cohere-compass-sdk
Cohere Compass SDK
Decision gist · record as of 2026-08-14
Yes, if you have a hosted Compass server and need to parse and index documents programmatically. The SDK has low install friction, active maintenance, and no known vulnerabilities. The main blocker is the external dependency on a running Compass server—without it, the SDK cannot function. License status is unclear, so verify licensing terms before production use.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- A hosted Compass server must be running and accessible at the provided index_url
- Low friction installation with five stable runtime dependencies.
- Package is actively maintained with a recent release.
License · maintenance · safety
(unclear)
last release 2026-08-12 (2 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 182,453 downloads/mo, #10,097 on PyPI
Alternatives
Verify before relying
pip install cohere-compass-sdk
from cohere_compass_sdk import CompassClient
client = CompassClient(index_url=api_url, bearer_token=bearer_token)
client.create_index(...)- Whether a hosted Compass server is required before the SDK can be used in any capacity
- Whether authentication credentials (bearer token) are mandatory or optional for basic operations
- Performance characteristics when parsing large files or batches across different file systems
What it is and what it does
The Cohere Compass SDK is a Python client library for interacting with Compass, a document indexing and search system. It provides two main components: a CompassParserClient that sends files to a remote Compass Parser API for parsing (supporting pdf, docx, json, csv and other formats from local, S3, GCS and other file systems), and a CompassClient that manages documents in a Compass index via a RESTful API—allowing you to create, delete, and search indexed documents.
The SDK requires a hosted Compass server to function and uses httpx for HTTP communication, pydantic for data validation, tenacity for retry logic, fsspec for multi-filesystem support, and joblib for batch processing. It supports Python 3.11 and later, with both synchronous and asynchronous client variants available.
Use it for
- Parse a batch of PDF and DOCX files from S3 and insert them into a Compass index for full-text search
- Build a document ingestion pipeline that reads from local folders, parses multiple file types, and indexes results
- Create a search application that queries indexed documents through the CompassClient API
- Automate document processing workflows that handle different file systems (local, GCS, S3) transparently
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you have a hosted Compass server and need to parse and index documents programmatically.
The SDK has low install friction, active maintenance, and no known vulnerabilities. The main blocker is the external dependency on a running Compass server—without it, the SDK cannot function. License status is unclear, so verify licensing terms before production use.
Install
cohere-compass-sdk on PyPI
Before you install
Low friction installation with five stable runtime dependencies. Package is actively maintained with a recent release.
A hosted Compass server must be running and accessible at the provided index_url
Quickstart
pip install cohere-compass-sdk
from cohere_compass_sdk import CompassClient
client = CompassClient(index_url=api_url, bearer_token=bearer_token)
client.create_index(...)Verify before relying
- Whether a hosted Compass server is required before the SDK can be used in any capacity
- Whether authentication credentials (bearer token) are mandatory or optional for basic operations
- Performance characteristics when parsing large files or batches across different file systems
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <4.0,>=3.11 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagesfsspecjoblibpydantictenacityhttpx |
| Maintenance | Actively maintained 2 days since the last release |
| First released | |
| Downloads | 182,453 / month, #10,097 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3Programming Language :: Python :: 3.11 |
Evidence: cohere_compass_sdk-2.16.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “compass index management”
- cohere-compass-sdkParse documents via a remote Compass Parser API and manage indexed…
- pyScssCompiles Sass/SCSS stylesheets to CSS, supporting approximately 95%…
- elasticsearch-curatorManages Elasticsearch indices and snapshots through automated actions…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also opentelemetry-instrumentation-cohere · cohere · azure-search-documents · langchain-cohere · unstructured-client · cohere-melody · icalevents · pysolr · beanie · pyScss