenCostReport = LLMTokenCostReport | ImgGenTokenCostReport | ExtractTokenCostReport | SearchTokenCostReport | FetchTokenCostReportCostRegistryRoot = list[TokenCostReport]@@ -80,7 +82,9 @@ class CostRegistry(RootModel[CostRegistryRoot]):model_name = (record.get(report_field.LLM_NAME)or record.get(ImgGenTokenCostReportField.IMG_GEN_NAME)- or record.get(ExtractTokenCostReportField.EXTRACT_NAME, "unknown")+ or record.get(ExtractTokenCostReportField.EXTRACT_NAME)+ or record.get(SearchTokenCostReportField.SEARCH_NAME)+ or record.get(FetchTokenCostReportField.FETCH_NAME, "unknown"))model_type = record.get(report_field.MODEL_TYPE, "llm")model_types[model_name] = model_type@@ -231,6 +235,24 @@ class CostRegistry(RootModel[CostRegistryRoot]):nb_tokens_by_category=tokens_usage.nb_tokens_by_category,costs_by_token_category=costs_by_token_category,)+ if isinstance(tokens_usage, SearchTokensUsage):+ return SearchTokenCostReport(+ model_type=tokens_usage.model_type,+ job_metadata=tokens_usage.job_metadata,+ inference_model_name=tokens_usage.inference_model_name,+ platform_model_id=tokens_usage.inference_model_id,+ nb_tokens_by_category=tokens_usage.nb_tokens_by_category,+ costs_by_token_category=costs_by_token_category,+ )+ if isinstance(tokens_usage, FetchTokensUsage):+ return FetchTokenCostReport(+ model_type=tokens_usage.model_type,+ job_metadata=tokens_usage.job_metadata,+ inference_model_name=tokens_usage.inference_model_name,+ platform_model_id=tokens_usage.inference_model_id,+ nb_tokens_by_category=tokens_usage.nb_tokens_by_category,+ costs_by_token_category=costs_by_token_category,+ )return ExtractTokenCostReport(model_type=tokens_usage.model_type,job_metadata=tokens_usage.job_metadata,diff --git a/pipelex/core/stuffs/text_and_images_content.py b/pipelex/core/stuffs/text_and_images_content.pyindex 6d78ba707..83fecdeff 100644--- a/pipelex/core/stuffs/text_and_images_content.py+++ b/pipelex/core/stuffs/text_and_images_content.py@@ -16,6 +16,7 @@ from pipelex.tools.misc.pretty import PrettyPrintableclass TextAndImagesContent(StuffContent):text: TextContent | None = Field(default=None, description="A text content")images: list[ImageContent] | None = Field(default=None, description="A list of images that were extracted from the text")+ raw_html: str | None = Field(default=None, description="The raw HTML of the fetched page, if requested")@property@override@@ -43,6 +44,8 @@ class TextAndImagesContent(StuffContent):# TODO: include the images into the HTML rendering@overridedef rendered_html(self) -> str:+ if self.raw_html:+ return self.raw_htmlif self.text:return self.text.rendered_html()return ""@@ -62,6 +65,8 @@ class TextAndImagesContent(StuffContent):# TODO: include the images into the HTML rendering@overrideasync def rendered_html_async(self) -> str:+ if self.raw_html:+ return self.raw_htmlif self.text:rendered = await self.text.rendered_html_async()else:diff --git a/pipelex/kit/configs/inference/backends/linkup.toml b/pipelex/kit/configs/inference/backends/linkup.tomlindex 9ff7d159f..184e324e9 100644--- a/pipelex/kit/configs/inference/backends/linkup.toml+++ b/pipelex/kit/configs/inference/backends/linkup.toml@@ -24,14 +24,14 @@ thinking_mode = "none"# SEARCH MODELS################################################################################-["linkup/standard"]+["linkup-standard"]model_id = "standard"inputs = ["text"]-outputs = ["structured"]-costs = {}+outputs = ["sourced-answers", "structured"]+costs = { input = 0.005, output = 0 }-["linkup/deep"]+["linkup-deep"]model_id = "deep"inputs = ["text"]-outputs = ["structured"]-costs = {}+outputs = ["sourced-answers", "structured"]+costs = { input = 0.05, output = 0 }diff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md b/pipelex/kit/configs/inference/backends/pipelex_gateway_models.mdindex 28b91b15a..8b0e2adc8 100644--- a/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway_models.md@@ -446,13 +446,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td><td style="text-align:center;background-color:rgba(76,175,80,0.15)">❌</td></tr>-<tr>-<td>mistral-document-ai-2505</td>-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>-<td style="text-align:center;background-color:rgba(33,150,243,0.15)">✅</td>-<td style="text-align:center;background-color:rgba(76,175,80,0.15)">✅</td>-<td style="text-align:center;background-color:rgba(76,175,80,0.15)">❌</td>-</tr></tbody></table>@@ -522,6 +515,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late> **AUTO-GENERATED FILE** - Do not edit manually.-> Last updated: 2026-03-02T23:49:25Z+> Last updated: 2026-03-03T22:21:10Z>> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.\ No newline at end of filediff --git a/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md b/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.mdindex d39ef8e6b..4d38f25c9 100644--- a/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md+++ b/pipelex/kit/configs/inference/backends/pipelex_gateway_models_plain.md@@ -163,9 +163,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late- **deepseek-ocr**- inputs: image- outputs: pages-- **mistral-document-ai-2505**- - inputs: image, pdf- - outputs: pages**About extracted pages:** Each page contains Markdown text (based on AI-interpreted layout) and optional extracted images. A single image input is treated as one page. Pipelex also wraps the `pypdfium2` library for raw text (without any AI interpretation) and images extraction and page views rendering. All these elements can be used as inputs into downstream pipes, including LLM prompts.@@ -196,6 +193,6 @@ For configuration details, see the [documentation](https://docs.pipelex.com/late> **AUTO-GENERATED FILE** - Do not edit manually.-> Last updated: 2026-03-02T23:49:25Z+> Last updated: 2026-03-03T22:21:10Z>> Run `pipelex-dev update-gateway-models` or `make ugm` to regenerate.\ No newline at end of filediff --git a/pipelex/kit/configs/inference/deck/4_search_deck.toml b/pipelex/kit/configs/inference/deck/4_search_deck.tomlindex 9c5433936..6cc955d7e 100644--- a/pipelex/kit/configs/inference/deck/4_search_deck.toml+++ b/pipelex/kit/configs/inference/deck/4_search_deck.toml@@ -19,7 +19,6 @@####################################################################################################[search]-default_depth = "standard"choice_default = "@default-search"####################################################################################################@@ -27,12 +26,12 @@ choice_default = "@default-search"####################################################################################################[search.aliases]-default-search = "linkup/standard"+default-search = "linkup-standard"##################################################################################################### Search Presets####################################################################################################[search.presets]-linkup-standard = { model = "linkup/standard", depth = "standard", include_images = false, include_inline_citations = true }-linkup-deep = { model = "linkup/deep", depth = "deep", include_images = false, include_inline_citations = true }+standard = { model = "linkup-standard", include_images = false, include_inline_citations = true }+deep = { model = "linkup-deep", include_images = false, include_inline_citations = true }diff --git a/pipelex/kit/configs/inference/routing_profiles.toml b/pipelex/kit/configs/inference/routing_profiles.tomlindex 612338ae7..090d2d4be 100644--- a/pipelex/kit/configs/inference/routing_profiles.toml+++ b/pipelex/kit/configs/inference/routing_profiles.toml@@ -27,8 +27,6 @@ active = "all_pipelex_gateway"[profiles.all_pipelex_gateway]description = "Use Pipelex Gateway for all its supported models"default = "pipelex_gateway"-[profiles.all_pipelex_gateway.routes]-"linkup/*" = "linkup"[profiles.all_anthropic]description = "Use Anthropic backend for all its supported models"@@ -62,6 +60,10 @@ default = "groq"description = "Use HuggingFace backend for all its supported models"default = "huggingface"+[profiles.all_linkup]+description = "Use Linkup backend for all its supported models"+default = "linkup"+[profiles.all_mistral]description = "Use Mistral backend for all its supported models"default = "mistral"diff --git a/pipelex/kit/configs/pipelex.toml b/pipelex/kit/configs/pipelex.tomlindex 6b594bceb..0fa16c4ac 100644--- a/pipelex/kit/configs/pipelex.toml+++ b/pipelex/kit/configs/pipelex.toml@@ -59,6 +59,10 @@ ranksep = 30 # Vertical spacing between ranks/levelsinitial_zoom = 1.0 # Initial zoom level (1.0 = 100%)pan_to_top = true # Pan to show top of graph on load+[pipelex.pipeline_execution_config.graph_config.reactflow_config.style]+theme = "dark"+palette = "dracula"+##################################################################################################### Storage Config####################################################################################################diff --git a/pipelex/pipe_operators/search/pipe_search.py b/pipelex/pipe_operators/search/pipe_search.pyindex 6eba17f9f..0ff820734 100644--- a/pipelex/pipe_operators/search/pipe_search.py+++ b/pipelex/pipe_operators/search/pipe_search.py@@ -7,9 +7,8 @@ from pipelex.cogt.content_generation.dry_run_factory import DryRunFactoryfrom pipelex.cogt.exceptions import ModelChoiceNotFoundErrorfrom pipelex.cogt.model_backends.model_type import ModelTypefrom pipelex.cogt.models.model_deck_check import check_search_choice_with_deck-from pipelex.cogt.search.search_depth import SearchDepthfrom pipelex.cogt.search.search_setting import SearchModelChoice, SearchSetting-from pipelex.cogt.search.search_worker_factory import get_search_worker+from pipelex.cogt.search.search_worker_factory import SearchWorkerFactoryfrom pipelex.cogt.templating.template_blueprint import TemplateBlueprintfrom pipelex.cogt.templating.template_rendering import render_templatefrom pipelex.core.memory.working_memory import WorkingMemory@@ -35,7 +34,6 @@ class PipeSearch(PipeOperator[PipeSearchOutput]):type: Literal["PipeSearch"] = "PipeSearch"search_choice: SearchModelChoice | Noneprompt_blueprint: TemplateBlueprint- depth_override: SearchDepth | None = Noneinclude_images_override: bool | None = Nonemax_results_override: int | None = Nonefrom_date: str | None = None@@ -105,15 +103,13 @@ class PipeSearch(PipeOperator[PipeSearchOutput]):search_setting = search_setting.model_copy(update={"model": resolved_model_handle})# 4. Apply pipe-level overrides- if self.depth_override is not None:- search_setting = search_setting.model_copy(update={"depth": self.depth_override})if self.include_images_override is not None:search_setting = search_setting.model_copy(update={"include_images": self.include_images_override})if self.max_results_override is not None:search_setting = search_setting.model_copy(update={"max_results": self.max_results_override})# 5. Get search worker from factory- worker = get_search_worker(model_handle=search_setting.model)+ worker = SearchWorkerFactory.make_search_worker(inference_model=inference_model)# 6. Execute search based on output typecontent: StuffContent@@ -121,6 +117,7 @@ class PipeSearch(PipeOperator[PipeSearchOutput]):content = await worker.search_sourced_answer(query=query_text,search_setting=search_setting,+ job_metadata=job_metadata,include_domains=self.include_domains,exclude_domains=self.exclude_domains,from_date=self.from_date,@@ -132,6 +129,7 @@ class PipeSearch(PipeOperator[PipeSearchOutput]):query=query_text,search_setting=search_setting,output_schema=output_structure_class,+ job_metadata=job_metadata,include_domains=self.include_domains,exclude_domains=self.exclude_domains,from_date=self.from_date,diff --git a/pipelex/pipe_operators/search/pipe_search_blueprint.py b/pipelex/pipe_operators/search/pipe_search_blueprint.pyindex f38635e34..80cfae88d 100644--- a/pipelex/pipe_operators/search/pipe_search_blueprint.py+++ b/pipelex/pipe_operators/search/pipe_search_blueprint.py@@ -2,7 +2,6 @@ from typing import Literalfrom typing_extensions import override-from pipelex.cogt.search.search_depth import SearchDepthfrom pipelex.cogt.search.search_setting import SearchModelChoicefrom pipelex.cogt.templating.template_category import TemplateCategoryfrom pipelex.cogt.templating.template_preprocessor import preprocess_template@@ -18,7 +17,6 @@ class PipeSearchBlueprint(PipeBlueprint):pipe_category: Literal["PipeOperator"] = "PipeOperator"prompt: strmodel: SearchModelChoice | None = None- depth: SearchDepth | None = Noneinclude_images: bool | None = Nonemax_results: int | None = Nonefrom_date: str | None = Nonediff --git a/pipelex/pipe_operators/search/pipe_search_factory.py b/pipelex/pipe_operators/search/pipe_search_factory.pyindex c1428c402..18f262ff4 100644--- a/pipelex/pipe_operators/search/pipe_search_factory.py+++ b/pipelex/pipe_operators/search/pipe_search_factory.py@@ -50,7 +50,6 @@ class PipeSearchFactory(PipeFactoryProtocol[PipeSearchBlueprint, PipeSearch]):inputs=inputs,search_choice=blueprint.model,prompt_blueprint=prompt_blueprint,- depth_override=blueprint.depth,include_images_override=blueprint.include_images,max_results_override=blueprint.max_results,from_date=blueprint.from_date,diff --git a/pipelex/pipelex.toml b/pipelex/pipelex.tomlindex f15d4c47f..5fd13cb23 100644--- a/pipelex/pipelex.toml+++ b/pipelex/pipelex.toml@@ -74,8 +74,8 @@ image-text-extractor = "@default-extract-image"full-document-extractor = "@default-extract-document"[pipelex.builder_config.talent_preset_mappings.search]-web-search = "$linkup-standard"-web-search-deep = "$linkup-deep"+web-search = "$standard"+web-search-deep = "$deep"[pipelex.feature_config]# WIP/Experimental feature flagsdiff --git a/pipelex/pipeline/job_metadata.py b/pipelex/pipeline/job_metadata.pyindex 9d03b178b..7631ae5cc 100644--- a/pipelex/pipeline/job_metadata.py+++ b/pipelex/pipeline/job_metadata.py@@ -14,6 +14,8 @@ class JobCategory(StrEnum):IMG_GEN_JOB = "img_gen_job"JINJA2_JOB = "jinja2_job"EXTRACT_JOB = "extract_job"+ SEARCH_JOB = "search_job"+ FETCH_JOB = "fetch_job"class UnitJobId(StrEnum):@@ -21,18 +23,23 @@ class UnitJobId(StrEnum):LLM_GEN_OBJECT = "llm_gen_object"IMG_GEN_TEXT_TO_IMAGE = "img_gen_text_to_image"EXTRACT_PAGES = "extract_pages"+ SEARCH_SOURCED_ANSWER = "search_sourced_answer"+ SEARCH_STRUCTURED = "search_structured"+ FETCH_URL = "fetch_url"@propertydef model_kind(self) -> str:match self:- case UnitJobId.LLM_GEN_TEXT:- return "LLM"- case UnitJobId.LLM_GEN_OBJECT:+ case UnitJobId.LLM_GEN_TEXT | UnitJobId.LLM_GEN_OBJECT:return "LLM"case UnitJobId.IMG_GEN_TEXT_TO_IMAGE:return "ImgGen"case UnitJobId.EXTRACT_PAGES:return "Extract"+ case UnitJobId.SEARCH_SOURCED_ANSWER | UnitJobId.SEARCH_STRUCTURED:+ return "Search"+ case UnitJobId.FETCH_URL:+ return "Fetch"class JobMetadata(BaseModel):diff --git a/pipelex/plugins/gateway/gateway_exceptions.py b/pipelex/plugins/gateway/gateway_exceptions.pyindex 35eaac4b0..3228bf203 100644--- a/pipelex/plugins/gateway/gateway_exceptions.py+++ b/pipelex/plugins/gateway/gateway_exceptions.py@@ -19,3 +19,7 @@ class GatewayDeckError(GatewayError):class GatewayExtractResponseError(GatewayError):pass+++class GatewaySearchResponseError(GatewayError):+ passdiff --git a/pipelex/plugins/gateway/gateway_fetch_worker.py b/pipelex/plugins/gateway/gateway_fetch_worker.pynew file mode 100644index 000000000..a79b1f19b--- /dev/null+++ b/pipelex/plugins/gateway/gateway_fetch_worker.py@@ -0,0 +1,179 @@+import json+from typing import Any, cast++from portkey_ai import AsyncPortkey+from portkey_ai.api_resources import exceptions as portkey_exceptions+from portkey_ai.api_resources.utils import GenericResponse+from tenacity import AsyncRetrying, RetryCallState, retry_if_exception, stop_after_attempt, wait_random_exponential+from typing_extensions import override++from pipelex import log+from pipelex.cogt.exceptions import SdkTypeError+from pipelex.cogt.model_backends.model_spec import InferenceModelSpec+from pipelex.cogt.search.fetch_job import FetchJob+from pipelex.cogt.search.fetch_worker_abstract import FetchWorkerAbstract+from pipelex.cogt.search.search_job_factory import FetchJobFactory+from pipelex.cogt.usage.token_category import NbTokensByCategoryDict, TokenCategory+from pipelex.config import get_config+from pipelex.core.stuffs.image_content import ImageContent+from pipelex.core.stuffs.text_and_images_content import TextAndImagesContent+from pipelex.core.stuffs.text_content import TextContent+from pipelex.pipeline.job_metadata import JobMetadata, UnitJobId+from pipelex.plugins.gateway.gateway_deck import GatewayDeck+from pipelex.plugins.gateway.gateway_exceptions import GatewaySearchResponseError+from pipelex.plugins.gateway.gateway_factory import GatewayFactory+from pipelex.plugins.gateway.gateway_search_schemas import GatewayFetchRequestParams+from pipelex.reporting.reporting_protocol import ReportingProtocol+++class GatewayFetchWorker(FetchWorkerAbstract):+ """Fetch worker that routes through Portkey to the pipelex-relay LinkUp fetch endpoint."""