You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@camel.apache.org by al...@apache.org on 2024/10/08 14:48:58 UTC
(camel-quarkus-examples) 01/02: data-extract: switch to ollama container maintained version
This is an automated email from the ASF dual-hosted git repository.
aldettinger pushed a commit to branch camel-quarkus-main
in repository https://gitbox.apache.org/repos/asf/camel-quarkus-examples.git
commit b8f1ec3bf824a0262151a5a178bd3e5ad33e2168
Author: aldettinger <al...@gmail.com>
AuthorDate: Tue Oct 8 14:56:02 2024 +0200
data-extract: switch to ollama container maintained version
---
data-extract-langchain4j/README.adoc | 25 ++++++++++++++++++++++---
1 file changed, 22 insertions(+), 3 deletions(-)
diff --git a/data-extract-langchain4j/README.adoc b/data-extract-langchain4j/README.adoc
index 3970d36..00ea497 100644
--- a/data-extract-langchain4j/README.adoc
+++ b/data-extract-langchain4j/README.adoc
@@ -22,21 +22,40 @@ Finally, we'll invoke the AiService extraction method via the https://camel.apac
=== Start the Large Language Model
-Let's start a container to serve the LLM with Ollama:
+Let's start a container to serve the LLM with Ollama, in a first shell type:
[source,shell]
----
-docker run -p11434:11434 langchain4j/ollama-codellama:latest
+docker run --rm -it -v cqex-data-extract-ollama:/root/.ollama -p 11434:11434 --name cqex-data-extract-ollama ollama/ollama:0.3.12
----
After a moment, a log like below should be output:
[source,shell]
----
-time=2024-09-03T08:03:15.532Z level=INFO source=types.go:98 msg="inference compute" id=0 library=cpu compute="" driver=0.0 name="" total="62.5 GiB" available="54.4 GiB"
+time=2024-10-08T12:43:43.329Z level=INFO source=types.go:107 msg="inference compute" id=0 library=cpu variant=avx2 compute="" driver=0.0 name="" total="62.5 GiB" available="52.4 GiB"
+----
+
+Then, download the codellama model, in a second shell type:
+
+[source,shell]
+----
+docker exec -it cqex-data-extract-ollama ollama pull codellama
+----
+
+After a moment, log like below should be output:
+
+[source,shell]
+----
+pulling manifest
+...
+verifying sha256 digest
+writing manifest
+success
----
That's it, the LLM is now ready to serve our data extraction requests.
+The second shell could be reused, however the first one need to stay up while running this example.
=== Package and run the application