pinecone scala Download - pinecone scala Source code download

Pinecone Scala Client

This is an intuitive async full-fledged Scala client for Pinecone API supporting all the available index, vector, collection, inference and assistant operations/endpoints, provided in two convenient services called PineconeVectorService and PineconeIndexService. The supported calls are:

Vector Operations: describeIndexStats, query, delete, fetch, update, and upsert
Collection Operations: listCollections, createCollection, describeCollection, and deleteCollection
Index Operations: listIndexes, creatIndex, describeIndex, deleteIndex, and configureIndex
Inference Operations: embedData, rerank, and evaluate
Assistant Operations: listAssistants, createAssistant, describeAssistant, deleteAssistant, listFiles, uploadFile, describeFile, deleteFile, chatWithAssistant
- these operations are provided by two services: PineconeAssistantService and PineconeAssistantFileService

Note that in order to be consistent with the Pinecone API naming, the service function names match exactly the API endpoint titles/descriptions with camelcase. Also, we aimed the lib to be self-contained with the fewest dependencies possible therefore we ended up using only two libs play-ahc-ws-standalone and play-ws-standalone-json (at the top level).

✔️ Important: this is a "community-maintained" library and, as such, has no relation to Pinecone company.

Check out an article about the lib/client on Medium. Also, if you want to see hands-on examples right away, go to the Pinecone Examples or OpenAI + Pinecone Examples modules.

Installation

The currently supported Scala versions are 2.12, 2.13, and 3.

To pull the library you have to add the following dependency to your build.sbt

"io.cequence" %% "pinecone-scala-client" % "1.2.2"

or to pom.xml (if you use maven)

<dependency>
    <groupId>io.cequence</groupId>
    <artifactId>pinecone-scala-client_2.12</artifactId>
    <version>1.2.2</version>
</dependency>

Config

Env. variables: PINECONE_SCALA_CLIENT_API_KEY, and PINECONE_SCALA_CLIENT_ENV if pod-based service is used
File config (default): pinecone-scala-client.conf

Usage ?‍?

Ia. Obtaining PineconeIndexService

First you need to provide an implicit execution context as well as akka materializer, e.g., as

  implicit val ec = ExecutionContext.global
  implicit val materializer = Materializer(ActorSystem())

Then you can obtain a service (pod or serverless-based) in one of the following ways.

Default config (expects env. variable(s) to be set as defined in Config section)

  import io.cequence.pineconescala.service.PineconeIndexServiceFactory.FactoryImplicits

  val service = PineconeIndexServiceFactory().asOne

Custom config

  val config = ConfigFactory.load("path_to_my_custom_config")
  val service = PineconeIndexServiceFactory(config).asOne

Without config for pod-based service (with env) - creates an instance of PineconePodBasedIndexService

  val service  = PineconeIndexServiceFactory(
    apiKey = "your_api_key",
    environment = "your_env" // e.g. "northamerica-northeast1-gcp
  )

Without config for serverless service - creates an instance of PineconeServerlessIndexService

  val service = PineconeIndexServiceFactory(
    apiKey = "your_api_key"
  )

Ib. Obtaining PineconeVectorService

Same as with PineconeIndexService, you need to first provide implicit execution context and Akka materializer. Then you can obtain a service in one of the following ways.

Default config (expects env. variable(s) to be set as defined in Config section). Note that if the index with a given name is not available, the factory will return None.

  PineconeVectorServiceFactory("index_name").map { serviceOption =>
    val service = serviceOption.getOrElse(
      throw new Exception(s"Index with a given name does not exist.")
    )
    // do something with the service
  }

Ic. Obtaining PineconeInferenceService

Same as with PineconeIndexService, you need to first provide implicit execution context and Akka materializer. Then you can obtain a service in one of the following ways.

Default config

  val service = PineconeInferenceServiceFactory()

Custom config

  val config = ConfigFactory.load("path_to_my_custom_config")
  val service = PineconeInferenceServiceFactory(config)

Directly with api-key

  val service = PineconeInferenceServiceFactory(
    apiKey = "your_api_key"
  )

Id. Obtaining PineconeAssistantService

Default config

  val service = PineconeAssistantServiceFactory()

Custom config

  val config = ConfigFactory.load("path_to_my_custom_config")
  val service = PineconeAssistantServiceFactory(config)

Directly with api-key

  val service = PineconeAssistantServiceFactory(
    apiKey = "your_api"
  )

Ie. Obtaining PineconeAssistantFileService

Default config

  val service = PineconeAssistantFileServiceFactory()

Custom config

  val config = ConfigFactory.load("path_to_my_custom_config")
  val service = PineconeAssistantFileServiceFactory(config)

Directly with api-key

  val service = PineconeAssistantFileServiceFactory(
    apiKey = "your_api"
  )

II. Calling functions

Full documentation of each call with its respective inputs and settings is provided in PineconeVectorService and PineconeIndexService. Since all the calls are async they return responses wrapped in Future.

