feat(functions): mixed JSON BNF grammars (#2328)

feat(functions): support mixed JSON BNF grammar

This PR provides new options to control how functions are extracted from
the LLM, and also provides more control on how JSON grammars can be used
(also in conjunction).

New YAML settings introduced:

- `grammar_message`: when enabled, the generated grammar can also decide
  to push strings and not only JSON objects. This allows the LLM to pick
to either respond freely or using JSON.
- `grammar_prefix`: Allows to prefix a string to the JSON grammar
  definition.
- `replace_results`: Is a map that allows to replace strings in the LLM
  result.

As an example, consider the following settings for Hermes-2-Pro-Mistral,
which allow extracting both JSON results coming from the model, and the
ones coming from the grammar:

```yaml
function:
  # disable injecting the "answer" tool
  disable_no_action: true
  # This allows the grammar to also return messages
  grammar_message: true
  # Suffix to add to the grammar
  grammar_prefix: '<tool_call>\n'
  return_name_in_function_response: true
  # Without grammar uncomment the lines below
  # Warning: this is relying only on the capability of the
  # LLM model to generate the correct function call.
  # no_grammar: true
  # json_regex_match: "(?s)<tool_call>(.*?)</tool_call>"
  replace_results:
    "<tool_call>": ""
    "\'": "\""
```

Note: To disable entirely grammars usage in the example above, uncomment the
`no_grammar` and `json_regex_match`.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

pkg/functions/parse.go

@@ -4,21 +4,49 @@ import (
 	"encoding/json"
 	"fmt"
 	"regexp"
+	"strings"
 
 	"github.com/go-skynet/LocalAI/pkg/utils"
 	"github.com/rs/zerolog/log"
 )
 
+// FunctionsConfig is the configuration for the tool/function call.
+// It includes setting to map the function name and arguments from the response
+// and, for instance, also if processing the requests with BNF grammars.
 type FunctionsConfig struct {
-	DisableNoAction         bool   `yaml:"disable_no_action"`
-	NoActionFunctionName    string `yaml:"no_action_function_name"`
-	NoActionDescriptionName string `yaml:"no_action_description_name"`
-	ParallelCalls           bool   `yaml:"parallel_calls"`
-	NoGrammar               bool   `yaml:"no_grammar"`
-	ResponseRegex           string `yaml:"response_regex"`
+	// DisableNoAction disables the "no action" tool
+	// By default we inject a tool that does nothing and is used to return an answer from the LLM
+	DisableNoAction bool `yaml:"disable_no_action"`
 
+	// NoActionFunctionName is the name of the function that does nothing. It defaults to "answer"
+	NoActionFunctionName string `yaml:"no_action_function_name"`
+
+	// NoActionDescriptionName is the name of the function that returns the description of the no action function
+	NoActionDescriptionName string `yaml:"no_action_description_name"`
+
+	// ParallelCalls enables the LLM to return multiple function calls in the same response
+	ParallelCalls bool `yaml:"parallel_calls"`
+
+	// GrammarMessage enables the LLM to return strings and not only JSON objects
+	// This is useful for models to not constraing returning only JSON and also messages back to the user
+	GrammarMessage bool `yaml:"grammar_message"`
+
+	// NoGrammar disables the grammar parsing and parses the responses directly from the LLM
+	NoGrammar bool `yaml:"no_grammar"`
+
+	// ResponseRegex is a named regex to extract the function name and arguments from the response
+	ResponseRegex string `yaml:"response_regex"`
+
+	// JSONRegexMatch is a regex to extract the JSON object from the response
 	JSONRegexMatch string `yaml:"json_regex_match"`
 
+	// GrammarPrefix is the suffix to append to the grammar when being generated
+	// This is useful when models prepend a tag before returning JSON
+	GrammarPrefix string `yaml:"grammar_prefix"`
+
+	// ReplaceResults allow to replace strings in the results before parsing them
+	ReplaceResults map[string]string `yaml:"replace_results"`
+
 	// FunctionName enable the LLM to return { "name": "function_name", "arguments": { "arg1": "value1", "arg2": "value2" } }
 	// instead of { "function": "function_name", "arguments": { "arg1": "value1", "arg2": "value2" } }.
 	// This might be useful for certain models trained with the function name as the first token.
@@ -31,6 +59,15 @@ type FuncCallResults struct {
 }
 
 func ParseFunctionCall(llmresult string, functionConfig FunctionsConfig) []FuncCallResults {
+	log.Debug().Msgf("LLM result: %s", llmresult)
+
+	for k, v := range functionConfig.ReplaceResults {
+		log.Debug().Msgf("Replacing %s with %s", k, v)
+		llmresult = strings.ReplaceAll(llmresult, k, v)
+	}
+
+	log.Debug().Msgf("LLM result(processed): %s", llmresult)
+
 	multipleResults := functionConfig.ParallelCalls
 	useGrammars := !functionConfig.NoGrammar
 
@@ -48,7 +85,7 @@ func ParseFunctionCall(llmresult string, functionConfig FunctionsConfig) []FuncC
 		s = utils.EscapeNewLines(s)
 		err := json.Unmarshal([]byte(s), &ss)
 		if err != nil {
-			log.Error().Err(err).Str("escapedLLMResult", s).Msg("unable to unmarshal llm result")
+			log.Warn().Err(err).Str("escapedLLMResult", s).Msg("unable to unmarshal llm result")
 		}
 		log.Debug().Msgf("Function return: %s %+v", s, ss)
 
@@ -132,7 +169,7 @@ func ParseFunctionCall(llmresult string, functionConfig FunctionsConfig) []FuncC
 		s := utils.EscapeNewLines(llmresult)
 		err := json.Unmarshal([]byte(s), &ss)
 		if err != nil {
-			log.Error().Err(err).Str("escapedLLMResult", s).Msg("multiple results: unable to unmarshal llm result")
+			log.Warn().Err(err).Str("escapedLLMResult", s).Msg("multiple results: unable to unmarshal llm result")
 		}
 		log.Debug().Msgf("Function return: %s %+v", s, ss)