++ def __init__(+ self,+ sdk_instance: Any,+ inference_model: InferenceModelSpec,+ reporting_delegate: ReportingProtocol | None = None,+ ):+ super().__init__(reporting_delegate=reporting_delegate)++ if not isinstance(sdk_instance, AsyncPortkey):+ msg = f"Provided sdk_instance for {self.__class__.__name__} is not of type AsyncPortkey: it's a '{type(sdk_instance)}'"+ raise SdkTypeError(msg)++ self.portkey_client: AsyncPortkey = sdk_instance+ self.inference_model = inference_model+ self._tenacity_config = get_config().cogt.tenacity_config++ def _make_retryer(self) -> AsyncRetrying:+ """Create a fresh AsyncRetrying instance for each call."""+ return AsyncRetrying(+ retry=retry_if_exception(self._is_retryable_portkey_error),+ before_sleep=self._log_retry,+ wait=wait_random_exponential(+ multiplier=self._tenacity_config.wait_multiplier,+ max=self._tenacity_config.wait_max,+ exp_base=self._tenacity_config.wait_exp_base,+ ),+ reraise=True,+ stop=stop_after_attempt(self._tenacity_config.max_retries),+ )++ @override+ async def fetch_url(+ self,+ url: str,+ job_metadata: JobMetadata,+ include_raw_html: bool | None = None,+ render_js: bool | None = None,+ extract_images: bool | None = None,+ timeout: float | None = None, # noqa: ASYNC109+ ) -> TextAndImagesContent:+ job_metadata.unit_job_id = UnitJobId.FETCH_URL+ fetch_job = FetchJobFactory.make_fetch_job(job_metadata=job_metadata)+ fetch_job.fetch_job_before_start(inference_model=self.inference_model)++ params = GatewayFetchRequestParams(+ url=url,+ include_raw_html=include_raw_html,+ render_js=render_js,+ extract_images=extract_images,+ timeout=timeout,+ )++ config_id = GatewayDeck.get_config_id(headers=self.inference_model.extra_headers or {})+ log.dev(f"Fetch via gateway config '{config_id}'")++ messages: list[dict[str, str]] = [{"role": "user", "content": params.model_dump_json()}]++ attempt_number = 0+ response: GenericResponse | None = None+ retryer = self._make_retryer()+ try:+ async for attempt in retryer:+ with attempt:+ attempt_number += 1+ response = await self.portkey_client.with_options(config=config_id).post( # pyright: ignore[reportUnknownMemberType, reportUnknownVariableType]+ "/chat/completions",+ model="linkup/fetch",+ messages=messages,+ )+ except portkey_exceptions.APIError as exc:+ error_summary = GatewayFactory.make_error_summary_from_portkey_error(exc)+ msg = f"Fetch service error after {attempt_number} attempt(s): {error_summary}"+ raise GatewaySearchResponseError(msg) from exc++ if response is None:+ msg = f"Could not get a fetch response via Portkey after {attempt_number} attempts"+ raise GatewaySearchResponseError(msg)++ if not isinstance(response, GenericResponse):+ msg = "Response is not of type GenericResponse"+ raise TypeError(msg)++ self._extract_usage(response=response, fetch_job=fetch_job)+ fetch_job.fetch_job_after_complete()+ if self.reporting_delegate:+ self.reporting_delegate.report_inference_job(inference_job=fetch_job)++ # Extract content from response — use dict access (GenericResponse uses extra="allow")+ try:+ choice: dict[str, Any] = response.choices[0] # type: ignore[attr-defined] # pyright: ignore[reportAttributeAccessIssue, reportUnknownMemberType]+ raw_content = cast("object", choice["message"]["content"])+ except (KeyError, IndexError, TypeError) as exc:+ msg = "Could not extract content from gateway fetch response"+ raise GatewaySearchResponseError(msg) from exc++ if not isinstance(raw_content, str):+ msg = f"Expected string content in fetch response, got {type(raw_content)}"+ raise GatewaySearchResponseError(msg)+ content_str: str = raw_content++ result_dict: dict[str, Any] = json.loads(content_str)++ text = TextContent(text=result_dict["markdown"]) if result_dict.get("markdown") else None++ images: list[ImageContent] | None = None+ if result_dict.get("images") is not None:+ images = [+ ImageContent(+ url=image["url"],+ caption=image.get("alt"),+ )+ for image in result_dict["images"]+ ]++ return TextAndImagesContent(+ text=text,+ images=images or None,+ raw_html=result_dict.get("raw_html"),+ )++ def _extract_usage(self, response: GenericResponse, fetch_job: FetchJob) -> None:+ """Extract token usage from the GenericResponse and populate the fetch job report."""+ response_dict: dict[str, Any] = response.model_dump(serialize_as_any=True)+ fetch_tokens_usage = fetch_job.job_report.fetch_tokens_usage+ if (usage_dict := response_dict.get("usage")) and fetch_tokens_usage:+ nb_tokens: NbTokensByCategoryDict = {}+ if input_tokens := usage_dict.get("prompt_tokens") or usage_dict.get("input_tokens"):+ nb_tokens[TokenCategory.INPUT] = input_tokens+ if output_tokens := usage_dict.get("completion_tokens") or usage_dict.get("output_tokens"):+ nb_tokens[TokenCategory.OUTPUT] = output_tokens+ fetch_tokens_usage.nb_tokens_by_category = nb_tokens++ def _is_retryable_portkey_error(self, exc: BaseException) -> bool:+ if isinstance(exc, portkey_exceptions.NotFoundError):+ msg = str(exc).lower()+ return "specified deployment could not be found" in msg+ return False++ def _log_retry(self, retry_state: RetryCallState) -> None:+ """Called before sleeping between retries."""+ if not retry_state.outcome:+ log.error("Tenacity retry state outcome is None")+ return+ exc = retry_state.outcome.exception()+ attempt = retry_state.attempt_number+ wait_duration = retry_state.next_action.sleep if retry_state.next_action else 0.0+ log.dev(f"{self.__class__.__name__} retry #{attempt} for fetch due to '{type(exc).__name__}'.")+ log.verbose(f"Wait duration before next attempt: {wait_duration:.4f}s")diff --git a/pipelex/plugins/gateway/gateway_search_schemas.py b/pipelex/plugins/gateway/gateway_search_schemas.pynew file mode 100644index 000000000..adec04b8c--- /dev/null+++ b/pipelex/plugins/gateway/gateway_search_schemas.py@@ -0,0 +1,28 @@+from pydantic import BaseModel, Field++from pipelex.cogt.search.search_depth import SearchDepth+++class GatewaySearchRequestParams(BaseModel):+ """Parameters for a web search request sent to the relay."""++ query: str = Field(description="The search query text")+ depth: SearchDepth = Field(default=SearchDepth.STANDARD, strict=False, description="Search depth: 'standard' or 'deep'")+ include_images: bool = Field(default=False, description="Whether to include images in results")+ include_inline_citations: bool = Field(default=True, description="Whether to include inline citations")+ max_results: int | None = Field(default=None, description="Maximum number of results to return")+ include_domains: list[str] | None = Field(default=None, description="Restrict search to these domains")+ exclude_domains: list[str] | None = Field(default=None, description="Exclude these domains from search")+ from_date: str | None = Field(default=None, description="Start date filter (YYYY-MM-DD)")+ to_date: str | None = Field(default=None, description="End date filter (YYYY-MM-DD)")+ output_schema: dict[str, object] | None = Field(default=None, description="JSON Schema for structured search output")+++class GatewayFetchRequestParams(BaseModel):+ """Parameters for a web page fetch request sent to the relay."""