## Upsert Pipeline `Pipeline pipelines().upsert(PipelineUpsertParamsparams, RequestOptionsrequestOptions = RequestOptions.none())` **put** `/api/v1/pipelines` Upsert a pipeline. Updates the pipeline if one with the same name and project already exists, otherwise creates a new one. ### Parameters - `PipelineUpsertParams params` - `Optional organizationId` - `Optional projectId` - `PipelineCreate pipelineCreate` Schema for creating a pipeline. ### Returns - `class Pipeline:` Schema for a pipeline. - `String id` Unique identifier - `EmbeddingConfig embeddingConfig` - `class ManagedOpenAIEmbedding:` - `Optional component` Configuration for the Managed OpenAI embedding model. - `Optional className` - `Optional embedBatchSize` The batch size for embedding calls. - `Optional modelName` The name of the OpenAI embedding model. - `OPENAI_TEXT_EMBEDDING_3_SMALL("openai-text-embedding-3-small")` - `Optional numWorkers` The number of workers to use for async embedding calls. - `Optional type` Type of the embedding model. - `MANAGED_OPENAI_EMBEDDING("MANAGED_OPENAI_EMBEDDING")` - `class AzureOpenAIEmbeddingConfig:` - `Optional component` Configuration for the Azure OpenAI embedding model. - `Optional additionalKwargs` Additional kwargs for the OpenAI API. - `Optional apiBase` The base URL for Azure deployment. - `Optional apiKey` The OpenAI API key. - `Optional apiVersion` The version for Azure OpenAI API. - `Optional azureDeployment` The Azure deployment to use. - `Optional azureEndpoint` The Azure endpoint to use. - `Optional className` - `Optional defaultHeaders` The default headers for API requests. - `Optional dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Optional embedBatchSize` The batch size for embedding calls. - `Optional maxRetries` Maximum number of retries. - `Optional modelName` The name of the OpenAI embedding model. - `Optional numWorkers` The number of workers to use for async embedding calls. - `Optional reuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Optional timeout` Timeout for each request. - `Optional type` Type of the embedding model. - `AZURE_EMBEDDING("AZURE_EMBEDDING")` - `class CohereEmbeddingConfig:` - `Optional component` Configuration for the Cohere embedding model. - `Optional apiKey` The Cohere API key. - `Optional className` - `Optional embedBatchSize` The batch size for embedding calls. - `Optional embeddingType` Embedding type. If not provided float embedding_type is used when needed. - `Optional inputType` Model Input type. If not provided, search_document and search_query are used when needed. - `Optional modelName` The modelId of the Cohere model to use. - `Optional numWorkers` The number of workers to use for async embedding calls. - `Optional truncate` Truncation type - START/ END/ NONE - `Optional type` Type of the embedding model. - `COHERE_EMBEDDING("COHERE_EMBEDDING")` - `class GeminiEmbeddingConfig:` - `Optional component` Configuration for the Gemini embedding model. - `Optional apiBase` API base to access the model. Defaults to None. - `Optional apiKey` API key to access the model. Defaults to None. - `Optional className` - `Optional embedBatchSize` The batch size for embedding calls. - `Optional modelName` The modelId of the Gemini model to use. - `Optional numWorkers` The number of workers to use for async embedding calls. - `Optional outputDimensionality` Optional reduced dimension for output embeddings. Supported by models/text-embedding-004 and newer (e.g. gemini-embedding-001). Not supported by models/embedding-001. - `Optional taskType` The task for embedding model. - `Optional title` Title is only applicable for retrieval_document tasks, and is used to represent a document title. For other tasks, title is invalid. - `Optional transport` Transport to access the model. Defaults to None. - `Optional type` Type of the embedding model. - `GEMINI_EMBEDDING("GEMINI_EMBEDDING")` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `Optional component` Configuration for the HuggingFace Inference API embedding model. - `Optional token` Hugging Face token. Will default to the locally saved token. Pass token=False if you don’t want to send your token to the server. - `String` - `boolean` - `Optional className` - `Optional cookies` Additional cookies to send to the server. - `Optional embedBatchSize` The batch size for embedding calls. - `Optional