Response Synthesizer#

Init file.

class llama_index.response_synthesizers.Accumulate(text_qa_template: Optional[BasePromptTemplate] = None, service_context: Optional[ServiceContext] = None, output_cls: Optional[Any] = None, streaming: bool = False, use_async: bool = False)#

Accumulate responses from multiple text chunks.

async aget_response(query_str: str, text_chunks: Sequence[str], separator: str = '\n---------------------\n', **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Apply the same prompt to text chunks and return async responses.

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

get_response(query_str: str, text_chunks: Sequence[str], separator: str = '\n---------------------\n', **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Apply the same prompt to text chunks and return responses.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

class llama_index.response_synthesizers.BaseSynthesizer(service_context: Optional[ServiceContext] = None, streaming: bool = False, output_cls: BaseModel = None)#

Response builder class.

abstract async aget_response(query_str: str, text_chunks: Sequence[str], **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get response.

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

abstract get_response(query_str: str, text_chunks: Sequence[str], **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get response.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

class llama_index.response_synthesizers.CompactAndRefine(service_context: Optional[ServiceContext] = None, text_qa_template: Optional[BasePromptTemplate] = None, refine_template: Optional[BasePromptTemplate] = None, output_cls: Optional[BaseModel] = None, streaming: bool = False, verbose: bool = False, structured_answer_filtering: bool = False, program_factory: Optional[Callable[[BasePromptTemplate], BasePydanticProgram]] = None)#

Refine responses across compact text chunks.

async aget_response(query_str: str, text_chunks: Sequence[str], prev_response: Optional[Union[BaseModel, str, Generator[str, None, None]]] = None, **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get response.

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

get_response(query_str: str, text_chunks: Sequence[str], prev_response: Optional[Union[BaseModel, str, Generator[str, None, None]]] = None, **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get compact response.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

class llama_index.response_synthesizers.Generation(simple_template: Optional[BasePromptTemplate] = None, service_context: Optional[ServiceContext] = None, streaming: bool = False)#

async aget_response(query_str: str, text_chunks: Sequence[str], **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get response.

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

get_response(query_str: str, text_chunks: Sequence[str], **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get response.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

class llama_index.response_synthesizers.Refine(service_context: Optional[ServiceContext] = None, text_qa_template: Optional[BasePromptTemplate] = None, refine_template: Optional[BasePromptTemplate] = None, output_cls: Optional[BaseModel] = None, streaming: bool = False, verbose: bool = False, structured_answer_filtering: bool = False, program_factory: Optional[Callable[[BasePromptTemplate], BasePydanticProgram]] = None)#

Refine a response to a query across text chunks.

async aget_response(query_str: str, text_chunks: Sequence[str], prev_response: Optional[Union[BaseModel, str, Generator[str, None, None]]] = None, **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get response.

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

get_response(query_str: str, text_chunks: Sequence[str], prev_response: Optional[Union[BaseModel, str, Generator[str, None, None]]] = None, **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Give response over chunks.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

class llama_index.response_synthesizers.ResponseMode(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)#

Response modes of the response builder (and synthesizer).

ACCUMULATE = 'accumulate'#: Synthesize a response for each text chunk, and then return the concatenation.

COMPACT = 'compact'#: Compact and refine mode first combine text chunks into larger consolidated chunks that more fully utilize the available context window, then refine answers across them. This mode is faster than refine since we make fewer calls to the LLM.

COMPACT_ACCUMULATE = 'compact_accumulate'#: Compact and accumulate mode first combine text chunks into larger consolidated chunks that more fully utilize the available context window, then accumulate answers for each of them and finally return the concatenation. This mode is faster than accumulate since we make fewer calls to the LLM.

GENERATION = 'generation'#: Ignore context, just use LLM to generate a response.

NO_TEXT = 'no_text'#: Return the retrieved context nodes, without synthesizing a final response.

