TLDR
The simplest way to run: using uvx (you need to pip install uv first):
For local model (will install torch and transformers, can be slow):
uvx --from 'photoprism_captioner[local]' photoprism_captioner --backend local --auth-token MY_PHOTOPRISM_AUTH_TOKEN --model Salesforce/blip-image-captioning-large --photoprism-url="https://my.photoprism.qwe.org"
For Ollama model (self-hosted LLM models provider):
uvx --from 'photoprism_captioner[remote]' photoprism_captioner --backend remote --auth-token MY_PHOTOPRISM_AUTH_TOKEN --model ollama/gemma3 --api-base http://my-ollama-instance:11434 --photoprism-url="https://my.photoprism.qwe.org"
For OpenAI model (Don't forget to set OPENAI_API_KEY environment variable):
uvx --from 'photoprism_captioner[remote]' photoprism_captioner --backend remote --auth-token MY_PHOTOPRISM_AUTH_TOKEN --model gpt-4o-2024-08-06 --api-base https://api.openai.com/v1/chat/completions --photoprism-url="https://my.photoprism.qwe.org"
1 maintainer
Metadata
1 maintainer
Release files for photoprism-captioner 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 | Provenance | Actions |
|---|---|---|---|---|
| photoprism_captioner-0.1.3.tar.gz | 6.0 kB | Without provenance | Details for photoprism_captioner-0.1.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| photoprism_captioner-0.1.3-py3-none-any.whl | Python 3 | none | any | Details for photoprism_captioner-0.1.3-py3-none-any.whl |
Total release size: 13.0 kB
Release files / photoprism_captioner-0.1.3.tar.gz
| Download URL | photoprism_captioner-0.1.3.tar.gz |
|---|---|
| Size | 6.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
70f3cb111e228e10fa71be952103e2a8ef1123d642f6fcc49391ab37d5c4ba55
|
|
BLAKE2b-256 checksum How to use checksums |
30d9382a2dc4e4cb3cd3bf0b6f800217b672d83ec6adbb955e5b21a16581f1c2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.5.27
|
Release files / photoprism_captioner-0.1.3-py3-none-any.whl
| Download URL | photoprism_captioner-0.1.3-py3-none-any.whl |
|---|---|
| Size | 7.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
801613bba3bb7331b213cda0db98304389d677ba9495a769818afecf1fb6c7a3
|
|
BLAKE2b-256 checksum How to use checksums |
601783e80dd1b2263902dde48b2a6e272c7ec5b66781930880a7bad3b9572df1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.5.27
|
Security for photoprism-captioner 0.1.3
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