headers` Additional headers to send to the server. By default only the authorization and user-agent headers are sent. Values in this dictionary will override the default values. - `Optional modelName` Hugging Face model name. If None, the task will be used. - `Optional numWorkers` The number of workers to use for async embedding calls. - `Optional pooling` Enum of possible pooling choices with pooling behaviors. - `CLS("cls")` - `MEAN("mean")` - `LAST("last")` - `Optional queryInstruction` Instruction to prepend during query embedding. - `Optional task` Optional task to pick Hugging Face's recommended model, used when model_name is left as default of None. - `Optional textInstruction` Instruction to prepend during text embedding. - `Optional timeout` The maximum number of seconds to wait for a response from the server. Loading a new model in Inference API can take up to several minutes. Defaults to None, meaning it will loop until the server is available. - `Optional type` Type of the embedding model. - `HUGGINGFACE_API_EMBEDDING("HUGGINGFACE_API_EMBEDDING")` - `class OpenAIEmbeddingConfig:` - `Optional component` Configuration for the OpenAI embedding model. - `Optional additionalKwargs` Additional kwargs for the OpenAI API. - `Optional apiBase` The base URL for OpenAI API. - `Optional apiKey` The OpenAI API key. - `Optional apiVersion` The version for OpenAI API. - `Optional className` - `Optional defaultHeaders` The default headers for API requests. - `Optional dimensions` The number of dimensions on the output embedding vectors. Works only with v3 embedding models. - `Optional embedBatchSize` The batch size for embedding calls. - `Optional maxRetries` Maximum number of retries. - `Optional modelName` The name of the OpenAI embedding model. - `Optional numWorkers` The number of workers to use for async embedding calls. - `Optional reuseClient` Reuse the OpenAI client between requests. When doing anything with large volumes of async API calls, setting this to false can improve stability. - `Optional timeout` Timeout for each request. - `Optional type` Type of the embedding model. - `OPENAI_EMBEDDING("OPENAI_EMBEDDING")` - `class VertexAiEmbeddingConfig:` - `Optional component` Configuration for the VertexAI embedding model. - `Optional clientEmail` The client email for the VertexAI credentials. - `String location` The default location to use when making API calls. - `Optional privateKey` The private key for the VertexAI credentials. - `Optional privateKeyId` The private key ID for the VertexAI credentials. - `String project` The default GCP project to use when making Vertex API calls. - `Optional tokenUri` The token URI for the VertexAI credentials. - `Optional additionalKwargs` Additional kwargs for the Vertex. - `Optional className` - `Optional embedBatchSize` The batch size for embedding calls. - `Optional embedMode` The embedding mode to use. - `DEFAULT("default")` - `CLASSIFICATION("classification")` - `CLUSTERING("clustering")` - `SIMILARITY("similarity")` - `RETRIEVAL("retrieval")` - `Optional modelName` The modelId of the VertexAI model to use. - `Optional numWorkers` The number of workers to use for async embedding calls. - `Optional type` Type of the embedding model. - `VERTEXAI_EMBEDDING("VERTEXAI_EMBEDDING")` - `class BedrockEmbeddingConfig:` - `Optional component` Configuration for the Bedrock embedding model. - `Optional additionalKwargs` Additional kwargs for the bedrock client. - `Optional awsAccessKeyId` AWS Access Key ID to use - `Optional awsSecretAccessKey` AWS Secret Access Key to use - `Optional awsSessionToken` AWS Session Token to use - `Optional className` - `Optional embedBatchSize` The batch size for embedding calls. - `Optional maxRetries` The maximum number of API retries. - `Optional modelName` The modelId of the Bedrock model to use. - `Optional numWorkers` The number of workers to use for async embedding calls. - `Optional profileName` The name of aws profile to use. If not given, then the default profile is used. - `Optional regionName` AWS region name to use. Uses region configured in AWS CLI if not passed - `Optional timeout` The timeout for the Bedrock API request in seconds. It will be used for both connect and read timeouts. - `Optional type` Type of the embedding model. - `BEDROCK_EMBEDDING("BEDROCK_EMBEDDING")` - `String name` - `String projectId` - `Optional