You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
* migrated to stream query APIV2
* fixing tests
* enabled non streaming response
* updated README
* changed the max search results to 10
* removed debug logs
* minor update
* added back FCS calculating spinner
* renamed corpusKey to corpusKeys
* reformatted with 2 spaces
* parsed the facts text using snippets
@@ -79,9 +79,10 @@ import { ReactChatbot } from "@vectara/react-chatbot";
79
79
80
80
Every Vectara account is associated with a customer ID. You can find your customer ID by logging into the [Vectara Console](https://console.vectara.com/) and opening your account dropdown in the top-right corner.
81
81
82
-
##### `corpusIds` (required)
82
+
##### `corpuskeys` (required)
83
83
84
-
After you [create a corpus](https://docs.vectara.com/docs/console-ui/creating-a-corpus), you can find its ID by navigating to the corpus and looking in the top-left corner, next to the corpus name.
84
+
After you [create a corpus](https://docs.vectara.com/docs/console-ui/creating-a-corpus), you can find its Key by navigating to the corpus and looking in the top-left corner, next to the corpus name.
85
+
To run queries against multiple corpora, use a comma-separated list of corpus keys. For example: "corpus_1,corpus_2".
85
86
86
87
##### `apiKey` (required)
87
88
@@ -132,6 +133,18 @@ When set, this will calculate the [Factual Consistency Score (FCS)](https://docs
132
133
133
134
Define the [summarizer and prompt](https://docs.vectara.com/docs/learn/grounded-generation/select-a-summarizer) to use to generate the chat response.
134
135
136
+
##### `numberOfSearchResults` (optional)
137
+
138
+
Define the number of search results to be used to generate summary. Default is set to 15.
139
+
140
+
##### `rerankerId` (optional)
141
+
142
+
Define the reranker Id to be used , Defaults to 272725718.
143
+
144
+
##### `lambda` (optional)
145
+
146
+
How much to weigh lexical scores compared to the embedding score. 0 means lexical search is not used at all, and 1 means only lexical search is used.
0 commit comments