++ url: str = Field(description="The URL to fetch")+ include_raw_html: bool | None = Field(default=None, description="Whether to include raw HTML in response")+ render_js: bool | None = Field(default=None, description="Whether to render JavaScript before fetching")+ extract_images: bool | None = Field(default=None, description="Whether to extract images from the page")+ timeout: float | None = Field(default=None, description="Request timeout in seconds")diff --git a/pipelex/plugins/gateway/gateway_search_worker.py b/pipelex/plugins/gateway/gateway_search_worker.pynew file mode 100644index 000000000..e3399ef43--- /dev/null+++ b/pipelex/plugins/gateway/gateway_search_worker.py@@ -0,0 +1,253 @@+import json+from typing import Any, cast++from portkey_ai import AsyncPortkey+from portkey_ai.api_resources import exceptions as portkey_exceptions+from portkey_ai.api_resources.utils import GenericResponse+from tenacity import AsyncRetrying, RetryCallState, retry_if_exception, stop_after_attempt, wait_random_exponential+from typing_extensions import override++from pipelex import log+from pipelex.cogt.exceptions import SdkTypeError+from pipelex.cogt.model_backends.model_spec import InferenceModelSpec+from pipelex.cogt.search.search_depth import SearchDepth+from pipelex.cogt.search.search_job import SearchJob+from pipelex.cogt.search.search_job_factory import SearchJobFactory+from pipelex.cogt.search.search_setting import SearchSetting+from pipelex.cogt.search.search_worker_abstract import SearchWorkerAbstract+from pipelex.cogt.usage.token_category import NbTokensByCategoryDict, TokenCategory+from pipelex.config import get_config+from pipelex.core.stuffs.search_result_content import SearchResultContent, SearchSourceContent+from pipelex.pipeline.job_metadata import JobMetadata, UnitJobId+from pipelex.plugins.gateway.gateway_deck import GatewayDeck+from pipelex.plugins.gateway.gateway_exceptions import GatewaySearchResponseError+from pipelex.plugins.gateway.gateway_factory import GatewayFactory+from pipelex.plugins.gateway.gateway_search_schemas import GatewaySearchRequestParams+from pipelex.reporting.reporting_protocol import ReportingProtocol+++class GatewaySearchWorker(SearchWorkerAbstract):+ """Search worker that routes through Portkey to the pipelex-relay LinkUp endpoints."""++ def __init__(+ self,+ sdk_instance: Any,+ inference_model: InferenceModelSpec,+ reporting_delegate: ReportingProtocol | None = None,+ ):+ super().__init__(reporting_delegate=reporting_delegate)++ if not isinstance(sdk_instance, AsyncPortkey):+ msg = f"Provided sdk_instance for {self.__class__.__name__} is not of type AsyncPortkey: it's a '{type(sdk_instance)}'"+ raise SdkTypeError(msg)++ self.portkey_client: AsyncPortkey = sdk_instance+ self.inference_model = inference_model+ self._tenacity_config = get_config().cogt.tenacity_config++ def _make_retryer(self) -> AsyncRetrying:+ """Create a fresh AsyncRetrying instance for each call."""+ return AsyncRetrying(+ retry=retry_if_exception(self._is_retryable_portkey_error),+ before_sleep=self._log_retry,+ wait=wait_random_exponential(+ multiplier=self._tenacity_config.wait_multiplier,+ max=self._tenacity_config.wait_max,+ exp_base=self._tenacity_config.wait_exp_base,+ ),+ reraise=True,+ stop=stop_after_attempt(self._tenacity_config.max_retries),+ )++ @override+ async def search_sourced_answer(+ self,+ query: str,+ search_setting: SearchSetting,+ job_metadata: JobMetadata,+ include_domains: list[str] | None = None,+ exclude_domains: list[str] | None = None,+ from_date: str | None = None,+ to_date: str | None = None,+ ) -> SearchResultContent:+ job_metadata.unit_job_id = UnitJobId.SEARCH_SOURCED_ANSWER+ search_job = SearchJobFactory.make_search_job(job_metadata=job_metadata)+ search_job.search_job_before_start(inference_model=self.inference_model)++ params = GatewaySearchRequestParams(+ query=query,+ depth=SearchDepth(self.inference_model.model_id),+ include_images=search_setting.include_images,+ include_inline_citations=search_setting.include_inline_citations,+ max_results=search_setting.max_results,+ include_domains=include_domains,+ exclude_domains=exclude_domains,+ from_date=from_date,+ to_date=to_date,+ )++ response = await self._call_relay(+ model=self.inference_model.model_id,+ content=params.model_dump_json(),+ )++ self._extract_usage(response=response, search_job=search_job)+ search_job.search_job_after_complete()+ if self.reporting_delegate:+ self.reporting_delegate.report_inference_job(inference_job=search_job)++ content_str = self._extract_content(response)+ result_dict: dict[str, Any] = json.loads(content_str)++ sources = [+ SearchSourceContent(+ name=source["name"],+ url=source["url"],+ snippet=source["snippet"],+ )+ for source in result_dict.get("sources", [])+ ]++ return SearchResultContent(+ answer=result_dict["answer"],+ sources=sources,+ )++ @override+ async def search_structured(+ self,+ query: str,+ search_setting: SearchSetting,+ output_schema: type,+ job_metadata: JobMetadata,+ include_domains: list[str] | None = None,+ exclude_domains: list[str] | None = None,+ from_date: str | None = None,+ to_date: str | None = None,+ ) -> dict[str, Any]:+ job_metadata.unit_job_id = UnitJobId.SEARCH_STRUCTURED+ search_job = SearchJobFactory.make_search_job(job_metadata=job_metadata)+ search_job.search_job_before_start(inference_model=self.inference_model)++ # Convert Pydantic model class to JSON Schema dict for the relay+ schema_dict: dict[str, Any]+ if hasattr(output_schema, "model_json_schema"):+ schema_dict = cast("dict[str, Any]", output_schema.model_json_schema()) # pyright: ignore[reportUnknownMemberType]+ else:+ msg = f"output_schema must be a Pydantic model class with model_json_schema(), got {output_schema}"+ raise SdkTypeError(msg)++ params = GatewaySearchRequestParams(+ query=query,+ depth=SearchDepth(self.inference_model.model_id),+ include_images=search_setting.include_images,+ include_inline_citations=search_setting.include_inline_citations,+ max_results=search_setting.max_results,+ include_domains=include_domains,+ exclude_domains=exclude_domains,+ from_date=from_date,+ to_date=to_date,+ output_schema=schema_dict,+ )++ response = await self._call_relay(+ model=self.inference_model.model_id,+ content=params.model_dump_json(),+ )++ self._extract_usage(response=response, search_job=search_job)+ search_job.search_job_after_complete()+ if self.reporting_delegate:+ self.reporting_delegate.report_inference_job(inference_job=search_job)++ content_str = self._extract_content(response)+ result: dict[str, Any] = json.loads(content_str)+ return result++ def _extract_usage(self, response: GenericResponse, search_job: SearchJob) -> None:+ """Extract token usage from the GenericResponse and populate the search job report."""+ response_dict: dict[str, Any] = response.model_dump(serialize_as_any=True)+ search_tokens_usage = search_job.job_report.search_tokens_usage+ if (usage_dict := response_dict.get("usage")) and search_tokens_usage:+ nb_tokens: NbTokensByCategoryDict = {}+ if input_tokens := usage_dict.get("prompt_tokens") or usage_dict.get("input_tokens"):+ nb_tokens[TokenCategory.INPUT] = input_tokens+ if output_tokens := usage_dict.get("completion_tokens") or usage_dict.get("output_tokens"):+ nb_tokens[TokenCategory.OUTPUT] = output_tokens+ search_tokens_usage.nb_tokens_by_category = nb_tokens++ async def _call_relay(self, model: str, content: str) -> GenericResponse:+ """Send a request through Portkey to the relay.