Feat/fireworks integration #2089
Conversation
Dockerfile.fireworks
Outdated
There was a problem hiding this comment.
I would say that the Docker file is useless in this case. It's a better idea if someone wants to use fireworks, make the necessary modifications.
There was a problem hiding this comment.
yes the docker file is only for running it even if the make modification docker file is usefull cause of dependency errors
python version mismatch etc
There was a problem hiding this comment.
I don't like this premise.
Adding another Docker/Docker-compose profile, will mean more code to maintain, when it is not the optimal PGPT user case. If fireworks was a fully local-setup environment, probably, it would be nice.
| - .env | ||
| profiles: | ||
| - fireworks |
There was a problem hiding this comment.
here i have used how other docker files and docker-compose are written
followed those template so that it won't be outsider :)
There was a problem hiding this comment.
I would say the same. It is not the core of PGPT, therefore, we should not give this kind of support. Our goal is to give a 100% private solution, in this area, our two main providers are Ollama and Llama-CPP. Of course, this PR gives more value to other people with the same problems, but it doesn't make sense to maintain on docker-compose and Dockerfile.
yeah i was searching for that to update , and for time being added those in docker and this above PR |
…t/fireworks-integration
|
Published docs preview URL: https://privategpt-preview-5bf4bf61-152c-4eb7-9161-558f9945cac5.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-e7446bbf-497c-4fae-8f49-04a334643c95.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-c593b77b-9a22-4f6e-8a67-ad2ca9d85a79.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-97eff913-b5ff-4f9a-9497-41795822260e.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-0527336e-de69-4607-a8d4-274a7b68979e.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-ccf44dde-a904-4cee-be33-502e65c9700c.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-fccc3c2f-9f7a-4256-8f1b-659f4ca0af72.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-0cffbf7e-3ac1-4b01-830b-493078a0e02a.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-42abb1f1-95a8-4f08-af7c-98298711fe4b.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-087aaa9d-2c65-4cd9-b6d6-01b00a7eca53.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-e9aea160-2fef-4b4b-b847-fbcee457b4e8.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-b0f06e4f-19be-4b17-856b-35e40f4e6690.docs.buildwithfern.com |
There was a problem hiding this comment.
Before that recommended setups, there are a couple tables with all available options.
poetry.lock
Outdated
There was a problem hiding this comment.
I'm not sure how the new dependencies are installed, but it bumps all dependencies. Please revert the current poetry.lock and update it using poetry lock --no-update. Many of the changes you have are related to bump versions. Probably, you will have to revert some formatting changes as well. Anyway, I will try to update Llama-index to the latest version, including all other dependencies. If you prefer to wait and merge it when it is ready, I can send you a ping.
There was a problem hiding this comment.
i had bumped it while i was having error when testing at github
will revert back to old version :)
|
Published docs preview URL: https://privategpt-preview-b9c8ffc1-9430-418e-a77d-86a567783c0b.docs.buildwithfern.com |
|
Published docs preview URL: https://privategpt-preview-69fd702c-a07a-47ff-82f5-6fd2fbeae5d9.docs.buildwithfern.com |
| - .env | ||
| profiles: | ||
| - fireworks |
There was a problem hiding this comment.
I would say the same. It is not the core of PGPT, therefore, we should not give this kind of support. Our goal is to give a 100% private solution, in this area, our two main providers are Ollama and Llama-CPP. Of course, this PR gives more value to other people with the same problems, but it doesn't make sense to maintain on docker-compose and Dockerfile.
|
context :I would say the same. It is not the core of PGPT, therefore, we should not give this kind of support. Our goal is to give a 100% private solution, in this area, our two main providers are Ollama and Llama-CPP. Of course, this PR gives more value to other people with the same problems, but it doesn't make sense to maintain on docker-compose and Dockerfile. REPLAY : docker file exist to make life easier |
|
Is this PR merge anytime soon? |
hope it does @jaluma any update? |
Totally right, Docker is the best way to run any project, including PGPT, but I'm not sure how much impact would have in PGPT community to have to keep a good maintain process. |
|
Published docs preview URL: https://privategpt-preview-fecc3d94-b751-4934-87b2-3a9560e8ad3b.docs.buildwithfern.com |
Description
issue : #1945
FEAT : added fireworks integration
used template used for openai
new dependencies :
llama-index-llms-fireworks = {version = "^0.1.5", optional = false}
llama-index-embeddings-fireworks = {version = "^0.1.2", optional = false}
HOW TO RUN :
install dependencies
poetry install --extras "ui llms-fireworks embeddings-fireworks vector-stores-qdrant embeddings-openai"set api key:
set FIREWORKS_API_KEY=YOUR_FIREWORKS_API_KEYset profile:
set PGPT_PROFILES=fireworksrun:
make runType of Change
Please delete options that are not relevant.
How Has This Been Tested?
Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration
Test Configuration:
Checklist: