The APIpie AI connector lets your AI agent act in each user's APIpie AI account. Each user connects their own APIpie AI access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 28 tools.
- Tools
- 28
- What they doRead · write · destructive
- 17 · 8 · 317 read8 write3 destructive
- Users sign in with
- Access token
Setup
Install the SDK
Terminal window npm install @scalekit-sdk/node dotenvTerminal window pip install scalekit-sdk-python python-dotenvSet your credentials
Add your Scalekit credentials to your
.envfile. Find values in app.scalekit.com > Developers > API Credentials..env SCALEKIT_ENVIRONMENT_URL=<your-environment-url>SCALEKIT_CLIENT_ID=<your-client-id>SCALEKIT_CLIENT_SECRET=<your-client-secret>Create the APIpie AI connection
In AgentKit > Connections, create an APIpie AI connection. The name you give it is the
connection_nameyour code passes. See Configure connections.Authorize a user and make your first call
quickstart.mts import { ScalekitClient } from '@scalekit-sdk/node'import 'dotenv/config'import { createInterface } from 'node:readline/promises'const scalekit = new ScalekitClient(process.env.SCALEKIT_ENVIRONMENT_URL,process.env.SCALEKIT_CLIENT_ID,process.env.SCALEKIT_CLIENT_SECRET,)const actions = scalekit.actionsconst connector = 'apipie'const identifier = 'user_123'// Generate an authorization link for the userconst { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })console.log('Authorize APIpie AI:', link)const rl = createInterface({ input: process.stdin, output: process.stdout })await rl.question('Press Enter after authorizing...')rl.close()// Make your first callconst result = await actions.executeTool({connector,identifier,toolName: 'apipie_models_detailed_list',toolInput: {},})console.log(result)Terminal window npx tsx quickstart.mtsquickstart.py import osfrom scalekit import ScalekitClientfrom dotenv import load_dotenvload_dotenv()scalekit_client = ScalekitClient(env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),client_id=os.getenv("SCALEKIT_CLIENT_ID"),client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),)actions = scalekit_client.actionsconnection_name = "apipie"identifier = "user_123"# Generate an authorization link for the userlink_response = actions.get_authorization_link(connection_name=connection_name,identifier=identifier,)print("Authorize APIpie AI:", link_response.link)input("Press Enter after authorizing...")# Make your first callresult = actions.execute_tool(tool_input={},tool_name="apipie_models_detailed_list",connection_name=connection_name,identifier=identifier,)print(result)Terminal window python quickstart.pyEach user opens the link once and enters their APIpie AI credentials there. See Authorize a user for the full flow and statuses.
Tools
Pass the exact name toexecute_toolapipie_jobs_searchSearch job postings (JSearch) by a free-form query with location, date, remote and type filters.Read-onlySearch Jobs
Search job postings (JSearch) by a free-form query with location, date, remote and type filters. Returns job postings with title, employer, location, description, apply links and dates. Include the job title and location in query for best results.
Inputs
querystringrequired- Search query, ideally job title plus location. Example: python developer in Berlin.
countrystring- Country code. Defaults to us. Example: de.
date_postedstring- Posted within. Defaults to all. Example: week.one of
alltoday3daysweekmonth employment_typesstring- Comma-separated types, for example FULLTIME,CONTRACTOR. Example: FULLTIME.
exclude_job_publishersstring- Comma-separated publishers to exclude. Example: Dice.
fieldsstring- Comma-separated job fields to return. Example: employer_name,job_title,job_apply_link.
job_requirementsstring- Comma-separated requirements, for example under_3_years_experience,no_degree. Example: no_degree.
languagestring- Language code for postings. Example: en.
num_pagesinteger- Number of pages to return from page. Defaults to 1. Example: 1.
pageinteger- Page to return (10 results each). Defaults to 1. Example: 1.
radiusinteger- Distance from the location in km. Example: 25.
userstring- Your end-user identifier, for per-user usage and billing observability. Example: customer-123.
work_from_homeboolean- Only remote jobs. Example: true.
apipie_models_detailed_listList models with detailed information, optionally filtered by type, provider or name.Read-onlyList Models Detailed
List models with detailed information, optionally filtered by type, provider or name. Returns models with full metadata, limits, pricing and capabilities. Use apipie_models_list for a quick list.
Inputs
modelstring- Model name. Example: claude-sonnet.
providerstring- Model provider. Example: anthropic.
typestring- Model type. Example: llm.
apipie_models_listList the models available through APIpie, optionally filtered by type, subtype or provider.Read-onlyList Models
List the models available through APIpie, optionally filtered by type, subtype or provider. Returns models with id, provider, type, subtype, context length and pricing. Use apipie_models_detailed_list for full details.
Inputs
combinationstring- Provider and subtype combination. Example: openai-chat.
enabledinteger- 1 to show only enabled chat models. Example: 1.one of
10 providerstring- Model provider. Example: openai.
subtypestring- Model subtype. Example: chat.one of
chatfill-maskquestion-answeringttssttmultimodal typestring- Model type. Example: llm.one of
llmvisionembeddingimagevoicemoderationcodingfree
apipie_property_details_getGet detailed information about one US property by its full address.Read-onlyGet Property Details
Get detailed information about one US property by its full address. Returns property details such as price or estimate, beds, baths, area, lot, year built, tax and history. Use apipie_real_estate_search to find properties first.
Inputs
addressstringrequired- Full property address. Example: 1600 Pennsylvania Ave NW, Washington, DC 20500.
userstring- Your end-user identifier, for per-user usage and billing observability. Example: customer-123.
apipie_queries_listList your API query history or its hourly, daily or weekly aggregates, newest first, with filters.Read-onlyList Query History
List your API query history or its hourly, daily or weekly aggregates, newest first, with filters. Returns query records with timestamp, user, app, provider, route (model), tokens and cost. Use this for cost and usage analysis.
Inputs
appstring- Only this app. Example: supportbot.
daysinteger- Days of history. Defaults to 30. Example: 7.
limitinteger- Records per page, up to 100. Defaults to 50. Example: 50.
offsetinteger- Records to skip. Example: 0.
providerstring- Only this provider. Example: openai.
routestring- Only this route or model. Example: gpt4omini.
showstring- all records, or hourly, daily (default) or weekly aggregates. Example: daily.one of
allhourlydailyweekly userstring- Only this user (letters and numbers, up to 14 characters). Example: customer123.
apipie_ragtune_collections_listList your RAG tune collections.Read-onlyList RAG Tune Collections
List your RAG tune collections. Returns the collection names. Use apipie_vector_collections_list for raw vector collections.
Inputs
vector_providerstring- Vector store to use. Use the same provider for a collection every time. Example: qdrant.one of
pineconeqdrant
apipie_real_estate_coordinates_searchSearch US property listings within a circle around a latitude and longitude.Read-onlySearch Real Estate By Coordinates
Search US property listings within a circle around a latitude and longitude. Returns listings with address, price, beds, baths, area and status. Use apipie_real_estate_search to search by place name.
Inputs
diameternumberrequired- Diameter of the search area in miles. Example: 2.
latnumberrequired- Latitude of the center. Example: 30.2672.
longnumberrequired- Longitude of the center. Example: -97.7431.
home_statusstring- Listing status. Defaults to FOR_SALE. Example: FOR_SALE.one of
FOR_SALEFOR_RENTRECENTLY_SOLD home_typestring- Comma-separated property types, for example Houses,Townhomes,Condos. Example: Houses,Condos.
max_bathroomsnumber- Maximum bathrooms. Example: 3.
max_bedroomsnumber- Maximum bedrooms. Example: 4.
max_pricenumber- Maximum price. Example: 800000.
max_sqftnumber- Maximum square footage. Example: 3000.
min_bathroomsnumber- Minimum bathrooms. Example: 1.
min_bedroomsnumber- Minimum bedrooms. Example: 2.
min_pricenumber- Minimum price. Example: 300000.
min_sqftnumber- Minimum square footage. Example: 1000.
sortstring- Sort order. Defaults to DEFAULT. Example: NEWEST.one of
DEFAULTVERIFIED_SOURCEPRICE_HIGH_LOWPRICE_LOW_HIGHNEWESTBEDROOMS userstring- Your end-user identifier, for per-user usage and billing observability. Example: customer-123.
apipie_real_estate_polygon_searchSearch US property listings inside a polygon.Read-onlySearch Real Estate By Polygon
Search US property listings inside a polygon. Returns listings with address, price, beds, baths, area and status. Use apipie_real_estate_coordinates_search for a circular area.