configHash` Hashes for the configuration of a pipeline. - `Optional embeddingConfigHash` Hash of the embedding config. - `Optional parsingConfigHash` Hash of the llama parse parameters. - `Optional transformConfigHash` Hash of the transform config. - `Optional createdAt` Creation datetime - `Optional dataSink` Schema for a data sink. - `String id` Unique identifier - `Component component` Component that implements the data sink - `class UnionMember0:` - `class CloudPineconeVectorStore:` Cloud Pinecone Vector Store. This class is used to store the configuration for a Pinecone vector store, so that it can be created and used in LlamaCloud. Args: api_key (str): API key for authenticating with Pinecone index_name (str): name of the Pinecone index namespace (optional[str]): namespace to use in the Pinecone index insert_kwargs (optional[dict]): additional kwargs to pass during insertion - `String apiKey` The API key for authenticating with Pinecone - `String indexName` - `Optional className` - `Optional insertKwargs` - `Optional namespace` - `Optional supportsNestedMetadataFilters` - `TRUE(true)` - `class CloudPostgresVectorStore:` - `String database` - `long embedDim` - `String host` - `String password` - `long port` - `String schemaName` - `String tableName` - `String user` - `Optional className` - `Optional hnswSettings` HNSW settings for PGVector. - `Optional distanceMethod` The distance method to use. - `L2("l2")` - `IP("ip")` - `COSINE("cosine")` - `L1("l1")` - `HAMMING("hamming")` - `JACCARD("jaccard")` - `Optional efConstruction` The number of edges to use during the construction phase. - `Optional efSearch` The number of edges to use during the search phase. - `Optional m` The number of bi-directional links created for each new element. - `Optional vectorType` The type of vector to use. - `VECTOR("vector")` - `HALF_VEC("half_vec")` - `BIT("bit")` - `SPARSE_VEC("sparse_vec")` - `Optional hybridSearch` - `Optional performSetup` - `Optional supportsNestedMetadataFilters` - `class CloudQdrantVectorStore:` Cloud Qdrant Vector Store. This class is used to store the configuration for a Qdrant vector store, so that it can be created and used in LlamaCloud. Args: collection_name (str): name of the Qdrant collection url (str): url of the Qdrant instance api_key (str): API key for authenticating with Qdrant max_retries (int): maximum number of retries in case of a failure. Defaults to 3 client_kwargs (dict): additional kwargs to pass to the Qdrant client - `String apiKey` - `String collectionName` - `String url` - `Optional className` - `Optional clientKwargs` - `Optional maxRetries` - `Optional supportsNestedMetadataFilters` - `TRUE(true)` - `class CloudAzureAiSearchVectorStore:` Cloud Azure AI Search Vector Store. - `String searchServiceApiKey` - `String searchServiceEndpoint` - `Optional className` - `Optional clientId` - `Optional clientSecret` - `Optional embeddingDimension` - `Optional filterableMetadataFieldKeys` - `Optional indexName` - `Optional searchServiceApiVersion` - `Optional supportsNestedMetadataFilters` - `TRUE(true)` - `Optional tenantId` - `class CloudMongoDBAtlasVectorSearch:` Cloud MongoDB Atlas Vector Store. This class is used to store the configuration for a MongoDB Atlas vector store, so that it can be created and used in LlamaCloud. Args: mongodb_uri (str): URI for connecting to MongoDB Atlas db_name (str): name of the MongoDB database collection_name (str): name of the MongoDB collection vector_index_name (str): name of the MongoDB Atlas vector index fulltext_index_name (str): name of the MongoDB Atlas full-text index - `String collectionName` - `String dbName` - `String mongoDBUri` - `Optional className` - `Optional embeddingDimension` - `Optional fulltextIndexName` - `Optional supportsNestedMetadataFilters` - `Optional vectorIndexName` - `class CloudMilvusVectorStore:` Cloud Milvus Vector Store. - `String uri` - `Optional token` - `Optional className` - `Optional collectionName` - `Optional embeddingDimension` - `Optional supportsNestedMetadataFilters` - `class CloudAstraDbVectorStore:` Cloud AstraDB Vector Store. This class is used to store the configuration for an AstraDB vector store, so that it can be created and used in LlamaCloud. Args: token (str): The Astra DB Application Token to use. api_endpoint (str): The Astra DB JSON API endpoint for your database. collection_name (str): Collection