llm_memory 0.1.2 → 0.1.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 0615d07f9e76aa0b4c762d027e757bb0cb03cc1448b11d5b5cf684d5a75b381a
-  data.tar.gz: 6aa24ea5ddf2476876ca2d873400018785c3bcc6c385faf35cac3f59de94049a
+  metadata.gz: 85f3330ed767cc28b5a3276a7772678c36726ce04562c184a4e6dcf287d14d1d
+  data.tar.gz: 3e1ae83b2517f7f80bb857de5024b62b886bb6a045428f2d40159e48818cf286
 SHA512:
-  metadata.gz: 7f6ac569b18f28502e3b0e34614498b559dff4b6e085988f3bae2f5160aef9eb6491a7e61f78edc3d5e0c9be0ac8878f4e0747cc2d02358aa389071eea393c0c
-  data.tar.gz: b818a177d945d9e2544f1079f214231d792419772688b4907a50a8ceb2fde2435d5571e4e03307fa1bee8f8d22499e7ddf5821363203b1a1ecbd473d4edbdc2d
+  metadata.gz: dba158d07c4a97a5b2e6bb1a98987173ba427a18a1a06d0a422f366ab2f7335ac168aea0351657b0c7f957352e6ffe747a2d817deb7c8d5454010c2ec535999a
+  data.tar.gz: 1db3ccb501f3b56d6e6dc00997f3f085b74f395521ffbbc1775bc5799bc388410523f6f209cfc185efbbf1437177c07dd5ee1725a49f6a27b207c6fc296067aa

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    llm_memory (0.1.2)
+    llm_memory (0.1.3)
       redis (~> 4.6.0)
       ruby-openai (~> 3.7.0)
       tiktoken_ruby (~> 0.0.4)

data/README.md

@@ -85,7 +85,7 @@ related_docs = hippocampus.query(query_str, limit: 3)
 #},,,]
 
 # ERB
-template = <<-TEMPLATE
+prompt = <<-TEMPLATE
 Context information is below.
 ---------------------
 <% related_docs.each do |doc| %>
@@ -98,7 +98,7 @@ Given the context information and not prior knowledge,
 answer the question: <%= query_str %>
 TEMPLATE
 
-broca = LlmMemory::Broca.new(prompt: tempate, model: 'gpt-3.5-turbo')
+broca = LlmMemory::Broca.new(prompt: prompt, model: 'gpt-3.5-turbo')
 messages = broca.respond(query_str: query_str, related_docs: related_docs)
 
 ...

data/lib/llm_memory/broca.rb

@@ -20,26 +20,31 @@ module LlmMemory
       @max_token = max_token
     end
 
-    def respond(*args)
-      final_prompt = generate_prompt(*args)
+    def respond(args)
+      final_prompt = generate_prompt(args)
       @messages.push({role: "user", content: final_prompt})
       adjust_token_count
-      response = client.chat(
-        parameters: {
-          model: @model,
-          messages: @messages,
-          temperature: @temperature
-        }
-      )
-      response_conent = response.dig("choices", 0, "message", "content")
-      @messages.push({role: "system", content: response_conent})
-      response_conent
+      begin
+        response = client.chat(
+          parameters: {
+            model: @model,
+            messages: @messages,
+            temperature: @temperature
+          }
+        )
+        response_content = response.dig("choices", 0, "message", "content")
+        @messages.push({role: "system", content: response_content})
+        response_content
+      rescue => e
+        puts e.inspect
+        # @messages = []
+        nil
+      end
     end
 
-    def generate_prompt(*args)
-      merged_args = args.reduce(:merge)
+    def generate_prompt(args)
       erb = ERB.new(@prompt)
-      erb.result_with_hash(merged_args)
+      erb.result_with_hash(args)
     end
 
     def adjust_token_count

data/lib/llm_memory/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module LlmMemory
-  VERSION = "0.1.2"
+  VERSION = "0.1.3"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: llm_memory
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Shohei Kameda
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2023-05-09 00:00:00.000000000 Z
+date: 2023-05-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: tiktoken_ruby