Inputs
polygonstringrequired- Polygon as a string of longitude latitude pairs separated by commas, closing on the first point. Example: -97.75 30.26, -97.73 30.26, -97.73 30.28, -97.75 30.28, -97.75 30.26.
home_statusstring- Listing status. Defaults to FOR_SALE. Example: FOR_SALE.one of
FOR_SALEFOR_RENTRECENTLY_SOLD home_typestring- Comma-separated property types, for example Houses,Townhomes,Condos. Example: Houses,Condos.
max_bathroomsnumber- Maximum bathrooms. Example: 3.
max_bedroomsnumber- Maximum bedrooms. Example: 4.
max_pricenumber- Maximum price. Example: 800000.
max_sqftnumber- Maximum square footage. Example: 3000.
min_bathroomsnumber- Minimum bathrooms. Example: 1.
min_bedroomsnumber- Minimum bedrooms. Example: 2.
min_pricenumber- Minimum price. Example: 300000.
min_sqftnumber- Minimum square footage. Example: 1000.
sortstring- Sort order. Defaults to DEFAULT. Example: NEWEST.one of
DEFAULTVERIFIED_SOURCEPRICE_HIGH_LOWPRICE_LOW_HIGHNEWESTBEDROOMS userstring- Your end-user identifier, for per-user usage and billing observability. Example: customer-123.
apipie_real_estate_searchSearch US property listings by county, neighborhood or ZIP code with price, size and room filters.Read-onlySearch Real Estate By Location
Search US property listings by county, neighborhood or ZIP code with price, size and room filters. Returns listings with address, price, beds, baths, area, status and photos, up to 41 per page. Use apipie_real_estate_coordinates_search or apipie_real_estate_polygon_search for map areas, and apipie_property_details_get for one address.
Inputs
locationstringrequired- County, neighborhood or ZIP code. Example: Austin, TX.
home_statusstring- Listing status. Defaults to FOR_SALE. Example: FOR_SALE.one of
FOR_SALEFOR_RENTRECENTLY_SOLD home_typestring- Comma-separated property types, for example Houses,Townhomes,Condos. Example: Houses,Condos.
max_bathroomsnumber- Maximum bathrooms. Example: 3.
max_bedroomsnumber- Maximum bedrooms. Example: 4.
max_pricenumber- Maximum price. Example: 800000.
max_sqftnumber- Maximum square footage. Example: 3000.
min_bathroomsnumber- Minimum bathrooms. Example: 1.
min_bedroomsnumber- Minimum bedrooms. Example: 2.
min_pricenumber- Minimum price. Example: 300000.
min_sqftnumber- Minimum square footage. Example: 1000.
pageinteger- Page to return. Defaults to 1. Example: 1.
sortstring- Sort order. Defaults to DEFAULT. Example: NEWEST.one of
DEFAULTVERIFIED_SOURCEPRICE_HIGH_LOWPRICE_LOW_HIGHNEWESTBEDROOMS userstring- Your end-user identifier, for per-user usage and billing observability. Example: customer-123.
apipie_state_getGet the stored state settings (default model, memory, search and generation options) for the app or one end user.Read-onlyGet State Settings
Get the stored state settings (default model, memory, search and generation options) for the app or one end user. Returns the state record with its settings. Omit user for the app-level state. Use apipie_state_update to change it.
Inputs
app_namestring- App label for centralized state management. Example: supportbot.
userstring- End-user ID; omit for app-level state. Example: customer-123.
apipie_vector_collections_listList your vector collections.Read-onlyList Vector Collections
List your vector collections. Returns the collection names. Use apipie_vectors_list for the vectors in one collection.
Inputs
This tool takes no inputs.
apipie_vectors_fetchGet records from a vector collection by ID.Read-onlyFetch Vectors
Get records from a vector collection by ID. Returns the records with their values and metadata. Use apipie_vectors_list to find IDs.
Inputs
collection_namestringrequired- Vector collection name. Example: support-docs.
idsstringrequired- Vector ID to fetch. Example: doc-42-chunk-3.
apipie_vectors_listList vector IDs in a collection, optionally by ID prefix, with pagination.Read-onlyList Vectors
List vector IDs in a collection, optionally by ID prefix, with pagination. Returns vector IDs and a pagination token. Use apipie_vectors_fetch to read records by ID.
Inputs
collection_namestringrequired- Vector collection name. Example: support-docs.
limitinteger- Maximum IDs to return. Example: 100.
pagination_tokenstring- Token from the previous page. Example: eyJza2lwIjoxMDB9.
prefixstring- Only IDs starting with this prefix. Example: doc-42.
apipie_vectors_queryFind the vectors in a collection nearest to a query vector, optionally filtered by metadata or tag.Read-onlyQuery Vectors
Find the vectors in a collection nearest to a query vector, optionally filtered by metadata or tag. Returns matches with ID, score and, when requested, values and metadata. Embed the query text with apipie_embeddings_create first.