name to use. If not existing, it will be created. embedding_dimension (int): Length of the embedding vectors in use. keyspace (optional[str]): The keyspace to use. If not provided, 'default_keyspace' - `String token` The Astra DB Application Token to use - `String apiEndpoint` The Astra DB JSON API endpoint for your database - `String collectionName` Collection name to use. If not existing, it will be created - `long embeddingDimension` Length of the embedding vectors in use - `Optional className` - `Optional keyspace` The keyspace to use. If not provided, 'default_keyspace' - `Optional supportsNestedMetadataFilters` - `TRUE(true)` - `String name` The name of the data sink. - `String projectId` - `SinkType sinkType` - `PINECONE("PINECONE")` - `POSTGRES("POSTGRES")` - `QDRANT("QDRANT")` - `AZUREAI_SEARCH("AZUREAI_SEARCH")` - `MONGODB_ATLAS("MONGODB_ATLAS")` - `MILVUS("MILVUS")` - `ASTRA_DB("ASTRA_DB")` - `Optional createdAt` Creation datetime - `Optional updatedAt` Update datetime - `Optional embeddingModelConfig` Schema for an embedding model config. - `String id` Unique identifier - `EmbeddingConfig embeddingConfig` The embedding configuration for the embedding model config. - `class AzureOpenAIEmbeddingConfig:` - `class CohereEmbeddingConfig:` - `class GeminiEmbeddingConfig:` - `class HuggingFaceInferenceApiEmbeddingConfig:` - `class OpenAIEmbeddingConfig:` - `class VertexAiEmbeddingConfig:` - `class BedrockEmbeddingConfig:` - `String name` The name of the embedding model config. - `String projectId` - `Optional createdAt` Creation datetime - `Optional updatedAt` Update datetime - `Optional embeddingModelConfigId` The ID of the EmbeddingModelConfig this pipeline is using. - `Optional llamaParseParameters` Settings that can be configured for how to use LlamaParse to parse files within a LlamaCloud pipeline. - `Optional adaptiveLongTable` - `Optional aggressiveTableExtraction` - `Optional annotateLinks` - `Optional autoMode` - `Optional autoModeConfigurationJson` - `Optional autoModeTriggerOnImageInPage` - `Optional autoModeTriggerOnRegexpInPage` - `Optional autoModeTriggerOnTableInPage` - `Optional autoModeTriggerOnTextInPage` - `Optional azureOpenAIApiVersion` - `Optional azureOpenAIDeploymentName` - `Optional azureOpenAIEndpoint` - `Optional azureOpenAIKey` - `Optional bboxBottom` - `Optional bboxLeft` - `Optional bboxRight` - `Optional bboxTop` - `Optional boundingBox` - `Optional compactMarkdownTable` - `Optional complementalFormattingInstruction` - `Optional contentGuidelineInstruction` - `Optional continuousMode` - `Optional disableImageExtraction` - `Optional disableOcr` - `Optional disableReconstruction` - `Optional doNotCache` - `Optional doNotUnrollColumns` - `Optional enableCostOptimizer` - `Optional extractCharts` - `Optional extractLayout` - `Optional extractPrintedPageNumber` - `Optional fastMode` - `Optional formattingInstruction` - `Optional gpt4oApiKey` - `Optional gpt4oMode` - `Optional guessXlsxSheetName` - `Optional hideFooters` - `Optional hideHeaders` - `Optional highResOcr` - `Optional htmlMakeAllElementsVisible` - `Optional htmlRemoveFixedElements` - `Optional htmlRemoveNavigationElements` - `Optional httpProxy` - `Optional ignoreDocumentElementsForLayoutDetection` - `Optional> imagesToSave` - `SCREENSHOT("screenshot")` - `EMBEDDED("embedded")` - `LAYOUT("layout")` - `Optional inlineImagesInMarkdown` - `Optional inputS3Path` - `Optional inputS3Region` - `Optional inputUrl` - `Optional internalIsScreenshotJob` - `Optional invalidateCache` - `Optional isFormattingInstruction` - `Optional jobTimeoutExtraTimePerPageInSeconds` - `Optional jobTimeoutInSeconds` - `Optional keepPageSeparatorWhenMergingTables` - `Optional> languages` - `AF("af")` - `AZ("az")` - `BS("bs")` - `CS("cs")` - `CY("cy")` - `DA("da")` - `DE("de")` - `EN("en")` - `ES("es")` - `ET("et")` - `FR("fr")` - `GA("ga")` - `HR("hr")` - `HU("hu")` - `ID("id")` - `IS("is")` - `IT("it")` - `KU("ku")` - `LA("la")` - `LT("lt")` - `LV("lv")` - `MI("mi")` - `MS("ms")` - `MT("mt")` - `NL("nl")` - `NO("no")` - `OC("oc")` - `PI("pi")` - `PL("pl")` - `PT("pt")` - `RO("ro")` - `RS_LATIN("rs_latin")` - `SK("sk")` - `SL("sl")` - `SQ("sq")` - `SV("sv")` - `SW("sw")` - `TL("tl")` - `TR("tr")` - `UZ("uz")` - `VI("vi")` - `AR("ar")` - `FA("fa")` - `UG("ug")` - `UR("ur")` - `BN("bn")` - `AS("as")` - `MNI("mni")` - `RU("ru")` - `RS_CYRILLIC("rs_cyrillic")` - `BE("be")` - `BG("bg")` - `UK("uk")` - `MN("mn")` - `ABQ("abq")` - `ADY("ady")` - `KBD("kbd")` - `AVA("ava")` - `DAR("dar")` - `INH("inh")` - `CHE("che")` - `LBE("lbe")` - `LEZ("lez")` - `TAB("tab")` - `TJK("tjk")` - `HI("hi")` - `MR("mr")` - `NE("ne")` - `BH("bh")` - `MAI("mai")` - `ANG("ang")` - `BHO("bho")` - `MAH("mah")` - `SCK("sck")` - `NEW("new")` - `GOM("gom")` - `SA("sa")` - `BGC("bgc")` - `TH("th")` - `CH_SIM("ch_sim")` - `CH_TRA("ch_tra")` - `JA("ja")` - `KO("ko")` - `TA("ta")` - `TE("te")` - `KN("kn")` - `Optional