Examples:

Index Operations

List indexes

  pineconeIndexService.listIndexes.map(indexes =>
    indexes.foreach(println)
  )

Create index (with default settings)

  import io.cequence.pineconescala.domain.response.CreateResponse

  pineconeIndexService.createIndex(
    name = "auto-gpt-test",
    dimension = 1536
  ).map {
    case CreateResponse.Created => println("Index successfully created.")
    case CreateResponse.BadRequest => println("Index creation failed. Request exceeds quota or an invalid index name.")
    case CreateResponse.AlreadyExists => println("Index with a given name already exists.")
  }

Describe index

  pineconeIndexService.describeIndex("index_name").map(indexInfo =>
    // if not found, indexInfo will be None    
    println(indexInfo)
  )

Delete index

  import io.cequence.pineconescala.domain.response.DeleteResponse

  pineconeIndexService.deleteIndex("index_name").map {
    case DeleteResponse.Deleted => println("Index successfully deleted.")
    case DeleteResponse.NotFound => println("Index with a given name not found.")
  }

Configure index

  import io.cequence.pineconescala.domain.response.ConfigureIndexResponse

  pineconeIndexService.configureIndex(
    name = "index_name",
    replicas = Some(2),
    pod_type = Some(PodType.p1_x2)
  ).map { 
    case ConfigureIndexResponse.Updated => println("Index successfully updated.")
    case ConfigureIndexResponse.BadRequestNotEnoughQuota => println("Index update failed. Not enough quota.")
    case ConfigureIndexResponse.NotFound => println("Index with a given name not found.")
  }

Collection Operations

List collections

  pineconeIndexService.listCollections.map(collectionNames =>
    println(collectionNames.mkString(", "))
  )

Create collection

  import io.cequence.pineconescala.domain.response.CreateResponse

  pineconeIndexService.createCollection(
    name = "collection_name",
    source = "index_name"
  ).map {
    case CreateResponse.Created => println("Collection successfully created.")
    case CreateResponse.BadRequest => println("Collection creation failed. Request exceeds quota or an invalid collection name.")
    case CreateResponse.AlreadyExists => println("Collection with a given name already exists.")
  }

Describe collection

  pineconeIndexService.describeCollection("collection_name").map(collectionInfo =>
    // if not found, collectionInfo will be None
    println(collectionInfo)
  )

Delete collection

  import io.cequence.pineconescala.domain.response.DeleteResponse

  pineconeIndexService.deleteCollection("collection_name").map {
    case DeleteResponse.Deleted => println("Collection successfully deleted.")
    case DeleteResponse.NotFound => println("Collection with a given name not found.")
  }

Vector Operations

Upsert

  val dimension = 1536

  pineconeVectorService.upsert(
    vectors = Seq(
      PVector(
        id = "666",
        values = Seq.fill(dimension)(Random.nextDouble),
        metadata = Map(
          "is_relevant" -> "not really but for testing it's ok, you know",
          "food_quality" -> "brunches are perfect but don't go there before closing time"
        )
      ),
      PVector(
        id = "777",
        values = Seq.fill(dimension)(Random.nextDouble),
        metadata = Map(
          "is_relevant" -> "very much so",
          "food_quality" -> "burritos are the best!"
        )
      )
    ),
    namespace = "my_namespace",
  ).map(vectorUpsertedCount =>
    println(s"Upserted $vectorUpsertedCount vectors.")
  )

Update

  val fetchedValues = ... // vectors fetched from somewhere 

  pineconeVectorService.update(
    id = "777",
    namespace = "my_namespace",
    values = fetchedValues.map(_ / 100), // divide fetched values by 100
    sparseValues = Some(SparseVector(
      indices = Seq(1, 2, 3),
      values = Seq(8.8, 7.7, 2.2)
    )),
    setMetaData = Map(
      "solid_info" -> "this is the source of the truth"
    )
  ).map(_ =>
    println(s"Vectors updated.")
  )

Query with default settings

  pineconeVectorService.query(
    vector = Seq.fill(1536)(Random.nextDouble), // some values/embeddings
    namespace = "my_namespace"
  ).map { queryResponse =>
    queryResponse.matches.foreach { matchInfo =>
      println(s"Matched vector id: ${matchInfo.id}")
      println(s"Matched vector values: ${matchInfo.values.take(20).mkString(", ")}..")
      println(s"Matched vector score: ${matchInfo.score}")
      println(s"Matched vector metadata: ${matchInfo.metadata}")
    }
  }

Query with custom settings

  pineconeVectorService.query(
    vector = Seq.fill(1536)(Random.nextDouble), // some values/embeddings
    namespace = "my_namespace",
    settings = QuerySettings(
      topK = 5,
      includeValues = true,
      includeMetadata = true
    )
  ).map { queryResponse =>
    queryResponse.matches.foreach { matchInfo =>
      println(s"Matched vector id: ${matchInfo.id}")
      println(s"Matched vector values: ${matchInfo.values.take(20).mkString(", ")}..")
      println(s"Matched vector score: ${matchInfo.score}")
      println(s"Matched vector metadata: ${matchInfo.metadata}")
    }
  }

Fetch

  pineconeVectorService.fetch(
    ids = Seq("666", "777"),
    namespace = "my_namespace"
  ).map { fetchResponse =>
    fetchResponse.vectors.values.map { pVector =>
      println(s"Fetched vector id: ${pVector.id}")
      println(s"Fetched vector values: ${pVector.values.take(20).mkString(", ")}..")
      println(s"Fetched vector metadata: ${pVector.metadata}")
   }
}

Delete by id(s)

  pineconeVectorService.delete(
    ids = Seq("666", "777"),
    namespace = "my_namespace"
  ).map(_ =>
    println("Vectors deleted")
  )

Delete all

  pineconeVectorService.deleteAll(
    namespace = "my_namespace"
  ).map(_ =>
    println("All vectors deleted")
  )

Describe index stats

  pineconeVectorService.describeIndexStats.map(stats =>
    println(stats)      
  )

Inference Operations

Generate embeddings

  pineconeInferenceService.createEmbeddings(
    Seq("The quick brown fox jumped over the lazy dog")
  ).map { embeddings =>
    println(embeddings.data.mkString("n"))
  }

Rerank documents / chunks

  pineconeInferenceService.rerank(
    query = "The tech company Apple is known for its innovative products like the iPhone.",
    documents = Seq(...)  
  ).map(
    _.data.foreach(println)
  )

Evaluate Q&A

  pineconeInferenceService.evaluate(
    question = "What are the capital cities of France, England and Spain?",
    answer = "Paris is a city of France and Barcelona of Spain",
    groundTruthAnswer = "Paris is the capital city of France, London of England and Madrid of Spain"
  ).map { response =>
    println(response)
  }

** Assistant Operations**

List assistants

  pineconeAssistantService.listAssistants.map(assistants =>
    println(assistants.mkString(", "))
  )

Create assistant

  import io.cequence.pineconescala.domain.response.CreateResponse

  pineconeAssistantService.createAssistant(
    name = "assistant_name",
    description = "assistant_description",
    assistantType = "assistant_type"
  ).map {
    case CreateResponse.Created => println("Assistant successfully created.")
    case CreateResponse.BadRequest => println("Assistant creation failed. Request exceeds quota or an invalid assistant name.")
    case CreateResponse.AlreadyExists => println("Assistant with a given name already exists.")
  }

Describe assistant

  pineconeAssistantService.describeAssistant("assistant_name").map(assistant =>
    // if not found, assistant will be None
    println(assistant)
  )

Delete assistant

  import io.cequence.pineconescala.domain.response.DeleteResponse

  pineconeAssistantService.deleteAssistant("assistant_name").map {
    case DeleteResponse.Deleted => println("Assistant successfully deleted.")
    case DeleteResponse.NotFound => println("Assistant with a given name not found.")
  }

List assistant files

  pineconeAssistantService.listFiles("assistant_name").map(files =>
    println(files.mkString(", "))
  )

Upload assistant file

  import io.cequence.pineconescala.domain.response.CreateResponse

  pineconeAssistantService.uploadFile(
    assistantName = "assistant_name",
    filePath = "path_to_file"
  ).map {
    case CreateResponse.Created => println("File successfully uploaded.")
    case CreateResponse.BadRequest => println("File upload failed. Request exceeds quota or an invalid file path.")
    case CreateResponse.AlreadyExists => println("File with a given name already exists.")
  }

Describe assistant file

  pineconeAssistantService.describeFile("assistant_name", "file_name").map(file =>
    // if not found, file will be None
    println(file)
  )

Chat with an assistant

  pineconeAssistantService.chatWithAssistant(
    "assistant_name",
    "What is the maximum height of a red pine?"
  ).map(response =>
    println(response)
  )

Demo

For ready-to-run demos pls. refer to separate modules:

Pinecone Scala Demo - shows how to use Pinecone vector, index, and collection operations
Pinecone + OpenAI Scala Demo - shows how to generate and store OpenAI embeddings into Pinecone and query them afterwards

FAQ ?

I got a timeout exception. How can I change the timeout setting?

You can do it either by passing the timeouts param to Pinecone{Vector,Index}ServiceFactory or, if you use your own configuration file, then you can simply add it there as:

pinecone-scala-client {
    timeouts {
        requestTimeoutSec = 200
        readTimeoutSec = 200
        connectTimeoutSec = 5
        pooledConnectionIdleTimeoutSec = 60
    }
}

I got an exception like com.typesafe.config.ConfigException$UnresolvedSubstitution: pinecone-scala-client.conf @ jar:file:.../io/cequence/pinecone-scala-client_2.13/1.2.2/pinecone-scala-client_2.13-1.2.2.jar!/pinecone-scala-client.conf: 4: Could not resolve substitution to a value: ${PINECONE_SCALA_CLIENT_API_KEY}. What should I do?

Set the env. variable PINECONE_SCALA_CLIENT_API_KEY. If you don't have one register here.
It all looks cool. I want to chat with you about your research and development?

Just shoot us an email at [email protected].