openai_chat_completion

Beta

Generates responses to messages in a chat conversation, using the OpenAI API and external tools.

Introduced in version 4.32.0.

  • Common

  • Advanced

# Common configuration fields, showing default values
label: ""
openai_chat_completion:
  server_address: https://api.openai.com/v1
  api_key: "" # No default (required)
  model: gpt-4o # No default (required)
  prompt: "" # No default (optional)
  system_prompt: "" # No default (optional)
  image: 'root = this.image.decode("base64") # decode base64 encoded image' # No default (optional)
  max_tokens: 0 # No default (optional)
  temperature: 0 # No default (optional)
  user: "" # No default (optional)
  response_format: text
  json_schema:
    name: "" # No default (required)
    schema: "" # No default (required)
  tools: [] # No default (required)
# All configuration fields, showing default values
label: ""
openai_chat_completion:
  server_address: https://api.openai.com/v1
  api_key: "" # No default (required)
  model: gpt-4o # No default (required)
  prompt: "" # No default (optional)
  system_prompt: "" # No default (optional)
  image: 'root = this.image.decode("base64") # decode base64 encoded image' # No default (optional)
  max_tokens: 0 # No default (optional)
  temperature: 0 # No default (optional)
  user: "" # No default (optional)
  response_format: text
  json_schema:
    name: "" # No default (required)
    description: "" # No default (optional)
    schema: "" # No default (required)
  schema_registry:
    url: "" # No default (required)
    name_prefix: schema_registry_id_
    subject: "" # No default (required)
    refresh_interval: "" # No default (optional)
    tls:
      skip_cert_verify: false
      enable_renegotiation: false
      root_cas: "" # No default (optional)
      root_cas_file: "" # No default (optional)
      client_certs: [] # Optional
    oauth:
      enabled: false
      consumer_key: "" # No default (optional)
      consumer_secret: "" # No default (optional)
      access_token: "" # No default (optional)
      access_token_secret: "" # No default (optional)
    basic_auth:
      enabled: false
      username: "" # No default (optional)
      password: "" # No default (optional)
    jwt:
      enabled: false
      private_key_file: "" # No default (optional)
      signing_method: "" # No default (optional)
      claims: {} # Optional
      headers: {} # Optional
  top_p: 0 # No default (optional)
  frequency_penalty: 0 # No default (optional)
  presence_penalty: 0 # No default (optional)
  seed: 0 # No default (optional)
  stop: [] # No default (optional)
  tools: [] # No default (required)

This processor sends user prompts to the OpenAI API, and the specified large language model (LLM) generates responses using all available context, including supplementary data provided by external tools. By default, the processor submits the entire payload of each message as a string, unless you use the prompt configuration field to customize it.

To learn more about chat completion, see the OpenAI API documentation, and Examples.

Fields

server_address

The OpenAI API endpoint to which the processor sends requests. Update the default value to use a different OpenAI-compatible service.

Type: string

Default: "https://api.openai.com/v1"

api_key

The API secret key for OpenAI API.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Secrets.

Type: string

model

The name of the OpenAI model to use.

Type: string

# Examples

model: gpt-4o

model: gpt-4o-mini

model: gpt-4

model: gpt4-turbo

prompt

The user prompt for which a response is generated. By default, the processor sends the entire payload as a string unless customized using this field.

Type: string

system_prompt

The system prompt to submit along with the user prompt. This field supports interpolation functions.

Type: string

image

An optional image to submit along with the prompt. The result of the Bloblang mapping must be a byte array.

Type: string

# Examples

image: 'root = this.image.decode("base64")' # Decode base64 encoded image

Requires version 4.38.0 or newer

max_tokens

The maximum number of tokens to generate for chat completion.

Type: int

temperature

Choose a sampling temperature between 0 and 2:

  • Higher values, such as 0.8 make the output more random.

  • Lower values, such as 0.2 make the output more focused and deterministic.

Redpanda recommends adding a value for this field or top_p, but not both.

Type: float

user

A unique identifier that represents the end-user generating the prompt. This value can help OpenAI monitor and detect platform abuse. This field supports interpolation functions.

Type: string

response_format

Specify the configured model’s output format.

If you choose the json_schema option, you must also configure a json_schema or schema_registry.

