Inference Logoinference.sh
apps/infsh/harrier-oss-v1

harrier-oss-v1

Multilingual text embedding using Microsoft's Harrier OSS v1 models. Supports retrieval, clustering, semantic similarity, classification, and reranking with state-of-the-art MTEB v2 scores.

run in browser run via API
run with your agent
# install belt
$curl -fsSL https://cli.inference.sh | sh
# view schema & details
$belt app get infsh/harrier-oss-v1
# run
$belt app run infsh/harrier-oss-v1

api reference

about

multilingual text embedding using microsoft's harrier oss v1 models. supports retrieval, clustering, semantic similarity, classification, and reranking with state-of-the-art mteb v2 scores.

1. calling the api

install the client

the client provides a convenient way to interact with the api.

bash
1pip install inferencesh

setup your api key

set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.

bash
1export INFERENCE_API_KEY="inf_your_key"

run and get result

submit a request and wait for the final result. best for batch processing or when you don't need progress updates.

python
1from inferencesh import inference23client = inference()456result = client.run({7        "app": "infsh/harrier-oss-v1",8        "input": {}9    })1011print(result["output"])

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.

python
1from inferencesh import inference23client = inference()456# stream=True yields updates as they arrive7for update in client.run({8        "app": "infsh/harrier-oss-v1",9        "input": {}10    }, stream=True):11    if update.get("progress"):12        print(f"progress: {update['progress']}%")13    if update.get("output"):14        print(f"output: {update['output']}")

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.

python
1# local file paths are automatically uploaded2result = client.run({3    "app": "infsh/harrier-oss-v1",4    "input": {5        "image": "/path/to/local/image.png",  # detected & uploaded6        "audio": "https://example.com/audio.mp3",  # url passed through7    }8})

manual upload

you can also upload files manually and use the returned url.

python
1# upload and get a hosted URL2file = client.files.upload("/path/to/file.png")3print(file.uri)  # https://cloud.inference.sh/...

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

python
1result = client.run({2    "app": "infsh/harrier-oss-v1",3    "input": {},4    "webhook": "https://your-server.com/webhook"5}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json
1{2  "id": "task_abc123",3  "status": 9,4  "output": { ... },5  "error": "",6  "session_id": null,7  "created_at": "2024-01-15T10:30:00Z",8  "updated_at": "2024-01-15T10:30:05Z"9}
idstring— task id
statusnumber— terminal status (9=completed, 10=failed, 11=cancelled)
outputobject— task output (when completed)
errorstring— error message (when failed)
session_idstring— session id (if using sessions)
created_atstring— iso timestamp
updated_atstring— iso timestamp

5. schema

input

textsarray

texts to embed (one embedding per text).

filesarray

files containing texts to embed. supports .txt (one text per line), .jsonl (one json string per line), or .json (array of strings).

instructionstring

task instruction for queries (e.g. 'given a web search query, retrieve relevant passages that answer the query'). only needed for query-side encoding, not for documents.

prompt_namestring

pre-configured prompt name (e.g. 'web_search_query', 'sts_query', 'bitext_query'). alternative to providing a custom instruction.

chunk_strategystring

chunking strategy. 'fixed': split by token count. 'recursive': split at paragraph/sentence/word boundaries within token budget. none: no chunking.

options:"fixed""recursive"
chunk_sizeinteger

target chunk size in tokens. clamped to model max (32768). only used when chunk_strategy is set.

default: 512
chunk_overlapinteger

overlap between chunks in tokens. only used when chunk_strategy is set.

default: 50

output

countinteger*

total number of embeddings across all files

dimensioninteger*

embedding dimension

embeddingsarray

json files containing embeddings, one per input text

inline_embeddingsarray

inline embeddings when output is small enough to skip file upload

setup

setup parameters are provided once via the setup field and are persisted for a session.

model_idstring

model variant: 270m (640d), 0.6b (1024d), or 27b (5376d)

default: "microsoft/harrier-oss-v1-0.6b"
options:"microsoft/harrier-oss-v1-270m""microsoft/harrier-oss-v1-0.6b""microsoft/harrier-oss-v1-27b"

ready to run harrier-oss-v1?

try in browserbrowse all tools

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.