Ollama - Remote hosts #8234
Ollama - Remote hosts #8234
Conversation
Fried-Squid
requested review from
Torantulino and
kcze
and removed request for
a team
|
|
github-actions
bot
added
platform/backend
PR Reviewer Guide 🔍Here are some key observations to aid the review process:
|
✅ Deploy Preview for auto-gpt-docs canceled.
|
|
This is a super nice change and its much needed 🙏 once CI tests pass it should be good to go! |
|
CI/CD all passing now 😄 |
github-actions
bot
added
the
conflicts
|
This pull request has conflicts with the base branch, please resolve those so we can evaluate the pull request. |
|
@Fried-Squid can i get that cla signed so we can work towards merging this |
|
Hey, not sure why but the CLA has pulled the wrong emails, those are my old
work credentials and I no longer work there, is there an easy way to fix
this? Have signed it on my main one
…On Thu, 10 Oct 2024, 17:41 Nicholas Tindle, ***@***.***> wrote:
@Fried-Squid <https://github.com/Fried-Squid> can i get that cla signed
so we can work towards merging this
—
Reply to this email directly, view it on GitHub
<#8234 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AMALLRQLXAALRVIJW5JGFMTZ22U5DAVCNFSM6AAAAABPEHQZB2VHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDIMBVGU4DQNRRGE>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
|
Somewhere you’re developing probably has an old git config that contains those emails as a default. Ex GitHub.com uses one of those when you update from master or your dev machine has its git config email set to an old email. You can reopen the PR with the correct emails after fixing locally or maybe try force pushing over but I’m not positive that force pushing to your branch will work |
Fried-Squid
force-pushed
the
ollama_remote
branch
from
25df9d6
to
cc7fe12
Compare
github-actions
bot
added
platform/frontend
Add AIListGeneratorBlock class
…cant-Gravitas#8219) Refactor iteration block to support iterating over dictionaries and to return individual list items.
…ebsiteContentBlock (Significant-Gravitas#8228) Refactor search.py: Add option for raw content scraping in ExtractWebsiteContentBlock
Automatically apply the `platform/blocks` label to PRs that change files in `backend/blocks/`
…vitas#8238) add prod values and clean up infra
…wnload agent button (Significant-Gravitas#8196) * feat(frontend): push to cloud if needed for marketplace * fix(market): missing envar in the example 😠 * feat(frontend): download button functions * feat(frontend): styling and linting * feat(frontend): move to popup * feat(frontend): style fixes and link replacement * feat(infra): add variables * fix(frontend): merge * fix(frontend): linting * feat(frontend): pr changes * Update NavBar.tsx * fix(frontend): linting --------- Co-authored-by: Zamil Majdy <[email protected]> Co-authored-by: Aarushi <[email protected]>
Fried-Squid
force-pushed
the
ollama_remote
branch
from
cc7fe12
to
651f3b5
Compare
|
@ntindle Sorted it out, for future reference you can just rebase the commits with --reset-author and force push over 😄 |
|
Hi, |
|
Go ahead and use this branch as usual, I'll try and keep it up to date until merge |
|
@Fried-Squid I get a:
my ollama host and port seem right, the hostname is resoved and the ollama API can be reached everywhere in my network via:
(autogpt is the hostname) Any ideas? |
|
Could be an issue with your networking - how are you running AutoGPT? Can you also try with IP over host, could be DNS... |
…es/deployment.yaml
Background
Currently, AutoGPT only supports ollama servers running locally. Often, this is not the case as the ollama server could be running on a more suited instance, such as a Jetson board. This PR adds "ollama host" to the input of all LLM blocks, allowing users to select the ollama host for the LLM blocks.
Changes 🏗️
Testing 🔍
Tested all LLM blocks with Ollama remote hosts as well as with the default localhost value.
Related issues
#8225