layoutAware` - `Optional lineLevelBoundingBox` - `Optional markdownTableMultilineHeaderSeparator` - `Optional maxPages` - `Optional maxPagesEnforced` - `Optional mergeTablesAcrossPagesInMarkdown` - `Optional model` - `Optional outlinedTableExtraction` - `Optional outputPdfOfDocument` - `Optional outputS3PathPrefix` - `Optional outputS3Region` - `Optional outputTablesAsHtml` - `Optional pageErrorTolerance` - `Optional pageFooterPrefix` - `Optional pageFooterSuffix` - `Optional pageHeaderPrefix` - `Optional pageHeaderSuffix` - `Optional pagePrefix` - `Optional pageSeparator` - `Optional pageSuffix` - `Optional parseMode` Enum for representing the mode of parsing to be used. - `PARSE_PAGE_WITHOUT_LLM("parse_page_without_llm")` - `PARSE_PAGE_WITH_LLM("parse_page_with_llm")` - `PARSE_PAGE_WITH_LVM("parse_page_with_lvm")` - `PARSE_PAGE_WITH_AGENT("parse_page_with_agent")` - `PARSE_PAGE_WITH_LAYOUT_AGENT("parse_page_with_layout_agent")` - `PARSE_DOCUMENT_WITH_LLM("parse_document_with_llm")` - `PARSE_DOCUMENT_WITH_LVM("parse_document_with_lvm")` - `PARSE_DOCUMENT_WITH_AGENT("parse_document_with_agent")` - `Optional parsingInstruction` - `Optional preciseBoundingBox` - `Optional premiumMode` - `Optional presentationOutOfBoundsContent` - `Optional presentationSkipEmbeddedData` - `Optional preserveLayoutAlignmentAcrossPages` - `Optional preserveVerySmallText` - `Optional preset` - `Optional priority` The priority for the request. This field may be ignored or overwritten depending on the organization tier. - `LOW("low")` - `MEDIUM("medium")` - `HIGH("high")` - `CRITICAL("critical")` - `Optional projectId` - `Optional removeHiddenText` - `Optional replaceFailedPageMode` Enum for representing the different available page error handling modes. - `RAW_TEXT("raw_text")` - `BLANK_PAGE("blank_page")` - `ERROR_MESSAGE("error_message")` - `Optional replaceFailedPageWithErrorMessagePrefix` - `Optional replaceFailedPageWithErrorMessageSuffix` - `Optional saveImages` - `Optional skipDiagonalText` - `Optional specializedChartParsingAgentic` - `Optional specializedChartParsingEfficient` - `Optional specializedChartParsingPlus` - `Optional specializedImageParsing` - `Optional spreadsheetExtractSubTables` - `Optional spreadsheetForceFormulaComputation` - `Optional spreadsheetIncludeHiddenSheets` - `Optional strictModeBuggyFont` - `Optional strictModeImageExtraction` - `Optional strictModeImageOcr` - `Optional strictModeReconstruction` - `Optional structuredOutput` - `Optional structuredOutputJsonSchema` - `Optional structuredOutputJsonSchemaName` - `Optional systemPrompt` - `Optional systemPromptAppend` - `Optional takeScreenshot` - `Optional targetPages` - `Optional tier` - `Optional useVendorMultimodalModel` - `Optional userPrompt` - `Optional vendorMultimodalApiKey` - `Optional vendorMultimodalModelName` - `Optional version` - `Optional> webhookConfigurations` Outbound webhook endpoints to notify on job status changes - `Optional> webhookEvents` Events to subscribe to (e.g. 'parse.success', 'extract.error'). If null, all events are delivered. - `EXTRACT_PENDING("extract.pending")` - `EXTRACT_SUCCESS("extract.success")` - `EXTRACT_ERROR("extract.error")` - `EXTRACT_PARTIAL_SUCCESS("extract.partial_success")` - `EXTRACT_CANCELLED("extract.cancelled")` - `PARSE_PENDING("parse.pending")` - `PARSE_RUNNING("parse.running")` - `PARSE_SUCCESS("parse.success")` - `PARSE_ERROR("parse.error")` - `PARSE_PARTIAL_SUCCESS("parse.partial_success")` - `PARSE_CANCELLED("parse.cancelled")` - `CLASSIFY_PENDING("classify.pending")` - `CLASSIFY_RUNNING("classify.running")` - `CLASSIFY_SUCCESS("classify.success")` - `CLASSIFY_ERROR("classify.error")` - `CLASSIFY_PARTIAL_SUCCESS("classify.partial_success")` - `CLASSIFY_CANCELLED("classify.cancelled")` - `SHEETS_PENDING("sheets.pending")` - `SHEETS_SUCCESS("sheets.success")` - `SHEETS_ERROR("sheets.error")` - `SHEETS_PARTIAL_SUCCESS("sheets.partial_success")` - `SHEETS_CANCELLED("sheets.cancelled")` - `UNMAPPED_EVENT("unmapped_event")` - `Optional webhookHeaders` Custom HTTP headers sent with each webhook request (e.g. auth tokens) - `Optional webhookOutputFormat` Response format sent to the webhook: 'string' (default) or 'json' - `Optional webhookUrl` URL to receive webhook POST notifications - `Optional webhookUrl` - `Optional managedPipelineId` The ID of the ManagedPipeline this playground pipeline is linked to. - `Optional metadataConfig` Metadata configuration for the pipeline. - `Optional> excludedEmbedMetadataKeys` List of metadata keys to exclude from embeddings - `Optional> excludedLlmMetadataKeys` List of metadata keys to exclude from LLM during retrieval - `Optional pipelineType` Type of pipeline. Either PLAYGROUND or MANAGED. - `PLAYGROUND("PLAYGROUND")` - `MANAGED("MANAGED")` - `Optional presetRetrievalParameters` Preset retrieval parameters for the pipeline. - `Optional alpha` Alpha value for hybrid retrieval to determine the weights between dense and sparse retrieval. 0 is sparse retrieval and 1 is dense retrieval. - `Optional className` - `Optional denseSimilarityCutoff` Minimum similarity score wrt query for retrieval - `Optional denseSimilarityTopK` Number of nodes for dense retrieval. - `Optional enableReranking` Enable reranking for retrieval - `Optional filesTopK` Number of files to retrieve (only for retrieval mode files_via_metadata and files_via_content). - `Optional rerankTopN` Number of reranked nodes for returning. - `Optional retrievalMode` The retrieval mode for the query. - `CHUNKS("chunks")` - `FILES_VIA_METADATA("files_via_metadata")` - `FILES_VIA_CONTENT("files_via_content")` - `AUTO_ROUTED("auto_routed")` - `Optional retrieveImageNodes` Whether to retrieve image nodes. - `Optional retrievePageFigureNodes` Whether to retrieve page figure nodes. - `Optional retrievePageScreenshotNodes` Whether to retrieve page screenshot nodes. - `Optional searchFilters` Metadata filters for vector stores. - `List filters` - `class MetadataFilter:` Comprehensive metadata filter for vector stores to support more operators. Value uses Strict types, as int, float and str are compatible types and were all converted to string before. See: https://docs.pydantic.dev/latest/usage/types/#strict-types - `String key` - `Optional value` - `double` - `String` - `List` - `List` - `List` - `Optional operator` Vector store filter operator. - `EQUALS("==")` - `GREATER(">")` - `LESS("<")` - `NOT_EQUALS("!=")` - `GREATER_OR_EQUALS(">=")` - `LESS_OR_EQUALS("<=")` - `IN("in")` - `NIN("nin")` - `ANY("any")` - `ALL("all")` - `TEXT_MATCH("text_match")` - `TEXT_MATCH_INSENSITIVE("text_match_insensitive")` - `CONTAINS("contains")` - `IS_EMPTY("is_empty")` - `class MetadataFilters:` Metadata filters for vector stores. - `Optional condition` Vector store filter conditions to combine different filters. - `AND("and")` - `OR("or")` - `NOT("not")` - `Optional searchFiltersInferenceSchema` JSON Schema that will be used to infer search_filters. Omit or leave as null to skip inference. - `class UnionMember0:` - `List` - `String` - `double` - `boolean` - `Optional sparseSimilarityTopK` Number of nodes for sparse retrieval. - `Optional sparseModelConfig` Configuration for sparse embedding models used in hybrid search. This allows users to choose between Splade and BM25 models for sparse retrieval in managed data sinks. - `Optional className` - `Optional modelType` The sparse model type to use. 'bm25' uses Qdrant's FastEmbed BM25 model (default for new pipelines), 'splade' uses HuggingFace Splade model, 'auto' selects based on deployment mode (BYOC uses term frequency, Cloud uses Splade). - `SPLADE("splade")` - `BM25("bm25")` - `AUTO("auto")` - `Optional status` Status of the pipeline. - `CREATED("CREATED")` - `DELETING("DELETING")` - `Optional transformConfig` Configuration for the transformation. - `class AutoTransformConfig:` - `Optional chunkOverlap` Chunk overlap for the transformation. - `Optional chunkSize` Chunk size for the transformation. - `Optional mode` - `AUTO("auto")` - `class AdvancedModeTransformConfig:` - `Optional chunkingConfig` Configuration for the chunking. - `class NoneChunkingConfig:` - `Optional mode` - `NONE("none")` - `class