Closed destrex271 closed 5 months ago
So here I have used the same approach that I utilized in LLMQueue, adding a starting point to interact with Ollama. This demo implementation will use the ollama_rs crate. This PR is to just start some work on the issue #85
We branched https://github.com/tembo-io/pg_vectorize/pull/103 off this (#88) PR branch and reduced scope to just chat completion. Closing this PR in favor of https://github.com/tembo-io/pg_vectorize/pull/103
So here I have used the same approach that I utilized in LLMQueue, adding a starting point to interact with Ollama. This demo implementation will use the ollama_rs crate. This PR is to just start some work on the issue #85