Type: string

Default: text

Options: text, json, json_schema

json_schema

The JSON schema used by the model when generating responses in json_schema format. To learn more about supported JSON schema features, see the OpenAI documentation.

Type: object

json_schema.name

The name of the JSON schema to use.

Type: string

json_schema.description

An optional description, which helps the model understand the schema’s purpose.

Type: string

json_schema.schema

The JSON schema for the model to use when generating the output.

Type: string

schema_registry

The schema registry to dynamically load schemas for model responses in json_schema format. Schemas must be in JSON format. To learn more about supported JSON schema features, see the OpenAI documentation.

Type: object

schema_registry.url

The base URL of the schema registry service.

Type: string

schema_registry.name_prefix

A prefix to add to the schema registry name. To form the complete schema registry name, the schema ID is appended as a suffix.

Type: string

Default: schema_registry_id_

schema_registry.subject

The subject name used to fetch the schema from the schema registry.

Type: string

schema_registry.refresh_interval

How frequently to poll the schema registry for updates. If not specified, the schema does not refresh automatically.

Type: string

schema_registry.tls

Specify custom TLS settings to override system defaults.

Type: object

schema_registry.tls.skip_cert_verify

Whether to skip server-side certificate verification.

Type: bool

Default: false

schema_registry.tls.enable_renegotiation

Whether to allow the remote server to request renegotiation. Enable this option if you’re seeing the error message local error: tls: no renegotiation.

Type: bool

Default: false

Requires version 3.45.0 or newer

schema_registry.tls.root_cas

Specify a certificate authority to use (optional). This is a string that represents a certificate chain from the parent trusted root certificate, through possible intermediate signing certificates, to the host certificate.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Secrets.

Type: string

Default: ""

# Examples
root_cas: |-
  -----BEGIN CERTIFICATE-----
  ...
  -----END CERTIFICATE-----

schema_registry.tls.root_cas_file

Specify the path to a root certificate authority file (optional). This is a file, often with a .pem extension, that contains a certificate chain from the parent trusted root certificate, through possible intermediate signing certificates, to the host certificate.certificate.

Type: string

Default: ""

# Examples
root_cas_file: ./root_cas.pem

schema_registry.tls.client_certs

A list of client certificates to use. For each certificate, specify values for either the cert and key fields, or cert_file and key_file fields.

Type: array

Default: []

# Examples
client_certs:
  - cert: foo
    key: bar
client_certs:
  - cert_file: ./example.pem
    key_file: ./example.key

schema_registry.tls.client_certs[].cert

The plain text certificate to use.

Type: string

Default: ""

schema_registry.tls.client_certs[].key

The plain text certificate key to use.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Secrets.

Type: string

Default: ""

schema_registry.tls.client_certs[].cert_file

The path to the certificate to use.

Type: string

Default: ""

schema_registry.tls.client_certs[].key_file

The path of a certificate key to use.

Type: string

Default: ""

schema_registry.tls.client_certs[].password

The plain text password for when the private key is password encrypted in PKCS#1 or PKCS#8 format. The obsolete pbeWithMD5AndDES-CBC algorithm is not supported for the PKCS#8 format.

The pbeWithMD5AndDES-CBC algorithm does not authenticate ciphertext, and is vulnerable to padding oracle attacks which may allow an attacker to recover the plain text password.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Secrets.

Type: string

Default: ""

# Examples
password: foo
password: ${KEY_PASSWORD}

schema_registry.oauth

Configure OAuth version 1.0 to give this component authorized access to your schema registry.

Type: object

schema_registry.oauth.enabled

Whether to use OAuth version 1 in requests to the schema registry.

Type: bool

Default: false

schema_registry.oauth.consumer_key

The value used to identify this component or client to your schema registry.

Type: string

Default: ""

schema_registry.oauth.consumer_secret

The secret used to establish ownership of the consumer key.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Secrets.

Type: string

Default: ""

schema_registry.oauth.access_token

The value this component can use to gain access to the data in the schema registry.

Type: string

Default: ""

schema_registry.oauth.access_token_secret

The secret that establishes ownership of the oauth.access_token.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Secrets.

Type: string

Default: ""

schema_registry.basic_auth

Configure basic authentication for requests from this component to your schema registry.

Type: object

schema_registry.basic_auth.enabled

Whether to use basic authentication in requests.

Type: bool

Default: false

schema_registry.basic_auth.username

The username of the account credentials to authenticate as.

