completion-kit 0.13.0 → 0.14.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 83e9019cabf58eef8e2110428561e9a4a14763e2f7b7334d77684e6714b85560
-  data.tar.gz: c05f8a637a7727091af35c2a673a7cca07e9c3bf424daff49cca9208da1a96ee
+  metadata.gz: 7a3fda7b41271efa8b169adff5bc72e3f347fa67641aa26ab2d52f84ad4d0526
+  data.tar.gz: fd9fcca6cc6ac22e32a3f8ba7f917fd8b0ccb30a270f45aa63fb7fc3ee59343b
 SHA512:
-  metadata.gz: 7bd1d7943255b84a81706d7977aaf2d224c88d6884c831302f669151b24659bfd60debb1f3c2558ac71e29b9f14ddc6b4140597955658576d8c39003d62b89dc
-  data.tar.gz: 71f23d6a1ac7dfc1b32792ee30116a9b3a32062836798b28fc3c07adc12ebe1ca79345a5249375c7b380af26df4a2fd78cf33976591ccee682c8eb3fd9bce0a9
+  metadata.gz: '02917101ab65551a18974c80b382ba508b5f0a80f67182bf630998aacfebc4584f85d03d9fc0c59d6de7b89c1881391340cd81c3cd1631bca6b545067f57a513'
+  data.tar.gz: 255c33ab87a13e1e4ed5387c8cff70c952cf0c68c3d3829ddc4c401208bc1d94019f121fd0cfbd7ec425a4669f3420b96b988ade2bba50f0113f5e714957295e

data/app/controllers/completion_kit/api/v1/datasets_controller.rb

@@ -45,7 +45,10 @@ module CompletionKit
         end
 
         def dataset_params
-          params.permit(:name, :csv_data, tag_names: [])
+          permitted = params.permit(:name, :csv_data, tag_names: [])
+          upload = params[:file]
+          permitted[:csv_data] = upload.read.to_s.force_encoding("UTF-8") if upload.respond_to?(:read)
+          permitted
         end
       end
     end

data/app/services/completion_kit/mcp_tools/datasets.rb

@@ -1,8 +1,12 @@
+require "faraday"
+
 module CompletionKit
   module McpTools
     module Datasets
       extend Base
 
+      MAX_CSV_BYTES = 10 * 1024 * 1024
+
       TOOLS = {
         "datasets_list" => {
           description: "List all datasets",
@@ -36,6 +40,19 @@ module CompletionKit
           description: "Delete a dataset",
           inputSchema: {type: "object", properties: {id: {type: "integer"}}, required: ["id"]},
           handler: :delete
+        },
+        "datasets_create_from_url" => {
+          description: "Create a dataset by downloading CSV from a URL instead of inlining it. Use this for large datasets: pass a public http(s) URL and the server fetches the CSV directly, so the data never has to pass through the tool-call arguments. The URL is SSRF-checked and the download is capped at 10MB.",
+          inputSchema: {
+            type: "object",
+            properties: {
+              name: {type: "string"},
+              url: {type: "string", description: "Public http(s) URL of the CSV file to download."},
+              tag_names: {type: "array", items: {type: "string"}}
+            },
+            required: ["name", "url"]
+          },
+          handler: :create_from_url
         }
       }.freeze
 
@@ -71,6 +88,35 @@ module CompletionKit
         Dataset.find(args["id"]).destroy!
         text_result("Dataset #{args["id"]} deleted")
       end
+
+      def self.create_from_url(args)
+        issues = ProviderEndpoint.validate(args["url"])
+        return error_result("URL is not allowed (#{issues.join(", ")}).") if issues.any?
+
+        response = csv_connection.get(args["url"])
+        return error_result("Could not download CSV (HTTP #{response.status}).") unless response.success?
+
+        body = response.body.to_s
+        return error_result("CSV is larger than the #{MAX_CSV_BYTES / (1024 * 1024)}MB limit.") if body.bytesize > MAX_CSV_BYTES
+
+        dataset = Dataset.new(name: args["name"], csv_data: body.dup.force_encoding("UTF-8"))
+        dataset.tag_names = args["tag_names"] if args.key?("tag_names")
+        if dataset.save
+          text_result(dataset.reload.as_json)
+        else
+          error_result(dataset.errors.full_messages.join(", "))
+        end
+      rescue Faraday::Error => e
+        error_result("Could not download CSV: #{e.message}")
+      end
+
+      def self.csv_connection
+        Faraday.new do |f|
+          f.options.timeout = 30
+          f.options.open_timeout = 5
+          f.adapter Faraday.default_adapter
+        end
+      end
     end
   end
 end

data/lib/completion_kit/version.rb

@@ -1,3 +1,3 @@
 module CompletionKit
-  VERSION = "0.13.0"
+  VERSION = "0.14.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: completion-kit
 version: !ruby/object:Gem::Version
-  version: 0.13.0
+  version: 0.14.0
 platform: ruby
 authors:
 - Damien Bastin