++ Args:+ model: The relay model identifier (e.g., "linkup-sourced-answer")+ content: JSON-encoded request parameters++ Returns:+ The Portkey GenericResponse+ """+ config_id = GatewayDeck.get_config_id(headers=self.inference_model.extra_headers or {})+ log.dev(f"Search via gateway config '{config_id}' with model '{model}'")++ messages: list[dict[str, str]] = [{"role": "user", "content": content}]++ attempt_number = 0+ response: GenericResponse | None = None+ retryer = self._make_retryer()+ try:+ async for attempt in retryer:+ with attempt:+ attempt_number += 1+ response = await self.portkey_client.with_options(config=config_id).post( # pyright: ignore[reportUnknownMemberType, reportUnknownVariableType]+ "/chat/completions",+ model=model,+ messages=messages,+ )+ except portkey_exceptions.APIError as exc:+ error_summary = GatewayFactory.make_error_summary_from_portkey_error(exc)+ msg = f"Search service error for model '{model}' after {attempt_number} attempt(s): {error_summary}"+ raise GatewaySearchResponseError(msg) from exc++ if response is None:+ msg = f"Could not get a response for model '{model}' via Portkey after {attempt_number} attempts"+ raise GatewaySearchResponseError(msg)++ if not isinstance(response, GenericResponse):+ msg = "Response is not of type GenericResponse"+ raise TypeError(msg)++ return response++ def _extract_content(self, response: GenericResponse) -> str:+ """Extract the content string from a GenericResponse.++ GenericResponse uses Pydantic's extra="allow", so `choices` is a raw+ list[dict] rather than a list of typed objects — use dict access.+ """+ try:+ choice: dict[str, Any] = response.choices[0] # type: ignore[attr-defined] # pyright: ignore[reportAttributeAccessIssue, reportUnknownMemberType]+ content = cast("object", choice["message"]["content"])+ if not isinstance(content, str):+ msg = f"Expected string content in response, got {type(content)}"+ raise GatewaySearchResponseError(msg)+ return content+ except (KeyError, IndexError, TypeError) as exc:+ msg = "Could not extract content from gateway search response"+ raise GatewaySearchResponseError(msg) from exc++ def _is_retryable_portkey_error(self, exc: BaseException) -> bool:+ if isinstance(exc, portkey_exceptions.NotFoundError):+ msg = str(exc).lower()+ return "specified deployment could not be found" in msg+ return False++ def _log_retry(self, retry_state: RetryCallState) -> None:+ """Called before sleeping between retries."""+ if not retry_state.outcome:+ log.error("Tenacity retry state outcome is None")+ return+ exc = retry_state.outcome.exception()+ attempt = retry_state.attempt_number+ wait_duration = retry_state.next_action.sleep if retry_state.next_action else 0.0+ log.dev(f"{self.__class__.__name__} retry #{attempt} for search due to '{type(exc).__name__}'.")+ log.verbose(f"Wait duration before next attempt: {wait_duration:.4f}s")diff --git a/pipelex/plugins/linkup/linkup_search_worker.py b/pipelex/plugins/linkup/linkup_search_worker.pydeleted file mode 100644index ac038d594..000000000--- a/pipelex/plugins/linkup/linkup_search_worker.py+++ /dev/null@@ -1,95 +0,0 @@-import asyncio-from datetime import date-from typing import Any--from linkup import LinkupClient, LinkupSourcedAnswer-from typing_extensions import override--from pipelex.cogt.search.search_setting import SearchSetting-from pipelex.cogt.search.search_worker_abstract import SearchWorkerAbstract-from pipelex.core.stuffs.search_result_content import SearchResultContent, SearchSourceContent-from pipelex.hub import get_secrets_provider---class LinkupSearchWorker(SearchWorkerAbstract):- def __init__(self) -> None:- api_key = get_secrets_provider().get_secret(secret_id="LINKUP_API_KEY")- self._client = LinkupClient(api_key=api_key)-- def _parse_date(self, date_str: str | None) -> date | None:- if date_str is None:- return None- return date.fromisoformat(date_str)-- @override- async def search_sourced_answer(- self,- query: str,- search_setting: SearchSetting,- include_domains: list[str] | None = None,- exclude_domains: list[str] | None = None,- from_date: str | None = None,- to_date: str | None = None,- ) -> SearchResultContent:- depth_value = search_setting.depth- response: LinkupSourcedAnswer = await asyncio.to_thread(- self._client.search,- query=query,- depth=depth_value, # type: ignore[arg-type]- output_type="sourcedAnswer",- include_images=search_setting.include_images,- include_inline_citations=search_setting.include_inline_citations,- max_results=search_setting.max_results,- include_domains=include_domains,- exclude_domains=exclude_domains,- from_date=self._parse_date(from_date),- to_date=self._parse_date(to_date),- )-- sources: list[SearchSourceContent] = []- for source in response.sources:- sources.append(- SearchSourceContent(- name=source.name,- url=source.url,- snippet=source.snippet,- )- )-- return SearchResultContent(- answer=response.answer,- sources=sources,- )-- @override- async def search_structured(- self,- query: str,- search_setting: SearchSetting,- output_schema: type,- include_domains: list[str] | None = None,- exclude_domains: list[str] | None = None,- from_date: str | None = None,- to_date: str | None = None,- ) -> dict[str, Any]:- depth_value = search_setting.depth- response = await asyncio.to_thread(- self._client.search,- query=query,- depth=depth_value, # type: ignore[arg-type]- output_type="structured",- structured_output_schema=output_schema,- include_images=search_setting.include_images,- max_results=search_setting.max_results,- include_domains=include_domains,- exclude_domains=exclude_domains,- from_date=self._parse_date(from_date),- to_date=self._parse_date(to_date),- include_sources=True,- )-- # If response is a Pydantic model, convert to dict- if hasattr(response, "model_dump"):- result: dict[str, Any] = response.model_dump()- return result- return dict(response) # type: ignore[arg-type]diff --git a/pipelex/plugins/linkup/linkup_worker.py b/pipelex/plugins/linkup/linkup_worker.pynew file mode 100644index 000000000..8afdd80ea--- /dev/null+++ b/pipelex/plugins/linkup/linkup_worker.py@@ -0,0 +1,180 @@+from datetime import date+from typing import Any++from linkup import LinkupClient, LinkupFetchResponse, LinkupSourcedAnswer+from typing_extensions import override++from pipelex.cogt.model_backends.model_spec import InferenceModelSpec+from pipelex.cogt.search.fetch_worker_abstract import FetchWorkerAbstract+from pipelex.cogt.search.search_depth import SearchDepth+from pipelex.cogt.search.search_job_factory import FetchJobFactory, SearchJobFactory+from pipelex.cogt.search.search_setting import SearchSetting+from pipelex.cogt.search.search_worker_abstract import SearchWorkerAbstract+from pipelex.cogt.usage.token_category import TokenCategory+from pipelex.core.stuffs.image_content import ImageContent+from pipelex.core.stuffs.search_result_content import SearchResultContent, SearchSourceContent+from pipelex.core.stuffs.text_and_images_content import TextAndImagesContent+from pipelex.core.stuffs.text_content import TextContent+from pipelex.hub import get_secrets_provider+from pipelex.pipeline.job_metadata import JobMetadata, UnitJobId+from pipelex.reporting.reporting_protocol import ReportingProtocol+++class LinkupWorker(SearchWorkerAbstract, FetchWorkerAbstract):+ def __init__(+ self,+ inference_model: InferenceModelSpec,+ reporting_delegate: ReportingProtocol | None = None,+ ) -> None:+ SearchWorkerAbstract.__init__(self, reporting_delegate=reporting_delegate)+ FetchWorkerAbstract.