o ZhfQ@sddlZddlZddlZddlmZmZddlmZmZm Z m Z m Z m Z ddl Z ddlmZddlmZddlmZddlmZmZmZmZmZdgZGd d d eeZd e eefd efd dZd e eefd efddZd e eefd efddZGdddeZ GdddeZ!d efddZ"d efddZ#d efddZ$ded e%fddZ&ded e e%d efd!d"Z'd#ed efd$d%Z(ed&d'd(d)Gd*ddeZ)dS)+N)ABCabstractmethod)AnyCallableDictListMappingOptional) deprecated)CallbackManagerForLLMRun)LLM) BaseModel ConfigDictField PrivateAttrmodel_validator Databricksc @seZdZUdZeed<eed<dedededefdd Zdedefd d Zdededefd d Z e ddede e defdefddZ edefddZdS)_DatabricksClientBasez0A base JSON API client that talks to Databricks.api_url api_tokenmethodurlrequestreturncCsHdd|ji}tj||||d}|js td|jd|j|S)N AuthorizationzBearer )rrheadersjsonzHTTP z error: )rrequestsrok ValueError status_codetextr)selfrrrrresponser$Z/var/www/html/lang_env/lib/python3.10/site-packages/langchain_community/llms/databricks.pyrsz_DatabricksClientBase.requestcCs|d|dS)NGETr)r"rr$r$r%_get&z_DatabricksClientBase._getcCs|d||S)NPOSTr')r"rrr$r$r%_post)r)z_DatabricksClientBase._postNtransform_output_fn.cCsdSNr$)r"rr,r$r$r%post,z_DatabricksClientBase.postcCdS)NFr$r"r$r$r%llm1sz_DatabricksClientBase.llmr-)__name__ __module__ __qualname____doc__str__annotations__rrr(r+rr rr.propertyboolr2r$r$r$r%rs$   rr#rcC|dddS)Nchoicesrr!r$r#r$r$r%_transform_completions6r>cCr;)N candidatesrr!r$r=r$r$r%_transform_llama2_chat:r?rAcCs|ddddS)Nr<rmessagecontentr$r=r$r$r%_transform_chat>srDcseZdZUdZeed<eed<eed<dZeed<dZe ed<dZ e eed <d effd d Z e d e fddZeddedeeefd efddZ ddede edefd efddZZS) _DatabricksServingEndpointClientz:An API client that talks to a Databricks serving endpoint.host endpoint_namedatabricks_uriNclientFexternal_or_foundationtaskdatac stjdi|zddlm}||j|_Wnty(}ztd|d}~ww|j|j}| dd dv|_ |j durH| d|_ dSdS) Nr)get_deploy_clientzMFailed to create the client. Please install mlflow with `pip install mlflow`.Z endpoint_type)Zexternal_modelZfoundation_model_apirKr$) super__init__Zmlflow.deploymentsrMrHrI ImportErrorZ get_endpointrGgetlowerrJrK)r"rLrMeendpoint __class__r$r%rPLs"  z)_DatabricksServingEndpointClient.__init__rcCs |jdvS)N) llm/v1/chatllm/v1/completions llama2/chat)rKr1r$r$r%r2as z$_DatabricksServingEndpointClient.llmbeforemodevaluescCs6d|vr|d}|d}d|d|d}||d<|S)NrrFrGhttps://z/serving-endpoints/z /invocationsr$)clsr^rFrGrr$r$r% set_api_urles z,_DatabricksServingEndpointClient.set_api_urlrr,.cCs|jr&|jj|j|d}|r||S|jdkrt|S|jdkr$t|S|Sd|gi}|jj|j|d}|d}t|trA|dn|}|jdkrLt |S|rR||S|S)N)rUZinputsrXrYZdataframe_recordsZ predictionsrrZ) rJrIZpredictrGrKrDr> isinstancelistrA)r"rr,respZwrapped_requestr#predspredr$r$r%r.os$    z%_DatabricksServingEndpointClient.postr-)r3r4r5r6r7r8rIrrJr:rKr rPr9r2r classmethodrrarr. __classcell__r$r$rVr%rEBs,    rEc@sxeZdZUdZeed<eed<eed<eddedeee fde fd d Z dd e d e e defde fddZ d S)#_DatabricksClusterDriverProxyClientzBAn API client that talks to a Databricks cluster driver proxy app.rF cluster_idcluster_driver_portr[r\r^rcCsBd|vr|d}|d}|d}d|d|d|}||d<|S)NrrFrjrkr_z/driver-proxy-api/o/0//r$)r`r^rFrjportrr$r$r%rasz/_DatabricksClusterDriverProxyClient.set_api_urlNrr,.cCs||j|}|r ||S|Sr-)r+r)r"rr,rdr$r$r%r.sz(_DatabricksClusterDriverProxyClient.postr-)r3r4r5r6r7r8rrgrrrar rr.r$r$r$r%ris  ricCs,z ddlm}|WStytdw)zgGet the notebook REPL context if running inside a Databricks notebook. Returns None otherwise. r get_contextzBCannot access dbruntime, not running inside a Databricks notebook.)Z!dbruntime.databricks_repl_contextrorQrnr$r$r%get_repl_contexts  rpc Cshtd}|s'z tj}|stdWnty&}ztd|d}~ww|ddd}|S)z{Get the default Databricks workspace hostname. Raises an error if the hostname cannot be automatically determined. ZDATABRICKS_HOSTz(context doesn't contain browserHostName.zshost was not set and cannot be automatically inferred. Set environment variable 'DATABRICKS_HOST'. Received error: Nr_zhttp://rl)osgetenvrpZbrowserHostNamer Exceptionlstriprstrip)rFrTr$r$r%get_default_hosts" rvc CsTtd}r |Sz tj}|stdW|Sty)}ztd|d}~ww)z{Get the default Databricks personal access token. Raises an error if the token cannot be automatically determined. ZDATABRICKS_TOKENz!context doesn't contain apiToken.zyapi_token was