REFINE = 'refine'#: Refine is an iterative way of generating a response. We first use the context in the first node, along with the query, to generate an initial answer. We then pass this answer, the query, and the context of the second node as input into a “refine prompt” to generate a refined answer. We refine through N-1 nodes, where N is the total number of nodes.

SIMPLE_SUMMARIZE = 'simple_summarize'#: Merge all text chunks into one, and make a LLM call. This will fail if the merged text chunk exceeds the context window size.

TREE_SUMMARIZE = 'tree_summarize'#: Build a tree index over the set of candidate nodes, with a summary prompt seeded with the query. The tree is built in a bottoms-up fashion, and in the end the root node is returned as the response

capitalize()#

Return a capitalized version of the string.

More specifically, make the first character have upper case and the rest lower case.

casefold()#: Return a version of the string suitable for caseless comparisons.

center(width, fillchar=' ', /)#

Return a centered string of length width.

Padding is done using the specified fill character (default is a space).

count(sub[, start[, end]]) → int#: Return the number of non-overlapping occurrences of substring sub in string S[start:end]. Optional arguments start and end are interpreted as in slice notation.

encode(encoding='utf-8', errors='strict')#

Encode the string using the codec registered for encoding.

encoding: The encoding in which to encode the string.
errors: The error handling scheme to use for encoding errors. The default is ‘strict’ meaning that encoding errors raise a UnicodeEncodeError. Other possible values are ‘ignore’, ‘replace’ and ‘xmlcharrefreplace’ as well as any other name registered with codecs.register_error that can handle UnicodeEncodeErrors.

endswith(suffix[, start[, end]]) → bool#: Return True if S ends with the specified suffix, False otherwise. With optional start, test S beginning at that position. With optional end, stop comparing S at that position. suffix can also be a tuple of strings to try.

expandtabs(tabsize=8)#

Return a copy where all tab characters are expanded using spaces.

If tabsize is not given, a tab size of 8 characters is assumed.

find(sub[, start[, end]]) → int#

Return the lowest index in S where substring sub is found, such that sub is contained within S[start:end]. Optional arguments start and end are interpreted as in slice notation.

Return -1 on failure.

format(*args, **kwargs) → str#: Return a formatted version of S, using substitutions from args and kwargs. The substitutions are identified by braces (‘{‘ and ‘}’).

format_map(mapping) → str#: Return a formatted version of S, using substitutions from mapping. The substitutions are identified by braces (‘{‘ and ‘}’).

index(sub[, start[, end]]) → int#

Return the lowest index in S where substring sub is found, such that sub is contained within S[start:end]. Optional arguments start and end are interpreted as in slice notation.

Raises ValueError when the substring is not found.

isalnum()#

Return True if the string is an alpha-numeric string, False otherwise.

A string is alpha-numeric if all characters in the string are alpha-numeric and there is at least one character in the string.

isalpha()#

Return True if the string is an alphabetic string, False otherwise.

A string is alphabetic if all characters in the string are alphabetic and there is at least one character in the string.

isascii()#

Return True if all characters in the string are ASCII, False otherwise.

ASCII characters have code points in the range U+0000-U+007F. Empty string is ASCII too.

isdecimal()#

Return True if the string is a decimal string, False otherwise.

A string is a decimal string if all characters in the string are decimal and there is at least one character in the string.

isdigit()#

Return True if the string is a digit string, False otherwise.

A string is a digit string if all characters in the string are digits and there is at least one character in the string.

isidentifier()#

Return True if the string is a valid Python identifier, False otherwise.

Call keyword.iskeyword(s) to test whether string s is a reserved identifier, such as “def” or “class”.

islower()#

Return True if the string is a lowercase string, False otherwise.

A string is lowercase if all cased characters in the string are lowercase and there is at least one cased character in the string.

isnumeric()#

Return True if the string is a numeric string, False otherwise.

A string is numeric if all characters in the string are numeric and there is at least one character in the string.

isprintable()#

Return True if the string is printable, False otherwise.

