o ZhT@svddlZddlZddlZddlZddlmZddlmZddlmZddlm Z ddl m Z m Z m Z mZmZmZmZddlmZdd lmZdd lmZmZmZeeZeriddlZdd lmZdd l m!Z!ndZertdd l"m#Z#er}ddl$m%Z%e&e'e(e)e e*ddfZ+e,dej-Z.e,dej-Z/e,dej-ej0BZ1e,dej-Z2Gddde3Z4Gddde3Z5de(de6e(e(ffddZ7de(de6fddZ8de de6fd d!Z9d"e(de:e e(e e6e e(ffd#d$Z;de de6fd%d&Z    + + +d5d,e?e?e6e(e(fd-e e?ee6e fd.e e?e6e(e(fd/e e(d0e e)d1e e)d2e e)de(fd3d4Z@dS)6N)contextmanager)datetime) lru_cache) isfunction)AnyCallableOptionalUnionget_args get_originget_type_hints)version)logging)is_jinja_availableis_torch_availableis_vision_available) Extension)ImmutableSandboxedEnvironment)Image)Tensor.z(^(.*?)[\n\s]*(Args:|Returns:|Raises:|\Z)z0\n\s*Args:\n\s*(.*?)[\n\s]*(Returns:|Raises:|\Z)a1 (?:^|\n) # Match the start of the args block, or a newline \s*(\w+):\s* # Capture the argument name and strip spacing (.*?)\s* # Capture the argument description, which can span multiple lines, and strip trailing spacing (?=\n\s*\w+:|\Z) # Stop when you hit the next argument or the end of the block z*\n\s*Returns:\n\s*(.*?)[\n\s]*(Raises:|\Z)c@eZdZdZdS)TypeHintParsingExceptionzJException raised for errors in parsing type hints to generate JSON schemasN__name__ __module__ __qualname____doc__rrU/var/www/auris/lib/python3.10/site-packages/transformers/utils/chat_template_utils.pyrBrc@r)DocstringParsingExceptionzJException raised for errors in parsing docstrings to generate JSON schemasNrrrrrr!Hr r! param_typereturnc Cshtdditdditdditdditddditii}tr#ddi|t<tr,ddi|t <| |dd iS) NtypeintegernumberstringbooleannullimageZaudioobject) intfloatstrboolr$rrrrrget)r"Z type_mappingrrr_get_json_schema_typeNs   r1hintcCst|}t|}|durzt|WStytd|w|tus,ttdrc|tjurcdd|D}t |dkr>|d}nt dd|DrSd t d d|Di}nd |i}t d|vrad |d <|S|t urv|smd diSdt|ddS|tur|sd diSt |dkrtdt|dddd|vrtdddd|DdS|turd di}t |dkrt|d|d<|Std|)NzGCouldn't parse this type hint, likely due to a custom class or object: UnionTypecSs g|] }|tdurt|qSN)r$_parse_type_hint.0trrr ls z$_parse_type_hint..rrcss|] }t|dtVqdS)r$N) isinstancer.r7subtyperrr psz#_parse_type_hint..r$cSsg|]}|dqS)r$rr;rrrr9rZanyOfTZnullablearray)r$itemszThe type hint ztyping.a1 is a Tuple with a single element, which we do not automatically convert to JSON schema as it is rarely necessary. If this input can contain more than one element, we recommend using a List[] type instead, or if it really is a single element, remove the Tuple[] wrapper and just pass the element directly..znConversion of '...' is not supported in Tuple type hints. Use List[] types for variable-length inputs instead.cSsg|]}t|qSr)r5r6rrrr9r>)r$Z prefixItemsr+ZadditionalProperties)r r r1KeyErrorrr hasattrtypesr3lenallsortedr$listr5tupler.replacedict)r2originargssubtypes return_dictoutrrrr5^sT        r5funcc Cst|}t|}g}|jD]#\}}|jtjjkr'td|j d|j |j tjjkr3| |qi}|D] \}}t |||<q:d|d}|rP||d<|S)Nz Argument z$ is missing a type hint in function r+)r$ propertiesrequired)r inspect signature parametersr@ annotation Parameteremptyrnamerdefaultappendr5) rRZ type_hintsrVrT param_nameparamrSr"schemarrr"_convert_type_hints_to_json_schemas    ra docstringc Cst|}t|}t|}|r|dnd}|r#|dnd}|r.|dnd}|durNddd|dD}t |}dd|D}ni}|||fS)a Parses a Google-style docstring to extract the function description, argument descriptions, and return description. Args: docstring (str): The docstring to parse. Returns: The function description, arguments, and return description. rN cSsg|]}|r|qSrstrip)r7linerrrr9sz1parse_google_format_docstring..c Ss(i|]}|dtdd|dqS)rz \s*\n+\s* r)resubre)r7matchrrr s(z1parse_google_format_docstring..) description_researchargs_re returns_regrouprejoinsplit args_split_refindall) rbZdescription_matchZ args_matchZ returns_match descriptionZdocstring_argsreturnsmatchesZ args_dictrrrparse_google_format_docstrings    rxc Cst|}|std|jd|}t|\}}}t|}|ddd}dur3|dur3||d<|dD]A\}}||vrMtd|jd|d||} t j d | t j d } | rvd d t | d D|d<| jd| } | |d<q9|j||d} |dur|| d<d| dS)a This function generates a JSON schema for a given function, based on its docstring and type hints. This is mostly used for passing lists of tools to a chat template. The JSON schema contains the name and description of the function, as well as the names, types and descriptions for each of its arguments. `get_json_schema()` requires that the function has a docstring, and that each argument has a description in the docstring, in the standard Google docstring format shown below. It also requires that all the function arguments have a valid Python type hint. Although it is not required, a `Returns` block can also be added, which will be included in the schema. This is optional because most chat templates ignore the return value of the function. Args: func: The function to generate a JSON schema for. Returns: A dictionary containing the JSON schema for the function. Examples: ```python >>> def multiply(x: float, y: float): >>> ''' >>> A function that multiplies two numbers >>> >>> Args: >>> x: The first number to multiply >>> y: The second number to multiply >>> ''' >>> return x * y >>> >>> print(get_json_schema(multiply)) { "name": "multiply", "description": "A function that multiplies two numbers", "parameters": { "type": "object", "properties": { "x": {"type": "number", "description": "The first number to multiply"}, "y": {"type": "number", "description": "The second number to multiply"} }, "required": ["x", "y"] } } ``` The general use for these schemas is that they are used to generate tool descriptions for chat templates that support them, like so: ```python >>> from transformers import AutoTokenizer >>> from transformers.utils import get_json_schema >>> >>> def multiply(x: float, y: float): >>> ''' >>> A function that multiplies two numbers >>> >>> Args: >>> x: The first number to multiply >>> y: The second number to multiply >>> return x * y >>> ''' >>> >>> multiply_schema = get_json_schema(multiply) >>> tokenizer = AutoTokenizer.from_pretrained("CohereForAI/c4ai-command-r-v01") >>> messages = [{"role": "user", "content": "What is 179 x 4571?"}] >>> formatted_chat = tokenizer.apply_chat_template( >>> messages, >>> tools=[multiply_schema], >>> chat_template="tool_use", >>> return_dict=True, >>> return_tensors="pt", >>> add_generation_prompt=True >>> ) >>> # The formatted chat can now be passed to model.generate() ``` Each argument description can also have an optional `(choices: ...)` block at the end, such as `(choices: ["tea", "coffee"])`, which will be parsed into an `enum` field in the schema. Note that this will only be parsed correctly if it is at the end of the line: ```python >>> def drink_beverage(beverage: str): >>> ''' >>> A function that drinks a beverage >>> >>> Args: >>> beverage: The beverage to drink (choices: ["tea", "coffee"]) >>> ''' >>> pass >>> >>> print(get_json_schema(drink_beverage)) ``` { 'name': 'drink_beverage', 'description': 'A function that drinks a beverage', 'parameters': { 'type': 'object', 'properties': { 'beverage': { 'type': 'string', 'enum': ['tea', 'coffee'], 'description': 'The beverage to drink' } }, 'required': ['beverage'] } } z Cannot generate JSON schema for z because it has no docstring!rSr#Nruz< because the docstring has no description for the argument ''z\(choices:\s*(.*?)\)\s*$)flagscSsg|]}|qSrrd)r7crrrr9Tr>z#get_json_schema..renum)r[rurWfunction)r$r})rUgetdocr!rrerxrapopr@rhrm IGNORECASEjsonloadsrpr'start) rRdocZmain_docZparam_descriptionsZ return_docZ json_schemarPargr`ZdescZ enum_choicesoutputrrrget_json_schemas4 k   rc Ksxg}g}|j||%|jd||||d|D]}||qd|} Wd| |fS1s3wY| |fS)Nmessagestools documentsadd_generation_promptrAr) environmentactivate_trackergenerater]rq) compiled_templaterrrrZtemplate_kwargsrendered_blocksgeneration_indicesblock rendered_chatrrr_render_with_assistant_indices^s"     rcCststdGdddt}ttjtdkr#tdtjddd}dd d }d d }tdd|tjj gd}||j d<||j d<||j d<| |S)Nzbapply_chat_template requires jinja2 to be installed. Please install it using `pip install jinja2`.cseZdZdhZdeffdd Zdejjdej j fddZ ej d ej j d ejjdefd d Zdefd dZedeedeefddZZS)z1_compile_jinja_template..AssistantTrackerZ generationrcs*t||j|jdd|_d|_dS)N)r)super__init__extendr_rendered_blocks_generation_indices)selfr __class__rrr{s  z:_compile_jinja_template..AssistantTracker.__init__parserr#cSs:t|jj}|jdgdd}tj|dgg||S)Nzname:endgenerationT)Z drop_needle_generation_support) nextstreamlinenoZparse_statementsjinja2nodes CallBlockZ call_methodZ set_lineno)rrrbodyrrrparses z7_compile_jinja_template..AssistantTracker.parsecontextcallercSs>|}|rtd|j}|t|}|j||f|S)NrA) is_activerFrqrrr])rrrrv start_indexZ end_indexrrrrs  zE_compile_jinja_template..AssistantTracker._generation_supportcSs |jp|jSr4)rr)rrrrr z;_compile_jinja_template..AssistantTracker.is_activerrcssFz|r td||_||_dVWd|_d|_dSd|_d|_w)Nz3AssistantTracker should not be reused before closed)r ValueErrorrr)rrrrrrrs zB_compile_jinja_template..AssistantTracker.activate_tracker)rrrtagsrrrrParserrrrZpass_eval_contextZ EvalContextZruntimeZMacror.rr/rrrIr,r __classcell__rrrrAssistantTrackerws  $rz3.1.0zLapply_chat_template requires jinja2>=3.1.0 to be installed. Your version is .cSs tj|r4)r exceptionsZ TemplateError)messagerrrraise_exceptionrz0_compile_jinja_template..raise_exceptionFcSstj|||||dS)N) ensure_asciiindent separators sort_keys)rdumps)xrrrrrrrtojsonsz'_compile_jinja_template..tojsoncSst|Sr4)rnowstrftime)formatrrr strftime_nowsz-_compile_jinja_template..strftime_nowT)Z trim_blocksZ lstrip_blocks extensionsrrr)FNNF) r ImportErrorrr rr __version__rextZ loopcontrolsfiltersglobalsZ from_string) chat_templaterrrrZ jinja_envrrr_compile_jinja_templateps&*      rF conversationsrrrreturn_assistant_tokens_maskcontinue_final_messagerc Ks|r td|s tdt|}|dur7g} |D]} t| tr&| | qt| r2| t | qt dnd} |durK|D] } t| tsJt dq?g} g} |D]}t |dr[|j }|rrtd ||| ||d|\}}| |n |jd || ||d|}|r|dd }t|ttfrt|D] }d |vr|d }nqt d ||vrt d ||}|||t||kr|d|t|}n |d|t|}| |qQ| | fS)Nz\{\%-?\s*generation\s*-?\%\}zareturn_assistant_tokens_mask==True but chat template does not contain `{% generation %}` keyword.zTools should either be a JSON schema, or a callable function with type hints and a docstring suitable for auto-conversion to a schema.zADocuments should be a list of dicts with 'title' and 'text' keys!r)rrrrrrcontenttextz]continue_final_message is set but we could not find any text to continuein the final message!acontinue_final_message is set but the final message does not appear in the chat after applying the chat template! This can happen if the chat template deletes portions of the final message. Please verify the chat template and final message in your chat to ensure they are compatible.r)rhrmloggerZ warning_oncerr:rLr]rrr TypeErrorrDrrrenderrIrJreversedrerindexrFlstrip)rrrrrrrkwargsrZ tool_schemasZtoolZdocumentrenderedZall_generation_indicesZchatrrZ final_messageZ content_blockZ final_msg_locrrrrender_jinja_templates           r)NNNFFF)ArUrrhrE contextlibrr functoolsrrtypingrrrr r r r packagingr rArZ import_utilsrrrZ get_loggerrrrZ jinja2.extrZjinja2.sandboxrZ PIL.ImagerZtorchrr,r-r.r/r$Z BASIC_TYPEScompileDOTALLrlrnVERBOSErsro Exceptionrr!rLr1r5rarJrxrrrrIrrrrrs    $        A(!  K