Inputs
collection_namestringrequired- Vector collection name. Example: support-docs.
vectorarrayrequired- Query embedding. Example: [0.12, -0.03, 0.44]
filterobject- Metadata filter. Example: {"metatag": "faq"}
include_metadataboolean- Include metadata. Example: true.
include_valuesboolean- Include vector values. Example: false.
metatagstring- Only vectors with this tag. Example: faq.
top_kinteger- Number of matches to return. Example: 5.
apipie_web_scrapeFetch a web page's content through Bright Data or Valyu.Read-onlyScrape Web Page
Fetch a web page's content through Bright Data or Valyu. Returns the page content, parsed (default) or raw. Use apipie_web_search to find pages first.
Inputs
urlstringrequired- URL of the page. Example: https://example.com/pricing.
formatstring- parsed (default) or raw. Example: parsed.one of
rawparsed providerstring- brightdata (default) or valyu. Example: brightdata.one of
brightdatavalyu scrape_lengthstring- Valyu only: short, medium, large, max, or a character count from 1000 to 1000000. Example: medium.
scrape_renderboolean- Render JavaScript fully before scraping. Example: true.
apipie_web_searchSearch the web with Valyu (search plus content extraction) or Google.Read-onlyWeb Search
Search the web with Valyu (search plus content extraction) or Google. Returns results with title, URL and, for Valyu, extracted content and relevance. Use apipie_web_search_answer for a written answer and apipie_web_scrape to read one page.
Inputs
querystringrequired- Search query. Example: latest EU AI Act guidance.
blacklistarray- Valyu only: domains, URLs or datasets to exclude. Example: ["example.com"]
end_datestring- Valyu only: latest date, YYYY-MM-DD. Example: 2026-11-01.
fast_modeboolean- Valyu only: lower latency, shorter results. Example: false.
geostring- Country code. Defaults to us. Example: us.
instructionsstring- Instructions for query rewriting and reranking, up to 500 characters. Example: Prefer official sources.
langstring- Language code. Defaults to en. Example: en.
max_pricenumber- Valyu only: maximum price in dollars per thousand retrievals. Example: 5.
relevance_thresholdnumber- Minimum relevance, 0 to 1, after reranking. Defaults to 0.5. Example: 0.5.
resultsinteger- Number of results: 1-100 for google, 1-20 for valyu. Defaults to 20. Example: 10.
safe_searchinteger- Google only: 1 on, -1 moderate (default), -2 off. Example: -1.one of
1-1-2 search_providerstring- valyu (default) or google. Example: valyu.one of
googlevalyu start_datestring- Valyu only: earliest date, YYYY-MM-DD. Example: 2026-01-01.
url_onlyboolean- Return only URLs, without content extraction. Example: false.
userstring- Your end-user identifier, for per-user usage and billing observability. Example: customer-123.
whitelistarray- Valyu only: domains, URLs or datasets to include. Example: ["europa.eu"]
apipie_web_search_answerSearch with Valyu and write an AI answer to a question grounded in the results.Read-onlySearch Answer
Search with Valyu and write an AI answer to a question grounded in the results. Returns the answer text with its sources. Use apipie_web_search for raw results.
Inputs
querystringrequired- Question to answer. Example: What changed in the EU AI Act in 2026?.
search_providerstringrequired- Must be valyu. Example: valyu.one of
valyu blacklistarray- Domains, URLs or datasets to exclude. Example: ["example.com"]
fast_modeboolean- Lower latency. Example: false.
geostring- Country code. Defaults to us. Example: us.
resultsinteger- Number of search results to use, 1-10. Defaults to 5. Example: 5.
searchstring- Sources to search: web, proprietary, all (default) or news. Example: news.one of
webproprietaryallnews system_instructionsstring- Instructions for how the answer is written. Example: Answer in three bullet points.
userstring- Your end-user identifier, for per-user usage and billing observability. Example: customer-123.
whitelistarray- Domains, URLs or datasets to include. Example: ["europa.eu"]
apipie_chat_completion_createSend a chat conversation to one or more language models through APIpie's router, with optional memory, RAG over a vector collection, internet search grounding and tool calling.WriteCreate Chat Completion
Send a chat conversation to one or more language models through APIpie's router, with optional memory, RAG over a vector collection, internet search grounding and tool calling. Returns an OpenAI-style completion: id, model, choices with the assistant message, and usage. Use apipie_models_list to pick a model. Use apipie_web_search_answer for a search-grounded answer without managing messages.
