Glossary

Overview

Glossary prompts define domain-specific terms, descriptions, and synonyms that agents use to understand specialized vocabulary. Each entry contains a term name, description, and list of synonyms.

Glossary prompts are stored as text prompts on the platform. The SDK parses the YAML or JSON content into typed Python objects.

---

Convenience methods

These methods automatically apply the folder prefix and type="glossary", so you don't have to.

get_glossary (source)

Get a glossary prompt by name.

Automatically prefixes the name with glossaries/ and sets type="glossary".

get_glossary(
    name: str,
    *,
    version: int | None = None,
    label: str | None = None,
    cache_ttl_seconds: int | None = None,
    fallback: str | None = None,
    max_retries: int | None = None,
    fetch_timeout_seconds: int | None = None,
) -> GlossaryPromptClient

Parameters

• name — Glossary name (without the glossaries/ prefix).

• version — Optional version number.

• label — Optional label filter.

• cache_ttl_seconds — Cache TTL override.

• fallback — Fallback YAML/JSON content string.

• max_retries — Maximum number of retries.

• fetch_timeout_seconds — Fetch timeout override.

Returns

GlossaryPromptClient

---

create_glossary (source)

Create a glossary prompt.

Automatically prefixes the name with glossaries/ and sets type="glossary".

create_glossary(
    *,
    name: str,
    prompt: str,
    labels: List[str] | None = None,
    tags: List[str] | None = None,
    config: Any | None = None,
    commit_message: str | None = None,
) -> GlossaryPromptClient

Parameters

• name — Glossary name (without the glossaries/ prefix).

• prompt — JSON content string.

• labels — Labels to assign.

• tags — Tags to assign.

• config — Additional config dict.

• commit_message — Optional commit message.

Returns

GlossaryPromptClient

---

update_glossary (source)

Update a glossary prompt version.

Automatically sets type="glossary" and routes through the type-specific endpoint.

update_glossary(
    *,
    name: str,
    version: int,
    new_labels: List[str] | None = None,
) -> Any

Parameters

• name — Glossary name (without the glossaries/ prefix).

• version — The version number of the prompt to update.

• new_labels — New labels to assign to the prompt version.

Returns

The updated prompt from the InteractiveAI API.

---

list_glossaries (source)

List glossary prompts.

list_glossaries(
    *,
    label: str | None = None,
    tag: str | None = None,
    page: int | None = None,
    limit: int | None = None,
) -> PromptMetaListResponse

Parameters

• label — Optional label filter.

• tag — Optional tag filter.

• page — Page number.

• limit — Items per page.

Returns

PromptMetaListResponse

---

delete_glossary (source)

Delete a glossary prompt.

Automatically prefixes the name with glossaries/.

delete_glossary(
    name: str,
    *,
    label: str | None = None,
    version: int | None = None,
) -> None

Parameters

• name — Glossary name (without the glossaries/ prefix).

• label — If set, deletes versions carrying this label.

• version — If set, deletes only this specific version.

---

Fetching glossary

glossary = client.get_glossary("finance-terms")

for term in glossary.entries:
    print(term.name, term.description, term.synonyms)

---

Creating glossary

content = """
{
  "terms": [
    {
      "name": "RIB",
      "description": "Official document required to validate a bank account for withdrawals.",
      "synonyms": ["bank details"]
    },
    {
      "name": "BALANCE_REAL",
      "description": "Amount of real money (cash) in the account.",
      "synonyms": ["real balance", "cash balance"]
    }
  ]
}
"""

glossary = client.create_glossary(
    name="finance-terms",
    prompt=content,
    labels=["production"],
)

The SDK validates the YAML structure on create and raises ValueError if the content is malformed.

---

GlossaryPromptClient

Returned by get_glossary() and create_glossary().

Attributes

• name — Prompt name.

• version — Prompt version number.

• labels — List of labels (e.g. ["production"]).

• tags — List of tags.

• config — Arbitrary config dict stored with the prompt.

• is_fallback — True if this was returned from a fallback value.

• raw_content — The original unparsed text content.

• entries — List[GlossaryEntry] (property).

Methods

• compile() — Returns the parsed GlossaryContent dataclass. Template variable substitution does not apply to structured prompts.

• variables — Always returns an empty list.

---

GlossaryEntry

Dataclass representing a single glossary term.

Field	Type	Description
name	str	Term name (e.g. "RIB").
description	str	Human-readable description of the term.
synonyms	List[str]	Alternative names or translations for the term.
key	str	Storage key when terms are stored as a mapping.

---

Content format

Glossary can be authored in YAML or JSON. JSON is recommended for readability.

{
  "terms": [
    {
      "name": "WITHDRAWABLE_BALANCE",
      "description": "Total amount the player can withdraw right now.",
      "synonyms": ["withdrawable balance", "available for withdrawal"]
    },
    {
      "name": "KYC_STATUS",
      "description": "Know Your Customer verification status.",
      "synonyms": ["KYC", "identity verification"]
    }
  ]
}