Address review comments.

Signed-off-by: Austin Lee <austin@aryn.ai>
opensearch-project · Oct 11, 2023 · a598e5e · a598e5e
1 parent bdebe65
commit a598e5e
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 0 deletions.
diff --git a/search-processors/README.md b/search-processors/README.md
@@ -51,6 +51,8 @@ GET /<index>/_search\?search_pipeline\=<search pipeline name>
 
 To use this with Bedrock models, use "bedrock/" as a prefix for the "llm_model" parameters, e.g. "bedrock/anthropic".
 
+The latest RAG processor has been tested with OpenAI's GPT 3.5 and 4 models and Bedrock's Anthropic Claude (v2) model only.
+
 ## Retrieval Augmented Generation response
 ```
 {

diff --git a/...rs/src/main/java/org/opensearch/searchpipelines/questionanswering/generative/llm/Llm.java b/...rs/src/main/java/org/opensearch/searchpipelines/questionanswering/generative/llm/Llm.java
@@ -22,6 +22,7 @@
  */
 public interface Llm {
 
+    // TODO Ensure the current implementation works with all models supported by Bedrock.
     enum ModelProvider {
         OPENAI,
         BEDROCK
-Original file line number
+Diff line change
@@ Expand Up / @@ -51,6 +51,8 @@ GET /<index>/_search\?search_pipeline\=<search pipeline name> @@
     To use this with Bedrock models, use "bedrock/" as a prefix for the "llm_model" parameters, e.g. "bedrock/anthropic".
+    The latest RAG processor has been tested with OpenAI's GPT 3.5 and 4 models and Bedrock's Anthropic Claude (v2) model only.
     ## Retrieval Augmented Generation response
     ```
     {
@@ Expand Down @@