A string is printable if all of its characters are considered printable in repr() or if it is empty.

isspace()#

Return True if the string is a whitespace string, False otherwise.

A string is whitespace if all characters in the string are whitespace and there is at least one character in the string.

istitle()#

Return True if the string is a title-cased string, False otherwise.

In a title-cased string, upper- and title-case characters may only follow uncased characters and lowercase characters only cased ones.

isupper()#

Return True if the string is an uppercase string, False otherwise.

A string is uppercase if all cased characters in the string are uppercase and there is at least one cased character in the string.

join(iterable, /)#

Concatenate any number of strings.

The string whose method is called is inserted in between each given string. The result is returned as a new string.

Example: ‘.’.join([‘ab’, ‘pq’, ‘rs’]) -> ‘ab.pq.rs’

ljust(width, fillchar=' ', /)#

Return a left-justified string of length width.

Padding is done using the specified fill character (default is a space).

lower()#: Return a copy of the string converted to lowercase.

lstrip(chars=None, /)#

Return a copy of the string with leading whitespace removed.

If chars is given and not None, remove characters in chars instead.

static maketrans()#

Return a translation table usable for str.translate().

If there is only one argument, it must be a dictionary mapping Unicode ordinals (integers) or characters to Unicode ordinals, strings or None. Character keys will be then converted to ordinals. If there are two arguments, they must be strings of equal length, and in the resulting dictionary, each character in x will be mapped to the character at the same position in y. If there is a third argument, it must be a string, whose characters will be mapped to None in the result.

partition(sep, /)#

Partition the string into three parts using the given separator.

This will search for the separator in the string. If the separator is found, returns a 3-tuple containing the part before the separator, the separator itself, and the part after it.

If the separator is not found, returns a 3-tuple containing the original string and two empty strings.

removeprefix(prefix, /)#

Return a str with the given prefix string removed if present.

If the string starts with the prefix string, return string[len(prefix):]. Otherwise, return a copy of the original string.

removesuffix(suffix, /)#

Return a str with the given suffix string removed if present.

If the string ends with the suffix string and that suffix is not empty, return string[:-len(suffix)]. Otherwise, return a copy of the original string.

replace(old, new, count=-1, /)#

Return a copy with all occurrences of substring old replaced by new.

count
Maximum number of occurrences to replace. -1 (the default value) means replace all occurrences.

If the optional argument count is given, only the first count occurrences are replaced.

rfind(sub[, start[, end]]) → int#

Return the highest index in S where substring sub is found, such that sub is contained within S[start:end]. Optional arguments start and end are interpreted as in slice notation.

Return -1 on failure.

rindex(sub[, start[, end]]) → int#

Return the highest index in S where substring sub is found, such that sub is contained within S[start:end]. Optional arguments start and end are interpreted as in slice notation.

Raises ValueError when the substring is not found.

rjust(width, fillchar=' ', /)#

Return a right-justified string of length width.

Padding is done using the specified fill character (default is a space).

rpartition(sep, /)#

Partition the string into three parts using the given separator.

This will search for the separator in the string, starting at the end. If the separator is found, returns a 3-tuple containing the part before the separator, the separator itself, and the part after it.

If the separator is not found, returns a 3-tuple containing two empty strings and the original string.

rsplit(sep=None, maxsplit=-1)#

Return a list of the substrings in the string, using sep as the separator string.

sep
The separator used to split the string.

When set to None (the default value), will split on any whitespace character (including n r t f and spaces) and will discard empty strings from the result.

maxsplit
Maximum number of splits (starting from the left). -1 (the default value) means no limit.

Splitting starts at the end of the string and works to the front.

rstrip(chars=None, /)#

Return a copy of the string with trailing whitespace removed.

If chars is given and not None, remove characters in chars instead.

split(sep=None, maxsplit=-1)#

Return a list of the substrings in the string, using sep as the separator string.

sep
The separator used to split the string.