Inputs
messagesarrayrequired- Conversation so far, oldest first. Each message has a role (system, user or assistant) and content. Example: [{"role": "user", "content": "Why is the sky blue?"}]
modelstringrequired- Model to use, or up to 5 comma-separated models. See apipie_models_list. Example: gpt-4o-mini.
inline_clistring- Enable inline CLI :commands in the prompt, true/false or a comma-separated feature list. Example: true.
integrityinteger- Answer integrity: 12 returns the best of two answers, 13 the best of three. Example: 12.one of
1213 max_tokensinteger- Maximum tokens to generate. Example: 1024.
mem_clearinteger- 1 to delete all stored memories for mem_session now. Example: 1.one of
01 mem_sessionstring- Memory chain ID, to keep separate memories per user or app. Example: session-4471.
memoryboolean- Keep conversation context in APIpie's integrated memory. Example: true.
providerstring- Provider to route to. Omit to let APIpie pick the most responsive provider. Example: openai.
rag_tunestring- Name of a RAG tune or vector collection to augment the query with. Example: support-docs.
routingstring- How to route when no provider is set and several serve the model, for example perf or price. Example: perf.
search_blacklistarray- Root domains the search must not use. Example: ["example.com"]
search_providerstring- Enable internet search grounding with this provider. Defaults to valyu. Example: valyu.one of
valyugoogle search_whitelistarray- Root domains the search may use. Example: ["reuters.com", "apnews.com"]
temperaturenumber- Sampling temperature. Lower is more deterministic. Example: 0.7.
tool_choicestring- none, auto, or the name of a tool to force. Example: auto.
toolsarray- OpenAI-style function tool definitions the model may call. Example: [{"type": "function", "function": {"name": "get_weather", "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}}}]
top_pnumber- Nucleus sampling cutoff. Example: 0.9.
userstring- Your end-user identifier, for per-user usage and billing observability. Example: customer-123.
vector_providerstring- Vector store to use. Use the same provider for a collection every time. Example: qdrant.one of
pineconeqdrant
apipie_embeddings_createGenerate an embedding vector for a text with an embedding model.WriteCreate Embeddings
Generate an embedding vector for a text with an embedding model. Returns data with the embedding vector, the model and usage. Use apipie_vector_upsert to store it and apipie_vectors_query to search with it. Pick a model from apipie_models_list with type embedding.
Inputs
inputstringrequired- Text to embed. Example: How do I reset my password?.
modelstringrequired- Embedding model. Example: text-embedding-3-small.
dimensionsinteger- Embedding size, up to the model's limit. Example: 512.
encoding_formatstring- Output encoding, OpenAI models only. Example: float.one of
floatnp
apipie_image_generateGenerate an image from a text prompt with an image model (for example DALL-E, Flux or Stable Diffusion).WriteGenerate Image
Generate an image from a text prompt with an image model (for example DALL-E, Flux or Stable Diffusion). Returns data with the image URL or base64 JSON, depending on response_format. Pick a model from apipie_models_list with type image. Options such as seed, steps and aspect_ratio apply only to some models.
Inputs
promptstringrequired- Description of the image to generate. Example: A watercolor lighthouse at sunset.
aspect_ratiostring- Aspect ratio, where supported. The spec lists 9:21 and 21:9. Example: 21:9.one of
9:2121:9 imagestring- URL of an image for the model to edit (not DALL-E 3). Example: https://example.com/input.png.
modelstring- Image model. Example: dall-e-3.
qualitystring- Image quality, for example standard or hd. Example: standard.
response_formatstring- url or b64_json. Example: url.one of
urlb64_json seedinteger- Seed for reproducible output, where supported. Example: 42.
sizestring- Image size. Example: 1024x1024.
stepsinteger- Inference steps, where supported. Defaults to 30. Example: 30.
stylestring- vivid or natural, where supported. Example: vivid.
apipie_ragtune_document_addDownload a document (PDF, DOC, DOCX, TXT, CSV, XLS or XLSX) from a URL, extract its text and store embeddings in a RAG tune collection.WriteAdd RAG Tune Document
Download a document (PDF, DOC, DOCX, TXT, CSV, XLS or XLSX) from a URL, extract its text and store embeddings in a RAG tune collection. Returns the processing result. Then pass the collection name as rag_tune in apipie_chat_completion_create.
