OpenInference Cohere Instrumentation
Python auto-instrumentation library for the Cohere Python client.
Chat and embedding calls made with the Cohere v2 client (ClientV2 and AsyncClientV2)
are traced and exported as OpenInference spans. Chat spans capture messages, invocation
parameters, tool calls, and token counts. Embedding spans capture the model name, input text,
invocation parameters, vectors, and token counts.
Coverage
ClientV2.chat, AsyncClientV2.chat, ClientV2.chat_stream,
AsyncClientV2.chat_stream, ClientV2.embed, and AsyncClientV2.embed are instrumented.
Streamed calls finish their span when the returned iterator is exhausted, with the accumulated
output message, tool calls, and token counts.
The following are not traced, and calls to them produce no spans:
- The v1 client (
cohere.Client) - Rerank and classify endpoints
Installation
pip install openinference-instrumentation-cohere
PyPI package: openinference-instrumentation-cohere
Quickstart
Install packages needed for this demonstration.
pip install openinference-instrumentation-cohere cohere arize-phoenix opentelemetry-sdk opentelemetry-exporter-otlp
Start Phoenix in the background as a collector. By default, it listens on http://localhost:6006.
phoenix serve
Set up CohereInstrumentor to trace your application and send the traces to Phoenix.
from openinference.instrumentation.cohere import CohereInstrumentor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
endpoint = "http://127.0.0.1:6006/v1/traces"
tracer_provider = TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
CohereInstrumentor().instrument(tracer_provider=tracer_provider)
Run a chat request. Set the CO_API_KEY environment variable with your Cohere API key.
import cohere
co = cohere.ClientV2()
response = co.chat(
model="command-a-03-2025",
messages=[{"role": "user", "content": "Why is the sky blue?"}],
)
print(response.message.content[0].text)
More Info
Metadata
Release files for openinference-instrumentation-cohere 0.1.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| openinference_instrumentation_cohere-0.1.3.tar.gz | 14.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| openinference_instrumentation_cohere-0.1.3-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 34.4 kB
Release files / openinference_instrumentation_cohere-0.1.3.tar.gz
| Download URL | openinference_instrumentation_cohere-0.1.3.tar.gz |
|---|---|
| Size | 14.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
839f101d812a9e4be12297581aad43c1ba41e346d44370faf35ac8505f1b7522
|
|
BLAKE2b-256 checksum How to use checksums |
9f8927152dd46d0998660fd467e724221cba4f69253a0fb0926f83c29f3672f7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 12, 2026.
Transparency logRelease files / openinference_instrumentation_cohere-0.1.3-py3-none-any.whl
| Download URL | openinference_instrumentation_cohere-0.1.3-py3-none-any.whl |
|---|---|
| Size | 19.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
dae0594f27ab6957088db280c6ed5f6eb1a3fe1392412ed6cbc7d6fe0fe415a5
|
|
BLAKE2b-256 checksum How to use checksums |
2e25f6b82de38d594e7e25b0057af977f4713a292affcf87b6fb89b29b3443d6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Aug 12, 2026.
Transparency log