langchainrb 0.13.3 → 0.13.4

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d39fd55aeaa36e9d2a0009dac4808743d97941bd139bc9373eafb153cfb7854e
-  data.tar.gz: ddf8757341169f2e38bb076a9dfb5f5328a0de4e01ce58ec5b3263fdd3c47105
+  metadata.gz: 7877086b6c4d0bba6c1fc4cafc156ff476ad83eb30df1a39b279885b224bf35d
+  data.tar.gz: 3a22b060896725308c5ce137ee5617a44a75355cfc7878ce6080e6b200722c51
 SHA512:
-  metadata.gz: 243d774a05c2d5bfa27c8f98f51adac3ff13252cb108de085d8ac21b65977b8e8c7f9b78f4a58872b2a299c1e615b9fa6852cf27b564b567f6fa3d15dea2cf26
-  data.tar.gz: 6665f726069148c0adc24947d570b67d2f56f00ad5ffeeb6653fe745401f14768b324c67711cdaf023e782a3fa61c2787050ed2087db6ca34410a65a5e02a8ec
+  metadata.gz: 05606b99693c0e81f3785a027e155205a3ffce8f4f236868395de837e2bc6f71661c39f6a2cc062e3c0a57a6c8295e13b6910df296a9092f2f7d0596e1c969b0
+  data.tar.gz: 00d478f82be9984a95a1d11676982dec79dea2a6c0bf92ceb1ab0e3309edac2ecee115a3dd46ca060f040e44d9b7c8623ffd27ba1d5fcd8182832f933eaf2815

data/CHANGELOG.md

@@ -1,5 +1,10 @@
 ## [Unreleased]
 
+## [0.13.4] - 2024-06-16
+- Fix Chroma#remove_texts() method
+- Fix NewsRetriever Tool returning non UTF-8 characters
+- Misc fixes and improvements
+
 ## [0.13.3] - 2024-06-03
 - New 🛠️  `Langchain::Tool::Tavily` to execute search (better than the GoogleSearch tool)
 - Remove `activesupport` dependency

data/README.md

@@ -57,7 +57,7 @@ Langchain.rb wraps supported LLMs in a unified interface allowing you to easily
 #### Supported LLMs and features:
 | LLM providers                                                                                   | `embed()`          | `complete()`       | `chat()`            | `summarize()`      | Notes              |
 | --------                                                                                        |:------------------:| :-------:          | :-----------------: | :-------:          | :----------------- |
-| [OpenAI](https://openai.com/?utm_source=langchainrb&utm_medium=github)                          | ✅                 | ✅                 | ✅                  | ❌                 | Including Azure OpenAI |
+| [OpenAI](https://openai.com/?utm_source=langchainrb&utm_medium=github)                          | ✅                 | ✅                 | ✅                  | ✅                 | Including Azure OpenAI |
 | [AI21](https://ai21.com/?utm_source=langchainrb&utm_medium=github)                              | ❌                 | ✅                 | ❌                  | ✅                 |                    |
 | [Anthropic](https://anthropic.com/?utm_source=langchainrb&utm_medium=github)                    | ❌                 | ✅                 | ✅                  | ❌                 |                    |
 | [AwsBedrock](https://aws.amazon.com/bedrock?utm_source=langchainrb&utm_medium=github)          | ✅                 | ✅                 | ✅                  | ❌                 | Provides AWS, Cohere, AI21, Antropic and Stability AI models |

data/lib/langchain/contextual_logger.rb

@@ -35,8 +35,8 @@ module Langchain
       @logger.respond_to?(method, include_private)
     end
 
-    def method_missing(method, *args, **kwargs, &block)
-      return @logger.send(method, *args, **kwargs, &block) unless @levels.include?(method)
+    def method_missing(method, *args, **kwargs, &)
+      return @logger.send(method, *args, **kwargs, &) unless @levels.include?(method)
 
       for_class = kwargs.delete(:for)
       for_class_name = for_class&.name

data/lib/langchain/loader.rb

@@ -90,7 +90,7 @@ module Langchain
     private
 
     def load_from_url
-      URI.parse(@path).open
+      URI.parse(URI::DEFAULT_PARSER.escape(@path)).open
     end
 
     def load_from_path
@@ -105,7 +105,7 @@ module Langchain
         # Only load and add to result files with supported extensions
         Langchain::Loader.new(file, @options).load(&block)
       rescue
-        UnknownFormatError nil
+        UnknownFormatError.new("Unknown format: #{source_type}")
       end.flatten.compact
     end
     # rubocop:enable Style/ArgumentsForwarding
@@ -123,7 +123,7 @@ module Langchain
     end
 
     def processor_klass
-      raise UnknownFormatError unless (kind = find_processor)
+      raise UnknownFormatError.new("Unknown format: #{source_type}") unless (kind = find_processor)
 
