mirrors / memvid--memvid

项目文件夹

memvid--memvid
文件
v0.1.3
T
文件历史
saleban olow 644607c27e Add Docker support, multi-LLM providers, and enhanced codec configuration
2025-06-05 10:50:57 -05:00
..
__pycache__
Add Docker support, multi-LLM providers, and enhanced codec configuration
2025-06-05 10:50:57 -05:00
__init__.py
Updated the init to work with the LLM client
2025-05-30 17:26:56 -07:00
chat.py
Reworked chat.py and added a new llm_client.py file to allow for the use of multiple different LLM endpoints. The configs have also been expanded to accomodate this. In addition, global configs have been added or moved for chunking and overlap, output file type, and video encoding/compression settings.
2025-05-30 17:10:39 -07:00
config.py
Updated the LLM client to use the actual models defined in config, cleaned up the debugging output, optimized the configs a bit and confirmed decoding is still viable at the decreased resolution.
2025-06-02 20:11:50 -07:00
docker_manager.py
Reworked the dockerization to all work from the base encoder. Many things are still hard-coded where they shouldn't be, but everything except AV1 is still massively blown up, and AV1 takes absolute ages (15 minutes for a single file). Next steps will be figuring out why h264/5 are still so bloated, but they all run now.
2025-06-01 22:24:51 -07:00
encoder.py
Updated the LLM client to use the actual models defined in config, cleaned up the debugging output, optimized the configs a bit and confirmed decoding is still viable at the decreased resolution.
2025-06-02 20:11:50 -07:00
index.py
Updated the LLM client to use the actual models defined in config, cleaned up the debugging output, optimized the configs a bit and confirmed decoding is still viable at the decreased resolution.
2025-06-02 20:11:50 -07:00
interactive.py
Harmonized everything with the new configs, fixed a few issues or inconsistencies. There are still some significant issues related to getting encoding to work the same way in docker and natively. Right now there's a lot of repetition, poor seperation of concerns, etc. because of the new docker way of doing things.
2025-05-31 20:31:04 -07:00
llm_client.py
Updated the LLM client to use the actual models defined in config, cleaned up the debugging output, optimized the configs a bit and confirmed decoding is still viable at the decreased resolution.
2025-06-02 20:11:50 -07:00
retriever.py
clean up 1
2025-05-27 11:02:35 -05:00
utils.py
Reworked the dockerization to all work from the base encoder. Many things are still hard-coded where they shouldn't be, but everything except AV1 is still massively blown up, and AV1 takes absolute ages (15 minutes for a single file). Next steps will be figuring out why h264/5 are still so bloated, but they all run now.
2025-06-01 22:24:51 -07:00