CharacterChunkingConfig:` - `Optional chunkOverlap` - `Optional chunkSize` - `Optional mode` - `CHARACTER("character")` - `class TokenChunkingConfig:` - `Optional chunkOverlap` - `Optional chunkSize` - `Optional mode` - `TOKEN("token")` - `Optional separator` - `class SentenceChunkingConfig:` - `Optional chunkOverlap` - `Optional chunkSize` - `Optional mode` - `SENTENCE("sentence")` - `Optional paragraphSeparator` - `Optional separator` - `class SemanticChunkingConfig:` - `Optional breakpointPercentileThreshold` - `Optional bufferSize` - `Optional mode` - `SEMANTIC("semantic")` - `Optional mode` - `ADVANCED("advanced")` - `Optional segmentationConfig` Configuration for the segmentation. - `class NoneSegmentationConfig:` - `Optional mode` - `NONE("none")` - `class PageSegmentationConfig:` - `Optional mode` - `PAGE("page")` - `Optional pageSeparator` - `class ElementSegmentationConfig:` - `Optional mode` - `ELEMENT("element")` - `Optional updatedAt` Update datetime ### Example ```java package com.llamacloud_prod.api.example; import com.llamacloud_prod.api.client.LlamaCloudClient; import com.llamacloud_prod.api.client.okhttp.LlamaCloudOkHttpClient; import com.llamacloud_prod.api.models.pipelines.Pipeline; import com.llamacloud_prod.api.models.pipelines.PipelineCreate; import com.llamacloud_prod.api.models.pipelines.PipelineUpsertParams; public final class Main { private Main() {} public static void main(String[] args) { LlamaCloudClient client = LlamaCloudOkHttpClient.fromEnv(); PipelineCreate params = PipelineCreate.builder() .name("x") .build(); Pipeline pipeline = client.pipelines().upsert(params); } } ``` #### Response ```json { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "class_name": "class_name", "embed_batch_size": 1, "model_name": "openai-text-embedding-3-small", "num_workers": 0 }, "type": "MANAGED_OPENAI_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "config_hash": { "embedding_config_hash": "embedding_config_hash", "parsing_config_hash": "parsing_config_hash", "transform_config_hash": "transform_config_hash" }, "created_at": "2019-12-27T18:11:19.117Z", "data_sink": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "component": { "foo": "bar" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "sink_type": "PINECONE", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config": { "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "embedding_config": { "component": { "additional_kwargs": { "foo": "bar" }, "api_base": "api_base", "api_key": "api_key", "api_version": "api_version", "azure_deployment": "azure_deployment", "azure_endpoint": "azure_endpoint", "class_name": "class_name", "default_headers": { "foo": "string" }, "dimensions": 0, "embed_batch_size": 1, "max_retries": 0, "model_name": "model_name", "num_workers": 0, "reuse_client": true, "timeout": 0 }, "type": "AZURE_EMBEDDING" }, "name": "name", "project_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "created_at": "2019-12-27T18:11:19.117Z", "updated_at": "2019-12-27T18:11:19.117Z" }, "embedding_model_config_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "llama_parse_parameters": { "adaptive_long_table": true, "aggressive_table_extraction": true, "annotate_links": true, "auto_mode": true, "auto_mode_configuration_json": "auto_mode_configuration_json", "auto_mode_trigger_on_image_in_page": true, "auto_mode_trigger_on_regexp_in_page": "auto_mode_trigger_on_regexp_in_page", "auto_mode_trigger_on_table_in_page": true, "auto_mode_trigger_on_text_in_page": "auto_mode_trigger_on_text_in_page", "azure_openai_api_version": "azure_openai_api_version", "azure_openai_deployment_name": "azure_openai_deployment_name", "azure_openai_endpoint": "azure_openai_endpoint", "azure_openai_key": "azure_openai_key", "bbox_bottom": 0, "bbox_left": 0, "bbox_right": 0, "bbox_top": 0, "bounding_box": "bounding_box", "compact_markdown_table": true, "complemental_formatting_instruction": "complemental_formatting_instruction", "content_guideline_instruction": "content_guideline_instruction", "continuous_mode": true, "disable_image_extraction": true, "disable_ocr": true, "disable_reconstruction": true, "do_not_cache": true, "do_not_unroll_columns": true, "enable_cost_optimizer": true, "extract_charts": true, "extract_layout": true, "extract_printed_page_number": true, "fast_mode": true, "formatting_instruction": "formatting_instruction", "gpt4o_api_key": "gpt4o_api_key", "gpt4o_mode": true, "guess_xlsx_sheet_name": true, "hide_footers": true, "hide_headers": true, "high_res_ocr": true, "html_make_all_elements_visible": true, "html_remove_fixed_elements": true, "html_remove_navigation_elements": true, "http_proxy": "http_proxy", "ignore_document_elements_for_layout_detection": true, "images_to_save": [ "screenshot" ], "inline_images_in_markdown": true, "input_s3_path": "input_s3_path", "input_s3_region": "input_s3_region", "input_url": "input_url", "internal_is_screenshot_job": true, "invalidate_cache": true, "is_formatting_instruction": true, "job_timeout_extra_time_per_page_in_seconds": 0, "job_timeout_in_seconds": 0, "keep_page_separator_when_merging_tables": true, "languages": [ "af" ], "layout_aware": true, "line_level_bounding_box": true, "markdown_table_multiline_header_separator": "markdown_table_multiline_header_separator", "max_pages": 0, "max_pages_enforced": 0, "merge_tables_across_pages_in_markdown": true, "model": "model", "outlined_table_extraction": true, "output_pdf_of_document": true, "output_s3_path_prefix": "output_s3_path_prefix", "output_s3_region": "output_s3_region", "output_tables_as_HTML": true, "page_error_tolerance": 0, "page_footer_prefix": "page_footer_prefix", "page_footer_suffix": "page_footer_suffix", "page_header_prefix": "page_header_prefix", "page_header_suffix": "page_header_suffix", "page_prefix": "page_prefix", "page_separator": "page_separator", "page_suffix": "page_suffix", "parse_mode": "parse_page_without_llm", "parsing_instruction": "parsing_instruction", "precise_bounding_box": true, "premium_mode": true, "presentation_out_of_bounds_content": true, "presentation_skip_embedded_data": true, "preserve_layout_alignment_across_pages": true, "preserve_very_small_text": true, "preset": "preset", "priority": "low", "project_id": "project_id", "remove_hidden_text": true, "replace_failed_page_mode": "raw_text", "replace_failed_page_with_error_message_prefix": "replace_failed_page_with_error_message_prefix", "replace_failed_page_with_error_message_suffix": "replace_failed_page_with_error_message_suffix", "save_images": true, "skip_diagonal_text": true, "specialized_chart_parsing_agentic": true, "specialized_chart_parsing_efficient": true, "specialized_chart_parsing_plus": true, "specialized_image_parsing": true, "spreadsheet_extract_sub_tables": true, "spreadsheet_force_formula_computation": true, "spreadsheet_include_hidden_sheets": true, "strict_mode_buggy_font": true, "strict_mode_image_extraction": true, "strict_mode_image_ocr": true, "strict_mode_reconstruction": true, "structured_output": true, "structured_output_json_schema": "structured_output_json_schema", "structured_output_json_schema_name": "structured_output_json_schema_name", "system_prompt": "system_prompt", "system_prompt_append": "system_prompt_append", "take_screenshot": true, "target_pages": "target_pages", "tier": "tier", "use_vendor_multimodal_model": true, "user_prompt": "user_prompt", "vendor_multimodal_api_key": "vendor_multimodal_api_key", "vendor_multimodal_model_name": "vendor_multimodal_model_name", "version": "version", "webhook_configurations": [ { "webhook_events": [ "parse.success", "parse.error" ], "webhook_headers": { "Authorization": "Bearer sk-..." }, "webhook_output_format": "json", "webhook_url": "https://example.com/webhooks/llamacloud" } ], "webhook_url": "webhook_url" }, "managed_pipeline_id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e", "metadata_config": { "excluded_embed_metadata_keys": [ "string" ], "excluded_llm_metadata_keys": [ "string" ] }, "pipeline_type": "PLAYGROUND", "preset_retrieval_parameters": { "alpha": 0, "class_name": "class_name", "dense_similarity_cutoff": 0, "dense_similarity_top_k": 1, "enable_reranking": true, "files_top_k": 1, "rerank_top_n": 1, "retrieval_mode": "chunks", "retrieve_image_nodes": true, "retrieve_page_figure_nodes": true, "retrieve_page_screenshot_nodes": true, "search_filters": { "filters": [ { "key": "key", "value": 0, "operator": "==" } ], "condition": "and" }, "search_filters_inference_schema": { "foo": { "foo": "bar" } }, "sparse_similarity_top_k": 1 }, "sparse_model_config": { "class_name": "class_name", "model_type": "splade" }, "status": "CREATED", "transform_config": { "chunk_overlap": 0, "chunk_size": 1, "mode": "auto" }, "updated_at": "2019-12-27T18:11:19.117Z" } ```