Type: string

Default: ""

schema_registry.basic_auth.password

The password of the account credentials to authenticate with.

This field contains sensitive information that usually shouldn’t be added to a configuration directly. For more information, see Secrets.

Type: string

Default: ""

schema_registry.jwt (beta)

Configure JSON Web Token (JWT) authentication for the secure transmission of data from your schema registry to this component.

Type: object

schema_registry.jwt.enabled

Whether to use JWT authentication in requests.

Type: bool

Default: false

schema_registry.jwt.private_key_file

A file in PEM format, encoded using PKCS1 or PKCS8 as private key.

Type: string

Default: ""

schema_registry.jwt.signing_method

The method used to sign the token, such as RS256, RS384, RS512, or EdDSA.

Type: string

Default: ""

schema_registry.jwt.claims

Values used to pass the identity of the authenticated entity to the service provider. In this case, between this component and the schema registry.

Type: object

Default: {}

schema_registry.jwt.headers

The key/value pairs that identify the type of token and signing algorithm (optional).

Type: object

Default: {}

top_p

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. For example, a top_p of 0.1 means only the tokens comprising the top 10% probability mass are sampled.

Redpanda recommends adding a value for this field or temperature, but not both.

Type: float

frequency_penalty

Specify a number between -2.0 and 2.0. Positive values penalize new tokens based on the frequency of their appearance in the text so far. This decreases the model’s likelihood to repeat the same line verbatim.

Type: float

presence_penalty

Specify a number between -2.0 and 2.0. Positive values penalize new tokens if they have appeared in the text so far. This increases the model’s likelihood to talk about new topics.

Type: float

seed

When set to a specific number, Redpanda Connect attempts to generate consistent responses for requests that use the same prompt, seed, and parameters.

Type: int

# Examples

seed: 42

stop

Specify up to four stop sequences to use. When the model encounters a stop pattern, it stops generating text and returns the final response.

Type: array

tools

External tools the model can invoke, such as functions, APIs, or web browsing. You can build a series of processors that include definitions of these tools, and the specified model can choose when to invoke them to help answer a prompt. For more information, see Examples.

If you don’t want to use external tools, enter an empty array tools:[].

Type: array

tools[].name

The name of the external tool you want to use.

Type: string

tools[].description

A description of what the tool does. The model uses this to decide when to invoke the tool.

Type: string

tools[].parameters

The parameters the model needs to invoke the tool.

Type: object

tools[].parameters.required

The parameters you must define.

Type: array

Default: []

tools[].parameters.properties

The required inputs to invoke the tool.

Type: object

tools[].parameters.properties.<name>.type

The data type of the parameter.

Type: string

tools[].parameters.properties.<name>.description

A description of the parameter.

Type: string

tools[].parameters.properties.<name>.enum

Defines this parameter as an enumeration and specifies the set of values the model is allowed to use.

Type: array

Default: []

tools[].processors

The pipeline to execute when the model invokes the external tool.

Type: array

Examples

  • Analyze an image and generate a description

  • Make calls to external tools

This configuration fetches image URLs from the stdin input, and uses the GPT-4o LLM to describe the images.

input:
  stdin:
    scanner:
      lines: {}
pipeline:
  processors:
    - http:
        verb: GET
        url: "${!content().string()}"
    - openai_chat_completion:
        model: gpt-4o
        api_key: "${OPENAI_API_KEY}"
        prompt: "Describe the following image"
        image: "root = content()"
output:
  stdout:
    codec: lines: lines

In this configuration, the GPT-4o model executes a number of processors, which make a tool call to retrieve weather data for a specific city.

input:
  generate:
    count: 1
    mapping: |
      root = "What is the weather like in Chicago?"
pipeline:
  processors:
    - openai_chat_completion:
        model: gpt-4o
        api_key: "${OPENAI_API_KEY}"
        prompt: "${!content().string()}"
        tools:
          - name: GetWeather
            description: "Retrieve the weather for a specific city"
            parameters:
              required: ["city"]
              properties:
                city:
                  type: string
                  description: the city to look up the weather for
            processors:
              - http:
                  verb: GET
                  url: 'https://wttr.in/${!this.city}?T'
                  headers:
                    User-Agent: curl/8.11.1 # Returns a text string from the weather website
output:
  stdout: {}