From 0185d620eb5e5cbc7acf8098e3f29a390ff9fa6d Mon Sep 17 00:00:00 2001 From: Aidan Do Date: Fri, 6 Dec 2024 17:34:56 +1100 Subject: [PATCH 1/4] doc: typo in chat-completion command --- docs/source/getting_started/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/getting_started/index.md b/docs/source/getting_started/index.md index e6365208f5..a71660fff8 100644 --- a/docs/source/getting_started/index.md +++ b/docs/source/getting_started/index.md @@ -62,7 +62,7 @@ llama-stack-client --endpoint http://localhost:$LLAMA_STACK_PORT models list You can test basic Llama inference completion using the CLI too. ```bash llama-stack-client --endpoint http://localhost:$LLAMA_STACK_PORT \ - inference chat_completion \ + inference chat-completion \ --message "hello, what model are you?" ``` From a2fc114b646d6693ac211481acfa03ceee682d8d Mon Sep 17 00:00:00 2001 From: Aidan Do Date: Fri, 6 Dec 2024 08:19:58 +0000 Subject: [PATCH 2/4] enable session persistence --- docs/source/getting_started/index.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/source/getting_started/index.md b/docs/source/getting_started/index.md index a71660fff8..6a18972b1d 100644 --- a/docs/source/getting_started/index.md +++ b/docs/source/getting_started/index.md @@ -62,7 +62,7 @@ llama-stack-client --endpoint http://localhost:$LLAMA_STACK_PORT models list You can test basic Llama inference completion using the CLI too. ```bash llama-stack-client --endpoint http://localhost:$LLAMA_STACK_PORT \ - inference chat-completion \ + inference chat_completion \ --message "hello, what model are you?" ``` @@ -118,6 +118,7 @@ async def run_main(): model=os.environ["INFERENCE_MODEL"], instructions="You are a helpful assistant", tools=[{"type": "memory"}], # enable Memory aka RAG + enable_session_persistence=True, ) agent = Agent(client, agent_config) From 98ab8f2d05bc6327109dbcd0eb3caa32b2b6279f Mon Sep 17 00:00:00 2001 From: Aidan Do Date: Fri, 6 Dec 2024 17:34:56 +1100 Subject: [PATCH 3/4] doc: typo in chat-completion command --- docs/source/getting_started/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/getting_started/index.md b/docs/source/getting_started/index.md index 6a18972b1d..e34aa01de0 100644 --- a/docs/source/getting_started/index.md +++ b/docs/source/getting_started/index.md @@ -62,7 +62,7 @@ llama-stack-client --endpoint http://localhost:$LLAMA_STACK_PORT models list You can test basic Llama inference completion using the CLI too. ```bash llama-stack-client --endpoint http://localhost:$LLAMA_STACK_PORT \ - inference chat_completion \ + inference chat-completion \ --message "hello, what model are you?" ``` From eaf4392fe934fe9978d43ecc24b1282219755310 Mon Sep 17 00:00:00 2001 From: Aidan Do Date: Fri, 6 Dec 2024 08:24:20 +0000 Subject: [PATCH 4/4] async --- docs/source/getting_started/index.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/getting_started/index.md b/docs/source/getting_started/index.md index e34aa01de0..bae31e8c49 100644 --- a/docs/source/getting_started/index.md +++ b/docs/source/getting_started/index.md @@ -140,7 +140,7 @@ async def run_main(): attachments=attachments, session_id=session_id, ) - async for log in EventLogger().log(response): + for log in EventLogger().log(response): log.print()