__init__(self, reporting_delegate=reporting_delegate)+ self.inference_model = inference_model+ api_key = get_secrets_provider().get_secret(secret_id="LINKUP_API_KEY")+ self._linkup_client = LinkupClient(api_key=api_key)++ def _parse_date(self, date_str: str | None) -> date | None:+ if date_str is None:+ return None+ return date.fromisoformat(date_str)++ @override+ async def search_sourced_answer(+ self,+ query: str,+ search_setting: SearchSetting,+ job_metadata: JobMetadata,+ include_domains: list[str] | None = None,+ exclude_domains: list[str] | None = None,+ from_date: str | None = None,+ to_date: str | None = None,+ ) -> SearchResultContent:+ job_metadata.unit_job_id = UnitJobId.SEARCH_SOURCED_ANSWER+ search_job = SearchJobFactory.make_search_job(job_metadata=job_metadata)+ search_job.search_job_before_start(inference_model=self.inference_model)++ depth_value = SearchDepth(self.inference_model.model_id)+ response: LinkupSourcedAnswer = await self._linkup_client.async_search(+ query=query,+ depth=depth_value, # type: ignore[arg-type] # pyright: ignore[reportArgumentType]+ output_type="sourcedAnswer",+ include_images=search_setting.include_images,+ include_inline_citations=search_setting.include_inline_citations,+ max_results=search_setting.max_results,+ include_domains=include_domains,+ exclude_domains=exclude_domains,+ from_date=self._parse_date(from_date),+ to_date=self._parse_date(to_date),+ )++ # Per-request cost model: costs are defined per million, so 1 request = 1_000_000+ if search_tokens_usage := search_job.job_report.search_tokens_usage:+ search_tokens_usage.nb_tokens_by_category = {TokenCategory.INPUT: 1_000_000, TokenCategory.OUTPUT: 1_000_000}+ search_job.search_job_after_complete()+ if self.reporting_delegate:+ self.reporting_delegate.report_inference_job(inference_job=search_job)++ sources: list[SearchSourceContent] = []+ for source in response.sources:+ sources.append(+ SearchSourceContent(+ name=source.name,+ url=source.url,+ snippet=source.snippet,+ )+ )++ return SearchResultContent(+ answer=response.answer,+ sources=sources,+ )++ @override+ async def search_structured(+ self,+ query: str,+ search_setting: SearchSetting,+ output_schema: type,+ job_metadata: JobMetadata,+ include_domains: list[str] | None = None,+ exclude_domains: list[str] | None = None,+ from_date: str | None = None,+ to_date: str | None = None,+ ) -> dict[str, Any]:+ job_metadata.unit_job_id = UnitJobId.SEARCH_STRUCTURED+ search_job = SearchJobFactory.make_search_job(job_metadata=job_metadata)+ search_job.search_job_before_start(inference_model=self.inference_model)++ depth_value = SearchDepth(self.inference_model.model_id)+ response = await self._linkup_client.async_search(+ query=query,+ depth=depth_value, # type: ignore[arg-type] # pyright: ignore[reportArgumentType]+ output_type="structured",+ structured_output_schema=output_schema,+ include_images=search_setting.include_images,+ max_results=search_setting.max_results,+ include_domains=include_domains,+ exclude_domains=exclude_domains,+ from_date=self._parse_date(from_date),+ to_date=self._parse_date(to_date),+ include_sources=True,+ )++ # Per-request cost model: costs are defined per million, so 1 request = 1_000_000+ if search_tokens_usage := search_job.job_report.search_tokens_usage:+ search_tokens_usage.nb_tokens_by_category = {TokenCategory.INPUT: 1_000_000, TokenCategory.OUTPUT: 1_000_000}+ search_job.search_job_after_complete()+ if self.reporting_delegate:+ self.reporting_delegate.report_inference_job(inference_job=search_job)++ # If response is a Pydantic model, convert to dict+ if hasattr(response, "model_dump"):+ result: dict[str, Any] = response.model_dump()+ return result+ return dict(response) # type: ignore[arg-type]++ @override+ async def fetch_url(+ self,+ url: str,+ job_metadata: JobMetadata,+ include_raw_html: bool | None = None,+ render_js: bool | None = None,+ extract_images: bool | None = None,+ timeout: float | None = None, # noqa: ASYNC109+ ) -> TextAndImagesContent:+ job_metadata.unit_job_id = UnitJobId.FETCH_URL+ fetch_job = FetchJobFactory.make_fetch_job(job_metadata=job_metadata)+ fetch_job.fetch_job_before_start(inference_model=self.inference_model)++ response: LinkupFetchResponse = await self._linkup_client.async_fetch(+ url=url,+ include_raw_html=include_raw_html,+ render_js=render_js,+ extract_images=extract_images,+ timeout=timeout,+ )++ # Per-request cost model: costs are defined per million, so 1 request = 1_000_000+ if fetch_tokens_usage := fetch_job.job_report.fetch_tokens_usage:+ fetch_tokens_usage.nb_tokens_by_category = {TokenCategory.INPUT: 1_000_000, TokenCategory.OUTPUT: 1_000_000}+ fetch_job.fetch_job_after_complete()+ if self.reporting_delegate:+ self.reporting_delegate.report_inference_job(inference_job=fetch_job)++ text = TextContent(text=response.markdown) if response.markdown else None++ images: list[ImageContent] | None = None+ if response.images is not None:+ images = [+ ImageContent(+ url=image.url,+ caption=image.alt or None,+ )+ for image in response.images+ ]++ return TextAndImagesContent(+ text=text,+ images=images or None,+ raw_html=response.raw_html,+ )diff --git a/pipelex/reporting/reporting_manager.py b/pipelex/reporting/reporting_manager.pyindex 44addf246..2512dc127 100644--- a/pipelex/reporting/reporting_manager.py+++ b/pipelex/reporting/reporting_manager.py@@ -12,6 +12,10 @@ from pipelex.cogt.img_gen.img_gen_report import ImgGenTokensUsagefrom pipelex.cogt.inference.inference_job_abstract import InferenceJobAbstractfrom pipelex.cogt.llm.llm_job import LLMJobfrom pipelex.cogt.llm.llm_report import LLMTokensUsage+from pipelex.cogt.search.fetch_job import FetchJob+from pipelex.cogt.search.fetch_report import FetchTokensUsage+from pipelex.cogt.search.search_job import SearchJob+from pipelex.cogt.search.search_report import SearchTokensUsagefrom pipelex.cogt.usage.cost_registry import CostRegistryfrom pipelex.config import get_configfrom pipelex.pipeline.pipeline_models import SpecialPipelineId@@ -22,7 +26,7 @@ from pipelex.tools.typing.pydantic_utils import empty_list_factory_ofif TYPE_CHECKING:from pathlib import Path-TokensUsage = LLMTokensUsage | ImgGenTokensUsage | ExtractTokensUsage+TokensUsage = LLMTokensUsage | ImgGenTokensUsage | ExtractTokensUsage | SearchTokensUsage | FetchTokensUsageUsageRegistryRoot = list[TokensUsage]@@ -106,6 +110,34 @@ class ReportingManager(ReportingProtocol):extract_token_cost_report = CostRegistry.complete_cost_report(tokens_usage=extract_tokens_usage)log.verbose(extract_token_cost_report, title="Token Cost report")+ def _report_search_job(self, search_job: SearchJob):+ search_tokens_usage = search_job.job_report.search_tokens_usage++ if not search_tokens_usage:+ log.warning("Search job has no search_tokens_usage")+ return++ pipeline_run_id = search_job.job_metadata.pipeline_run_id+ self._get_registry(pipeline_run_id).add_tokens_usage(search_tokens_usage)++ if self._reporting_config.is_log_costs_to_console:+ search_token_cost_report = CostRegistry.complete_cost_report(tokens_usage=search_tokens_usage)+ log.verbose(search_token_cost_report, title="Token Cost report")++ def _report_fetch_job(self, fetch_job: FetchJob):+ fetch_tokens_usage = fetch_job.job_report.fetch_tokens_usage++ if not fetch_tokens_usage:+ log.warning("Fetch job has no fetch_tokens_usage")+ return++ pipeline_run_id = fetch_job.job_metadata.pipeline_run_id+ self._get_registry(pipeline_run_id).add_tokens_usage(fetch_tokens_usage)++ if self._reporting_config.is_log_costs_to_console:+ fetch_token_cost_report = CostRegistry.complete_cost_report(tokens_usage=fetch_tokens_usage)+ log.verbose(fetch_token_cost_report, title="Token Cost report")+############################################################# ReportingProtocol############################################################@@ -126,6 +158,10 @@ class ReportingManager(ReportingProtocol):self._report_img_gen_job(img_gen_job=inference_job)elif isinstance(inference_job, ExtractJob):self._report_extract_job(extract_job=inference_job)+ elif isinstance(inference_job, SearchJob):+ self._report_search_job(search_job=inference_job)+ elif isinstance(inference_job, FetchJob):+ self._report_fetch_job(fetch_job=inference_job)else:log.warning(f"ReportingManager does not support reporting for inference job type: {type(inference_job).__name__}")diff --git a/pipelex/system/pipelex_service/pipelex_details.py b/pipelex/system/pipelex_service/pipelex_details.pyindex 973c84f28..262e0920c 100644--- a/pipelex/system/pipelex_service/pipelex_details.py+++ b/pipelex/system/pipelex_service/pipelex_details.py@@ -2,7 +2,7 @@ from pipelex.tools.misc.hash_utils import hash_sha256class PipelexDetails:- REMOTE_CONFIG_URL = "https://pipelex-config.s3.eu-west-3.amazonaws.com/pipelex_remote_config_05.json"+ REMOTE_CONFIG_URL = "https://pipelex-config.s3.eu-west-3.amazonaws.com/pipelex_remote_config_06.json"PIPELEX_GATEWAY_API_KEY_VAR = "PIPELEX_GATEWAY_API_KEY"@classmethoddiff --git a/tests/e2e/pipelex/pipes/pipe_operators/pipe_search/pipe_search.mthds b/tests/e2e/pipelex/pipes/pipe_operators/pipe_search/pipe_search.mthdsindex 92f5744e4..832827869 100644--- a/tests/e2e/pipelex/pipes/pipe_operators/pipe_search/pipe_search.mthds+++ b/tests/e2e/pipelex/pipes/pipe_operators/pipe_search/pipe_search.mthds@@ -6,7 +6,7 @@ type = "PipeSearch"description = "Search the web for recent news"inputs = { topic = "Text" }output = "SearchResult"-model = "$linkup-standard"+model = "$standard"prompt = "What's the latest news about $topic in the last 24 hours?"[pipe.search_sourced_e2e_using_preset]@@ -14,7 +14,7 @@ type = "PipeSearch"description = "Search the web for sourced information using the standard preset"inputs = { topic = "Text" }output = "SearchResult"-model = "$linkup-standard"+model = "$standard"prompt = "What is $topic?"[pipe.search_sourced_e2e_deep]@@ -22,5 +22,5 @@ type = "PipeSearch"description = "Search the web for sourced information using the deep preset"inputs = { topic = "Text" }output = "SearchResult"-model = "$linkup-deep"+model = "$deep"prompt = "What are the main details about $topic?"diff --git a/tests/integration/pipelex/cogt/test_data.py b/tests/integration/pipelex/cogt/test_data.pyindex 6539f91a0..2c6d16001 100644--- a/tests/integration/pipelex/cogt/test_data.py+++ b/tests/integration/pipelex/cogt/test_data.py@@ -234,18 +234,27 @@ class SerDeTestLLMCases:]+class FetchTestCases:+ """Test cases for fetch integration tests."""++ FETCH_URLS: ClassVar[list[tuple[str, str]]] = [ # topic, url+ ("Wikipedia Python", "https://en.wikipedia.org/wiki/Python_(programming_language)"),+ ]++class SearchTestCases:"""Test cases for search integration tests."""SOURCED_ANSWER_QUERIES: ClassVar[list[tuple[str, str]]] = [ # topic, query- ("Middle East", "Latest events in the middle east"),+ ("Declarative languages", "What makes declarative languages different from imperative languages?"),+ # ("Middle East", "Latest events in the middle east"),# ("Capital of France", "What is the capital of France?"),# ("Python creator", "Who created the Python programming language?"),]STRUCTURED_QUERIES: ClassVar[list[tuple[str, str]]] = [ # topic, query- ("Python language", "What is the Python programming language and what are its main features?"),- ("Machine learning", "What is machine learning and its main applications?"),+ ("Middle East", "Latest events in the middle east"),+ # ("Python language", "What is the Python programming language and what are its main features?"),]diff --git a/tests/integration/pipelex/cogt/test_fetch.py b/tests/integration/pipelex/cogt/test_fetch.pynew file mode 100644index 000000000..a470235c2--- /dev/null+++ b/tests/integration/pipelex/cogt/test_fetch.py@@ -0,0 +1,64 @@+import pytest++from pipelex import pretty_print+from pipelex.cogt.model_backends.model_type import ModelType+from pipelex.cogt.search.search_worker_factory import SearchWorkerFactory+from pipelex.hub import get_model_deck, get_report_delegate+from pipelex.pipeline.job_metadata import JobMetadata+from tests.integration.pipelex.cogt.test_data import FetchTestCases+from tests.integration.pipelex.fixtures.model_combo import ModelCombo++[email protected](loop_scope="class")+class TestFetch:+ @pytest.mark.parametrize(+ ("topic", "url"),+ FetchTestCases.FETCH_URLS,+ )+ async def test_fetch_url(self, search_combo: ModelCombo, job_metadata: JobMetadata, topic: str, url: str) -> None:+ """Verify that fetch_url returns non-empty text content."""+ model_deck = get_model_deck()+ inference_model = model_deck.get_required_inference_model(model_handle=search_combo.handle, model_type=ModelType.SEARCH)+ worker = SearchWorkerFactory.make_fetch_worker(inference_model=inference_model)+ result = await worker.fetch_url(url=url, job_metadata=job_metadata)+ pretty_print(result, title=f"Fetch Result ({topic})")+ assert result.text is not None, "Expected non-empty text content"+ assert len(result.text.text) > 0, "Expected text to have content"+ assert result.raw_html is None, "Expected raw_html to be None when not requested"+ assert result.images is None, "Expected images to be None when not requested"+ get_report_delegate().generate_report()++ @pytest.mark.parametrize(+ ("topic", "url"),+ FetchTestCases.FETCH_URLS,+ )+ async def test_fetch_url_with_raw_html(self, search_combo: ModelCombo, job_metadata: JobMetadata, topic: str, url: str) -> None:+ """Verify that fetch_url returns raw HTML when requested."""+ model_deck = get_model_deck()+ inference_model = model_deck.get_required_inference_model(model_handle=search_combo.handle, model_type=ModelType.SEARCH)+ worker = SearchWorkerFactory.make_fetch_worker(inference_model=inference_model)+ result = await worker.fetch_url(url=url, job_metadata=job_metadata, include_raw_html=True)+ pretty_print(result, title=f"Fetch Result with HTML ({topic})")+ assert result.text is not None, "Expected non-empty text content"+ assert result.raw_html is not None, "Expected raw_html to be present when requested"+ assert len(result.raw_html) > 0, "Expected raw_html to have content"+ get_report_delegate().generate_report()++ @pytest.mark.parametrize(+ ("topic", "url"),+ FetchTestCases.FETCH_URLS,+ )+ async def test_fetch_url_with_images(self, search_combo: ModelCombo, job_metadata: JobMetadata, topic: str, url: str) -> None:+ """Verify that fetch_url returns images when requested."""+ model_deck = get_model_deck()+ inference_model = model_deck.get_required_inference_model(model_handle=search_combo.handle, model_type=ModelType.SEARCH)+ worker = SearchWorkerFactory.make_fetch_worker(inference_model=inference_model)+ result = await worker.fetch_url(url=url, job_metadata=job_metadata, extract_images=True)+ pretty_print(result, title=f"Fetch Result with Images ({topic})")+ assert result.text is not None, "Expected non-empty text content"+ assert result.images is not None, "Expected images to be present when requested"+ assert isinstance(result.images, list), "Expected images to be a list"+ assert len(result.images) > 0, "Expected images list to be non-empty"+ get_report_delegate().generate_report()diff --git a/tests/integration/pipelex/cogt/test_search.py b/tests/integration/pipelex/cogt/test_search.pyindex 82eedbbfb..4b1847e70 100644--- a/tests/integration/pipelex/cogt/test_search.py+++ b/tests/integration/pipelex/cogt/test_search.py@@ -2,10 +2,13 @@ import pytestfrom pydantic import BaseModelfrom pipelex import pretty_print-from pipelex.cogt.search.search_depth import SearchDepth+from pipelex.cogt.model_backends.model_type import ModelTypefrom pipelex.cogt.search.search_setting import SearchSetting-from pipelex.cogt.search.search_worker_factory import get_search_worker+from pipelex.cogt.search.search_worker_factory import SearchWorkerFactory+from pipelex.hub import get_model_deck, get_report_delegate+from pipelex.pipeline.job_metadata import JobMetadatafrom tests.integration.pipelex.cogt.test_data import SearchTestCases+from tests.integration.pipelex.fixtures.model_combo import ModelComboclass TopicSummary(BaseModel):@@ -22,16 +25,19 @@ class TestSearch:("topic", "query"),SearchTestCases.SOURCED_ANSWER_QUERIES,)- async def test_search_sourced_answer(self, topic: str, query: str) -> None:+ async def test_search_sourced_answer(self, search_combo: ModelCombo, job_metadata: JobMetadata, topic: str, query: str) -> None:"""Verify that search_sourced_answer returns a non-empty answer with sources."""- worker = get_search_worker("linkup/standard")+ model_deck = get_model_deck()+ inference_model = model_deck.get_required_inference_model(model_handle=search_combo.handle, model_type=ModelType.SEARCH)+ worker = SearchWorkerFactory.make_search_worker(inference_model=inference_model)search_setting = SearchSetting(- model="linkup/standard",- depth=SearchDepth.STANDARD,+ model=search_combo.handle,+ max_results=2,)result = await worker.search_sourced_answer(query=query,search_setting=search_setting,+ job_metadata=job_metadata,)pretty_print(result, title=f"Sourced Answer Result ({topic})")assert result.answer, "Expected a non-empty answer"@@ -39,25 +45,33 @@ class TestSearch:for source in result.sources:assert source.name, "Expected source to have a name"assert source.url, "Expected source to have a URL"+ get_report_delegate().generate_report()@pytest.mark.parametrize(("topic", "query"),SearchTestCases.STRUCTURED_QUERIES,)- async def test_search_structured(self, topic: str, query: str) -> None:+ async def test_search_structured(self, search_combo: ModelCombo, job_metadata: JobMetadata, topic: str, query: str) -> None:"""Verify that search_structured returns a dict with the expected schema keys."""