       Langchain::Processors.const_get(kind)
     end

data/lib/langchain/tool/news_retriever/news_retriever.rb

@@ -126,7 +126,10 @@ module Langchain::Tool
       request["Content-Type"] = "application/json"
 
       response = http.request(request)
-      response.body
+      response
+        .body
+        # Remove non-UTF-8 characters
+        .force_encoding(Encoding::UTF_8)
     end
   end
 end

data/lib/langchain/vectorsearch/chroma.rb

@@ -64,7 +64,7 @@ module Langchain::Vectorsearch
     # @param ids [Array<String>] The list of ids to remove
     # @return [Hash] The response from the server
     def remove_texts(ids:)
-      collection.delete(ids)
+      collection.delete(ids: ids)
     end
 
     # Create the collection with the default schema
@@ -122,7 +122,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &block)
+    def ask(question:, k: 4, &)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -134,7 +134,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &block)
+      response = llm.chat(messages: messages, &)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/elasticsearch.rb

@@ -143,7 +143,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &block)
+    def ask(question:, k: 4, &)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -153,7 +153,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &block)
+      response = llm.chat(messages: messages, &)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/epsilla.rb

@@ -129,7 +129,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &block)
+    def ask(question:, k: 4, &)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -140,7 +140,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &block)
+      response = llm.chat(messages: messages, &)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/hnswlib.rb

@@ -58,7 +58,7 @@ module Langchain::Vectorsearch
     #
     # @param query [String] The text to search for
     # @param k [Integer] The number of results to return
-    # @return [Array] Results in the format `[[id1, distance3], [id2, distance2]]`
+    # @return [Array] Results in the format `[[id1, id2], [distance1, distance2]]`
     #
     def similarity_search(
       query:,
@@ -77,7 +77,7 @@ module Langchain::Vectorsearch
     #
     # @param embedding [Array<Float>] The embedding to search for
     # @param k [Integer] The number of results to return
-    # @return [Array] Results in the format `[[id1, distance3], [id2, distance2]]`
+    # @return [Array] Results in the format `[[id1, id2], [distance1, distance2]]`
     #
     def similarity_search_by_vector(
       embedding:,

data/lib/langchain/vectorsearch/milvus.rb

@@ -141,7 +141,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &block)
+    def ask(question:, k: 4, &)
       search_results = similarity_search(query: question, k: k)
 
       content_field = search_results.dig("results", "fields_data").select { |field| field.dig("field_name") == "content" }
@@ -152,7 +152,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &block)
+      response = llm.chat(messages: messages, &)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/pgvector.rb

@@ -146,7 +146,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &block)
+    def ask(question:, k: 4, &)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -157,7 +157,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &block)
+      response = llm.chat(messages: messages, &)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/pinecone.rb

@@ -171,7 +171,7 @@ module Langchain::Vectorsearch
     # @param filter [String] The filter to use
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, namespace: "", filter: nil, k: 4, &block)
+    def ask(question:, namespace: "", filter: nil, k: 4, &)
       search_results = similarity_search(query: question, namespace: namespace, filter: filter, k: k)
 
       context = search_results.map do |result|
@@ -182,7 +182,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &block)
+      response = llm.chat(messages: messages, &)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/qdrant.rb

@@ -137,7 +137,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [String] The answer to the question
-    def ask(question:, k: 4, &block)
+    def ask(question:, k: 4, &)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -148,7 +148,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &block)
+      response = llm.chat(messages: messages, &)
 
       response.context = context
       response

data/lib/langchain/vectorsearch/weaviate.rb

@@ -143,7 +143,7 @@ module Langchain::Vectorsearch
     # @param k [Integer] The number of results to have in context
     # @yield [String] Stream responses back one String at a time
     # @return [Hash] The answer
-    def ask(question:, k: 4, &block)
+    def ask(question:, k: 4, &)
       search_results = similarity_search(query: question, k: k)
 
       context = search_results.map do |result|
@@ -154,7 +154,7 @@ module Langchain::Vectorsearch
       prompt = generate_rag_prompt(question: question, context: context)
 
       messages = [{role: "user", content: prompt}]
-      response = llm.chat(messages: messages, &block)
+      response = llm.chat(messages: messages, &)
 
       response.context = context
       response

data/lib/langchain/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Langchain
-  VERSION = "0.13.3"
+  VERSION = "0.13.4"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: langchainrb
 version: !ruby/object:Gem::Version
-  version: 0.13.3
+  version: 0.13.4
 platform: ruby
 authors:
 - Andrei Bondarev
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-06-03 00:00:00.000000000 Z
+date: 2024-06-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: baran
@@ -834,8 +834,8 @@ licenses:
 - MIT
 metadata:
   homepage_uri: https://rubygems.org/gems/langchainrb
-  source_code_uri: https://github.com/andreibondarev/langchainrb
-  changelog_uri: https://github.com/andreibondarev/langchainrb/CHANGELOG.md
+  source_code_uri: https://github.com/patterns-ai-core/langchainrb
+  changelog_uri: https://github.com/patterns-ai-core/langchainrb/blob/main/CHANGELOG.md
   documentation_uri: https://rubydoc.info/gems/langchainrb
 post_install_message:
 rdoc_options: []