When set to None (the default value), will split on any whitespace character (including n r t f and spaces) and will discard empty strings from the result.

maxsplit
Maximum number of splits (starting from the left). -1 (the default value) means no limit.

Note, str.split() is mainly useful for data that has been intentionally delimited. With natural text that includes punctuation, consider using the regular expression module.

splitlines(keepends=False)#

Return a list of the lines in the string, breaking at line boundaries.

Line breaks are not included in the resulting list unless keepends is given and true.

startswith(prefix[, start[, end]]) → bool#: Return True if S starts with the specified prefix, False otherwise. With optional start, test S beginning at that position. With optional end, stop comparing S at that position. prefix can also be a tuple of strings to try.

strip(chars=None, /)#

Return a copy of the string with leading and trailing whitespace removed.

If chars is given and not None, remove characters in chars instead.

swapcase()#: Convert uppercase characters to lowercase and lowercase characters to uppercase.

title()#

Return a version of the string where each word is titlecased.

More specifically, words start with uppercased characters and all remaining cased characters have lower case.

translate(table, /)#

Replace each character in the string using the given translation table.

table
Translation table, which must be a mapping of Unicode ordinals to Unicode ordinals, strings, or None.

The table must implement lookup/indexing via __getitem__, for instance a dictionary or list. If this operation raises LookupError, the character is left untouched. Characters mapped to None are deleted.

upper()#: Return a copy of the string converted to uppercase.

zfill(width, /)#

Pad a numeric string with zeros on the left, to fill a field of the given width.

The string is never truncated.

class llama_index.response_synthesizers.SimpleSummarize(text_qa_template: Optional[BasePromptTemplate] = None, service_context: Optional[ServiceContext] = None, streaming: bool = False)#

async aget_response(query_str: str, text_chunks: Sequence[str], **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get response.

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

get_response(query_str: str, text_chunks: Sequence[str], **kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get response.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

class llama_index.response_synthesizers.TreeSummarize(summary_template: Optional[BasePromptTemplate] = None, service_context: Optional[ServiceContext] = None, output_cls: Optional[BaseModel] = None, streaming: bool = False, use_async: bool = False, verbose: bool = False)#

Tree summarize response builder.

This response builder recursively merges text chunks and summarizes them in a bottom-up fashion (i.e. building a tree from leaves to root).

More concretely, at each recursively step: 1. we repack the text chunks so that each chunk fills the context window of the LLM 2. if there is only one chunk, we give the final response 3. otherwise, we summarize each chunk and recursively summarize the summaries.

async aget_response(query_str: str, text_chunks: Sequence[str], **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get tree summarize response.

as_query_component(partial: Optional[Dict[str, Any]] = None, **kwargs: Any) → QueryComponent#: Get query component.

get_prompts() → Dict[str, BasePromptTemplate]#: Get a prompt.

get_response(query_str: str, text_chunks: Sequence[str], **response_kwargs: Any) → Union[BaseModel, str, Generator[str, None, None]]#: Get tree summarize response.

update_prompts(prompts_dict: Dict[str, BasePromptTemplate]) → None#

Update prompts.

Other prompts will remain in place.

llama_index.response_synthesizers.get_response_synthesizer(service_context: Optional[ServiceContext] = None, text_qa_template: Optional[BasePromptTemplate] = None, refine_template: Optional[BasePromptTemplate] = None, summary_template: Optional[BasePromptTemplate] = None, simple_template: Optional[BasePromptTemplate] = None, response_mode: ResponseMode = ResponseMode.COMPACT, callback_manager: Optional[CallbackManager] = None, use_async: bool = False, streaming: bool = False, structured_answer_filtering: bool = False, output_cls: Optional[BaseModel] = None, program_factory: Optional[Callable[[PromptTemplate], BasePydanticProgram]] = None, verbose: bool = False) → BaseSynthesizer#: Get a response synthesizer.