- worker = get_search_worker("linkup/standard")+ model_deck = get_model_deck()+ inference_model = model_deck.get_required_inference_model(model_handle=search_combo.handle, model_type=ModelType.SEARCH)+ worker = SearchWorkerFactory.make_search_worker(inference_model=inference_model)search_setting = SearchSetting(- model="linkup/standard",- depth=SearchDepth.STANDARD,+ model=search_combo.handle,)result = await worker.search_structured(query=query,search_setting=search_setting,output_schema=TopicSummary,+ job_metadata=job_metadata,)pretty_print(result, title=f"Structured Search Result ({topic})")assert isinstance(result, dict), "Expected a dict result"- assert "title" in result, "Expected 'title' key in result"- assert "summary" in result, "Expected 'summary' key in result"- assert "key_points" in result, "Expected 'key_points' key in result"+ assert "data" in result, "Expected 'data' key in result"+ assert "sources" in result, "Expected 'sources' key in result"+ data = result["data"]+ assert "title" in data, "Expected 'title' key in data"+ assert "summary" in data, "Expected 'summary' key in data"+ assert "key_points" in data, "Expected 'key_points' key in data"+ assert len(result["sources"]) > 0, "Expected at least one source"+ get_report_delegate().generate_report()diff --git a/tests/integration/pipelex/conftest.py b/tests/integration/pipelex/conftest.pyindex fa61fbc10..9a66f22d5 100644--- a/tests/integration/pipelex/conftest.py+++ b/tests/integration/pipelex/conftest.py@@ -8,6 +8,7 @@ from .fixtures.combo_fixtures import (extract_combo,img_gen_combo,llm_combo,+ search_combo,)from .fixtures.extract_fixtures import (extract_choice_for_image,@@ -33,6 +34,7 @@ __all__ = ["llm_combo","img_gen_combo","extract_combo",+ "search_combo",# Plugin fixtures"plugin_for_openai","plugin_for_anthropic",diff --git a/tests/integration/pipelex/fixtures/combo_fixtures.py b/tests/integration/pipelex/fixtures/combo_fixtures.pyindex 986ff294d..1ab00b405 100644--- a/tests/integration/pipelex/fixtures/combo_fixtures.py+++ b/tests/integration/pipelex/fixtures/combo_fixtures.py@@ -34,6 +34,7 @@ from tests.integration.pipelex.fixtures.model_selection import (get_extract_combos,get_img_gen_combos,get_llm_combos,+ get_search_combos,)@@ -150,3 +151,18 @@ def extract_combo(request: pytest.FixtureRequest):yield combo_cleanup_routing(monkeypatch, temp_dir)++[email protected](scope="module", params=get_search_combos())+def search_combo(request: pytest.FixtureRequest):+ """Provides a valid ModelCombo(handle, backend) for search with routing configured.++ Yields:+ ModelCombo(handle, backend) for search.+ """+ combo: ModelCombo = request.param+ monkeypatch, temp_dir = _setup_routing_for_backend(combo.backend)++ yield combo++ _cleanup_routing(monkeypatch, temp_dir)diff --git a/tests/integration/pipelex/fixtures/model_selection.py b/tests/integration/pipelex/fixtures/model_selection.pyindex d5b720aba..44a96949b 100644--- a/tests/integration/pipelex/fixtures/model_selection.py+++ b/tests/integration/pipelex/fixtures/model_selection.py@@ -83,3 +83,21 @@ def get_extract_combos() -> list[ModelCombo]:)return list(EXTRACT_COMBOS)+++@cache+def get_search_combos() -> list[ModelCombo]:+ """Get the list of valid (search_model, backend) combinations.++ Returns:+ List of ModelCombo(handle, backend).++ Raises:+ FileNotFoundError: If the generated fixtures file does not exist.+ """+ _ensure_generated_fixtures_exist()+ from tests.integration.pipelex.fixtures._generated_model_sets import ( # noqa: PLC0415+ SEARCH_COMBOS, # noqa: PLC2701+ )++ return list(SEARCH_COMBOS)diff --git a/tests/unit/pipelex/cogt/models/test_model_deck.py b/tests/unit/pipelex/cogt/models/test_model_deck.pyindex 0514804b2..1449b8973 100644--- a/tests/unit/pipelex/cogt/models/test_model_deck.py+++ b/tests/unit/pipelex/cogt/models/test_model_deck.py@@ -8,7 +8,6 @@ from pipelex.cogt.llm.thinking_mode import ThinkingModefrom pipelex.cogt.model_backends.model_spec import InferenceModelSpecfrom pipelex.cogt.model_backends.model_type import ModelTypefrom pipelex.cogt.models.model_deck import ModelDeck-from pipelex.cogt.search.search_depth import SearchDepthfrom pipelex.cogt.usage.cost_category import CostCategoryfrom pipelex.system.runtime import ProblemReaction@@ -58,7 +57,6 @@ class TestModelDeckGetOptionalInferenceModel:img_gen_presets={},img_gen_choice_default="gen_image_basic",# Search-specific- search_default_depth=SearchDepth.STANDARD,search_choice_default="@default-search",model_deck_config=ModelDeckConfig(is_model_fallback_enabled=is_model_fallback_enabled, missing_presets_reaction=ProblemReaction.NONE),)@@ -336,7 +334,6 @@ class TestModelDeckPrefixedAliasReferences:img_gen_presets={},img_gen_choice_default="gen_image_basic",# Search-specific- search_default_depth=SearchDepth.STANDARD,search_choice_default="@default-search",model_deck_config=ModelDeckConfig(is_model_fallback_enabled=is_model_fallback_enabled, missing_presets_reaction=ProblemReaction.NONE),)@@ -490,7 +487,6 @@ class TestModelDeckGetLLMSettingWithPresets:img_gen_presets={},img_gen_choice_default="gen_image_basic",# Search-specific- search_default_depth=SearchDepth.STANDARD,search_choice_default="@default-search",model_deck_config=ModelDeckConfig(is_model_fallback_enabled=False, missing_presets_reaction=ProblemReaction.NONE),)diff --git a/tests/unit/pipelex/core/stuffs/page_content/test_data.py b/tests/unit/pipelex/core/stuffs/page_content/test_data.pyindex 428d11c23..851d969b0 100644--- a/tests/unit/pipelex/core/stuffs/page_content/test_data.py+++ b/tests/unit/pipelex/core/stuffs/page_content/test_data.py@@ -19,6 +19,7 @@ class TestData:"text_and_images": {"text": {"text": "Page content text"},"images": None,+ "raw_html": None,},"page_view": None,}@@ -28,6 +29,7 @@ class TestData:"text_and_images": {"text": {"text": "Page content text"},"images": None,+ "raw_html": None,},"page_view": {"url": URLs.png_example_1,@@ -42,7 +44,11 @@ class TestData:}# Expected outputs for render methods- EXPECTED_RENDERED_MARKDOWN = "# text_and_images\n\n## text: ### text: Page content text\n\n## images: None\n\n# page_view: None"- EXPECTED_RENDERED_FOR_PROMPT = "# text_and_images\n\n## text: ### text: Page content text\n\n## images: None\n\n# page_view: None"+ EXPECTED_RENDERED_MARKDOWN = (+ "# text_and_images\n\n## text: ### text: Page content text\n\n## images: None\n\n## raw_html: None\n\n# page_view: None"+ )+ EXPECTED_RENDERED_FOR_PROMPT = (+ "# text_and_images\n\n## text: ### text: Page content text\n\n## images: None\n\n## raw_html: None\n\n# page_view: None"+ )# TextAndImagesContent.rendered_html returns the text content (table format, skips None values)EXPECTED_RENDERED_HTML = "<table><tr><th>text_and_images</th><td>Page content text</td></tr></table>"diff --git a/tests/unit/pipelex/core/stuffs/text_and_images_content/test_data.py b/tests/unit/pipelex/core/stuffs/text_and_images_content/test_data.pyindex a54a44ab9..6a04c8e5f 100644--- a/tests/unit/pipelex/core/stuffs/text_and_images_content/test_data.py+++ b/tests/unit/pipelex/core/stuffs/text_and_images_content/test_data.py@@ -17,6 +17,7 @@ class TestData:EXPECTED_SMART_DUMP_TEXT_ONLY: ClassVar[dict[str, Any]] = {"text": {"text": "Hello World"},"images": None,+ "raw_html": None,}# Expected outputs for smart_dump (text and images)@@ -44,6 +45,7 @@ class TestData:"filename": None,},],+ "raw_html": None,}# Expected outputs for render methods@@ -54,5 +56,5 @@ class TestData:EXPECTED_RENDERED_HTML = "Hello World"# Empty content test cases- EXPECTED_SMART_DUMP_EMPTY: ClassVar[dict[str, Any]] = {"text": None, "images": None}+ EXPECTED_SMART_DUMP_EMPTY: ClassVar[dict[str, Any]] = {"text": None, "images": None, "raw_html": None}EXPECTED_RENDERED_PLAIN_EMPTY = ""