Superduper allows users to work with anthropic API models. The key integration is the integration of high-quality API-hosted LLM services.
Verified details
These details have been verified by PyPIProject links
GitHub Statistics
Maintainers
Project description
superduper_anthropic
Superduper allows users to work with anthropic API models. The key integration is the integration of high-quality API-hosted LLM services.
Installation
pip install superduper_anthropic
API
| Class | Description |
|---|---|
superduper_anthropic.model.Anthropic |
Anthropic predictor. |
superduper_anthropic.model.AnthropicCompletions |
Cohere completions (chat) predictor. |
Examples
AnthropicCompletions
from superduper_anthropic.model import AnthropicCompletions
model = AnthropicCompletions(
identifier="claude-2.1",
predict_kwargs={"max_tokens": 64},
)
model.predict_batches(["Hello, world!"])
Project details
Verified details
These details have been verified by PyPIProject links
GitHub Statistics
Maintainers
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file superduper_anthropic-0.4.0.tar.gz.
File metadata
- Download URL: superduper_anthropic-0.4.0.tar.gz
- Upload date:
- Size: 12.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 16de41d279e54cb2fa08c80a52311158eabf284611502553609decab4c69884a |
|
| MD5 | f251d21cd6a115fc6799a29d18649e8a |
|
| BLAKE2b-256 | 83fc1b74c84db0908ac86bc8a9835f96b1e663806646cd1146e143794f80a145 |
Provenance
The following attestation bundles were made for superduper_anthropic-0.4.0.tar.gz:
Publisher:
release_plugins.yaml on superduper-io/superduper
-
Statement type:
https://in-toto.io/Statement/v1- Predicate type:
https://docs.pypi.org/attestations/publish/v1 - Subject name:
superduper_anthropic-0.4.0.tar.gz - Subject digest:
16de41d279e54cb2fa08c80a52311158eabf284611502553609decab4c69884a - Sigstore transparency entry: 146081635
- Sigstore integration time:
- Predicate type:
File details
Details for the file superduper_anthropic-0.4.0-py3-none-any.whl.
File metadata
- Download URL: superduper_anthropic-0.4.0-py3-none-any.whl
- Upload date:
- Size: 11.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 02ba890295c653d0d0b242ac83d20e09aa622f5c437aa7fd33e0863c25285725 |
|
| MD5 | 9994edff82a7d588c4f2189dd7fd9ceb |
|
| BLAKE2b-256 | e3b08ec9edf492d4f4d040c408aaa1908725a7b36abe15e300960415c119aec5 |
Provenance
The following attestation bundles were made for superduper_anthropic-0.4.0-py3-none-any.whl:
Publisher:
release_plugins.yaml on superduper-io/superduper
-
Statement type:
https://in-toto.io/Statement/v1- Predicate type:
https://docs.pypi.org/attestations/publish/v1 - Subject name:
superduper_anthropic-0.4.0-py3-none-any.whl - Subject digest:
02ba890295c653d0d0b242ac83d20e09aa622f5c437aa7fd33e0863c25285725 - Sigstore transparency entry: 146081637
- Sigstore integration time:
- Predicate type:
