feat: allow more input types to functions, fix tests (#377)

* feat: use json.rawMessage, test functions

* chore: lint

* fix: tests

the ChatCompletion mock server doesn't actually run otherwise. N=0
is the default request but the server will treat it as n=1

* fix: tests should default to n=1 completions

* chore: add back removed interfaces, custom marshal

* chore: lint

* chore: lint

* chore: add some tests

* chore: appease lint

* clean up JSON schema + tests

* chore: lint

* feat: remove backwards compatible functions

for illustrative purposes

* fix: revert params change

* chore: use interface{}

* chore: add test

* chore: add back FunctionDefine

* chore: /s/interface{}/any

* chore: add back jsonschemadefinition

* chore: testcov

* chore: lint

* chore: remove pointers

* chore: update comment

* chore: address CR

added test for compatibility as well

---------

Co-authored-by: James <jmacwhyte@MacBooger-II.local>

completion_test.go

@@ -83,7 +83,11 @@ func handleCompletionEndpoint(w http.ResponseWriter, r *http.Request) {
 		Model: completionReq.Model,
 	}
 	// create completions
-	for i := 0; i < completionReq.N; i++ {
+	n := completionReq.N
+	if n == 0 {
+		n = 1
+	}
+	for i := 0; i < n; i++ {
 		// generate a random string of length completionReq.Length
 		completionStr := strings.Repeat("a", completionReq.MaxTokens)
 		if completionReq.Echo {
@@ -94,8 +98,8 @@ func handleCompletionEndpoint(w http.ResponseWriter, r *http.Request) {
 			Index: i,
 		})
 	}
-	inputTokens := numTokens(completionReq.Prompt.(string)) * completionReq.N
-	completionTokens := completionReq.MaxTokens * completionReq.N
+	inputTokens := numTokens(completionReq.Prompt.(string)) * n
+	completionTokens := completionReq.MaxTokens * n
 	res.Usage = Usage{
 		PromptTokens:     inputTokens,
 		CompletionTokens: completionTokens,