Inputs
collection_namestringrequired- Vector collection name. Example: support-docs.
urlstringrequired- Public URL of the document. Example: https://example.com/handbook.pdf.
metatagstring- Tag stored with the document. Example: handbook.
vector_providerstring- Vector store to use. Use the same provider for a collection every time. Example: qdrant.one of
pineconeqdrant
apipie_state_updateCreate or merge state settings for the app or one end user, or remove specific keys.WriteUpdate State Settings
Create or merge state settings for the app or one end user, or remove specific keys. Returns the updated state record. Settings merge into existing ones; list keys in delete to remove them. Use apipie_state_delete to remove the whole record.
- Idempotent
Inputs
app_namestring- App label for centralized state management. Example: supportbot.
deletearray- Setting keys to remove. Example: ["temperature"]
enable_inline_cliboolean- Allow inline CLI :commands in prompts. Example: true.
enable_user_statesboolean- true for per-user state (needs user), false for per-app state. Example: true.
gui_onlyboolean- Lock state so it can only be edited in the APIpie dashboard. Example: false.
settingsobject- Settings to merge, for example model, memory or search options. Example: {"model": "gpt-4o-mini", "memory": true}
userstring- End-user ID. Required when enable_user_states is true. Example: customer-123.
apipie_text_anonymizeDetect personal data (PII) in text with Microsoft Presidio and replace each entity with a short hash.WriteAnonymize Text
Detect personal data (PII) in text with Microsoft Presidio and replace each entity with a short hash. Returns the anonymized text and a mapping of the original values to their hashes. Use this before sending sensitive text to a model.
- Idempotent
Inputs
textstringrequired- Text that may contain personal data. Example: Call John Smith at 555-0100 or john@example.com.
apipie_vector_collection_createCreate a vector collection with a name and dimension.WriteCreate Vector Collection
Create a vector collection with a name and dimension. Returns the created collection. The dimension must match the embedding model you use with apipie_embeddings_create.
Inputs
collection_namestringrequired- Vector collection name. Example: support-docs.
dimensionintegerrequired- Vector dimension. Example: 1536.
vector_providerstring- Vector store to use. Use the same provider for a collection every time. Example: qdrant.one of
pineconeqdrant
apipie_vector_upsertInsert or update one vector in a collection with its source text and an optional tag.WriteUpsert Vector
Insert or update one vector in a collection with its source text and an optional tag. Returns the upsert result. Create the embedding with apipie_embeddings_create first.
- Idempotent
Inputs
collection_namestringrequired- Vector collection name. Example: support-docs.
embeddingarrayrequired- Embedding values. Example: [0.12, -0.03, 0.44]
vector_idstringrequired- ID for the vector; an existing ID is overwritten. Example: doc-42-chunk-3.
datastring- Source text stored with the vector. Example: To reset your password, open Settings > Security.
metatagstring- Tag for filtering. Example: faq.
apipie_ragtune_collection_deleteDelete a RAG tune collection, or specific records in it.DestructiveDelete RAG Tune Collection
Delete a RAG tune collection, or specific records in it. Returns the deletion result. Set delete_all true to remove the whole collection.
- Idempotent
Inputs
collection_namestringrequired- Vector collection name. Example: support-docs.
delete_allboolean- true to delete the entire collection. Example: true.
filterobject- Metadata filter selecting records to delete. Example: {"metatag": "handbook"}
idsarray- Record IDs to delete. Example: ["rec-1"]
apipie_state_deleteDelete the state record of one end user, or all state records of the app when user is omitted.DestructiveDelete State Settings
Delete the state record of one end user, or all state records of the app when user is omitted. Returns a confirmation. Use apipie_state_update with delete to remove single keys instead.
- Idempotent
Inputs
app_namestring- App label for centralized state management. Example: supportbot.
userstring- End-user ID; omit to delete all state for the app. Example: customer-123.
apipie_vectors_deleteDelete a whole vector collection, or specific vectors by ID or metadata filter.DestructiveDelete Vectors
Delete a whole vector collection, or specific vectors by ID or metadata filter. Returns the deletion result. Set delete_all true to remove the collection; otherwise send ids or filter.
- Idempotent
Inputs
collection_namestringrequired- Vector collection name. Example: support-docs.
delete_allboolean- true to delete the entire collection. Example: false.
filterobject- Metadata filter selecting vectors to delete. Example: {"metatag": "faq"}
idsarray- Vector IDs to delete. Example: ["doc-42-chunk-3"]
No tools match.