not set and cannot be automatically inferred. Set environment variable 'DATABRICKS_TOKEN'. Received error: N)rqrrrpZapiTokenrrs)rrTr$r$r%get_default_api_tokens rwrLcCs"t|tsdSd}tt||S)zJChecks if a data is a valid hexadecimal string using a regular expression.Fz^[0-9a-fA-F]+$)rbr7r:rematch)rLpatternr$r$r%_is_hex_strings r{allow_dangerous_deserializationc Csz|stdzddl}Wnty}ztd|d}~wwz |t|WSty<}ztd|d}~ww)z3Loads a pickled function from a hexadecimal string.aWThis code relies on the pickle module. You will need to set allow_dangerous_deserialization=True if you want to opt-in to allow deserialization of data using pickle.Data can be compromised by a malicious actor if not handled properly to include a malicious payload that when deserialized with pickle can execute arbitrary code on your machine.rN*Please install cloudpickle>=2.0.0. Error: zFFailed to load the pickled function from a hexadecimal string. Error: )r cloudpicklersloadsbytesfromhex)rLr|r~rTr$r$r% _load_pickled_fn_from_hex_strings$ rfnc Cslzddl}Wnty}ztd|d}~wwz||WSty5}ztd|d}~ww)z6Pickles a function and returns the hexadecimal string.rNr}zFailed to pickle the function: )r~rsrdumpshex)rr~rTr$r$r%_pickle_fn_to_hex_strings rz0.3.3z1.0z#databricks_langchain.ChatDatabricks)ZsinceZremovalZalternative_importc s*eZdZUdZeedZeed< ee dZ eed< dZ e eed< dZ e eed< dZe eed< dZe eeefed < dZe eed < dZe ed efed < d Zeed< dZeed< dZeed< dZe eeed< dZe eed< eedZeeefed< dZe eed< dZ e!ed< e"Z#e$ed<e%ddZ&e'deeeffddZ(e)dd e*d!eeefdefd"d#Z+d$effd%d& Z,e'deeeffd'd(Z-e'de.eeffd)d*Z/e'defd+d,Z0  d2d-ede eed.e e1d/edef d0d1Z2Z3S)3ra Databricks serving endpoint or a cluster driver proxy app for LLM. It supports two endpoint types: * **Serving endpoint** (recommended for both production and development). We assume that an LLM was deployed to a serving endpoint. To wrap it as an LLM you must have "Can Query" permission to the endpoint. Set ``endpoint_name`` accordingly and do not set ``cluster_id`` and ``cluster_driver_port``. If the underlying model is a model registered by MLflow, the expected model signature is: * inputs:: [{"name": "prompt", "type": "string"}, {"name": "stop", "type": "list[string]"}] * outputs: ``[{"type": "string"}]`` If the underlying model is an external or foundation model, the response from the endpoint is automatically transformed to the expected format unless ``transform_output_fn`` is provided. * **Cluster driver proxy app** (recommended for interactive development). One can load an LLM on a Databricks interactive cluster and start a local HTTP server on the driver node to serve the model at ``/`` using HTTP POST method with JSON input/output. Please use a port number between ``[3000, 8000]`` and let the server listen to the driver IP address or simply ``0.0.0.0`` instead of localhost only. To wrap it as an LLM you must have "Can Attach To" permission to the cluster. Set ``cluster_id`` and ``cluster_driver_port`` and do not set ``endpoint_name``. The expected server schema (using JSON schema) is: * inputs:: {"type": "object", "properties": { "prompt": {"type": "string"}, "stop": {"type": "array", "items": {"type": "string"}}}, "required": ["prompt"]}` * outputs: ``{"type": "string"}`` If the endpoint model signature is different or you want to set extra params, you can use `transform_input_fn` and `transform_output_fn` to apply necessary transformations before and after the query. )default_factoryrFrNrGrjrk model_kwargstransform_input_fn.r, databricksrHg temperaturenstop max_tokens extra_paramsrKFr|_clientZforbid)extrarcCs6|j|jd}|jr|j|d<|jdur|j|d<|S)N)rrrr)rrrr)r"paramsr$r$r% _llm_paramss   zDatabricks._llm_paramsr[r\r^c Cs|d}|d}|r|rtd|rd|d<n%|rn"ztj}r'||d<tdty=}ztd|d}~ww|d}|rK|rKtd|rRd|d<n|durZtdt|d krgtd | |d }rd |vswJd d|vsJd|S)NrjrGz-Cannot set both endpoint_name and cluster_id.z"Context doesn't contain clusterId.zuNeither endpoint_name nor cluster_id was set. And the cluster_id cannot be automatically determined. Received error: rkz6Cannot set both endpoint_name and cluster_driver_port.zrArDrErirprvrwr:r{rrrr$r$r$r%sF     I