livekit-plugins-llama-index

[theomonnom]

[changeset-bot[bot]]

🦋 Changeset detected

Latest commit: 9285f2e8d9453eaf9172f2a24a3d542fec3682b4

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package

Name	Type
livekit-plugins-llama-index	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[theomonnom]

https://github.com/livekit/agents/issues/692

[ryanleecode]

the chat engine example is kind of busted because chat engine doesnt allow for concurrency. it's chat memory is shared for all connections.

[theomonnom]

the chat engine example is kind of busted because chat engine doesnt allow for concurrency. it's chat memory is shared for all connections.

Interesting, even if the chat_history is always set here (so using it instead of the internal memory?)

https://github.com/livekit/agents/pull/696/files#diff-c9c5aab8143dd7a1c7599a1791904401561e31b50f20b0dc4f836752c80541a2R64

[ryanleecode]

I think so because in their implementation its a shared memory buffer

https://github.com/run-llama/llama_index/blob/4e8d3d8cabfea5a2289c01fb9d435a50cdb8c360/llama-index-core/llama_index/core/chat_engine/condense_plus_context.py#L244

it can still work but you'd have to create a new chat engine per room

[theomonnom]

I think so because in their implementation its a shared memory buffer

https://github.com/run-llama/llama_index/blob/4e8d3d8cabfea5a2289c01fb9d435a50cdb8c360/llama-index-core/llama_index/core/chat_engine/condense_plus_context.py#L244

it can still work but you'd have to create a new chat engine per room

Oh, creating a new ChatEngine per room/job is actually the way I was implementing it. Can you give me more details about what you're doing? Is the MemoryBuffer saved somewhere?