LLM Mesh Integrations#

For the overall proposed structure, see LLM Mesh.

LangChain adapters#

class dataikuapi.dss.langchain.DKULLM(*args: Any, **kwargs: Any)#

Langchain-compatible wrapper around Dataiku-mediated LLMs

Note

Direct instantiation of this class is possible from within DSS, though it’s recommended to instead use dataikuapi.dss.llm.DSSLLM.as_langchain_llm().

Example:

llm = dkullm.as_langchain_llm()

# single prompt
print(llm.invoke("tell me a joke"))

# multiple prompts with batching
for response in llm.batch(["tell me a joke in English", "tell me a joke in French"]):
    print(response)

# streaming, with stop sequence
for chunk in llm.stream("Explain photosynthesis in a few words in English then French", stop=["dioxyde de"]):
    print(chunk, end="", flush=True)

llm_id: str#: LLM identifier to use

max_tokens: int = None#: Denotes the number of tokens to predict per generation. Deprecated: use key “maxOutputTokens” in field “completion_settings”.

temperature: float = None#: A non-negative float that tunes the degree of randomness in generation. Deprecated: use key “temperature” in field “completion_settings”.

top_k: int = None#: Number of tokens to pick from when sampling. Deprecated: use key “topK” in field “completion_settings”.

top_p: float = None#: Sample from the top tokens whose probabilities add up to p. Deprecated: use key “topP” in field “completion_settings”.

completion_settings: dict = {}#: Settings applied to completion queries, all keys are optional and can include: maxOutputTokens, temperature, topK, topP, frequencyPenalty, presencePenalty, logitBias, logProbs and topLogProbs.

class dataikuapi.dss.langchain.DKUChatModel(*args: Any, **kwargs: Any)#

Langchain-compatible wrapper around Dataiku-mediated chat LLMs

Note

Direct instantiation of this class is possible from within DSS, though it’s recommended to instead use dataikuapi.dss.llm.DSSLLM.as_langchain_chat_model().

Example:

from langchain_core.prompts import ChatPromptTemplate

llm = dkullm.as_langchain_chat_model()
prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
chain = prompt | llm
for chunk in chain.stream({"topic": "parrot"}):
    print(chunk.content, end="", flush=True)

llm_id: str#: LLM identifier to use

max_tokens: int = None#: Denotes the number of tokens to predict per generation. Deprecated: use key “maxOutputTokens” in field “completion_settings”.

temperature: float = None#: A non-negative float that tunes the degree of randomness in generation. Deprecated: use key “temperature” in field “completion_settings”.

top_k: int = None#: Number of tokens to pick from when sampling. Deprecated: use key “topK” in field “completion_settings”.

top_p: float = None#: Sample from the top tokens whose probabilities add up to p. Deprecated: use key “topP” in field “completion_settings”.

completion_settings: dict = {}#: Settings applied to completion queries, all keys are optional and can include: maxOutputTokens, temperature, topK, topP, frequencyPenalty, presencePenalty, logitBias, logProbs and topLogProbs.

Bind tool-like objects to this chat model.

Args:

tools: A list of tool definitions to bind to this chat model.

Can be a dictionary, pydantic model, callable, or BaseTool. Pydantic models, callables, and BaseTools will be automatically converted to their schema dictionary representation.

tool_choice: Which tool to request the model to call.

Options are:

name of the tool (str): call the corresponding tool;
“auto”: automatically select a tool (or no tool);
“none”: do not call a tool;
“any” or “required”: force at least one tool call;
True: call the one given tool (requires tools to be of length 1);
a dict of the form: {“type”: “tool_name”, “name”: “<<tool_name>>”}, or {“type”: “required”}, or {“type”: “any”} or {“type”: “none”}, or {“type”: “auto”};

strict: If specified, request the model to produce a JSON tool call that adheres to the provided schema. Support varies across models/providers. compatible: Allow DSS to modify the schema in order to increase compatibility, depending on known limitations of the model/provider. Defaults to automatic.

kwargs: Any additional parameters to bind.

class dataikuapi.dss.langchain.DKUEmbeddings(*args: Any, **kwargs: Any)#

Langchain-compatible wrapper around Dataiku-mediated embedding LLMs

Note

Direct instantiation of this class is possible from within DSS, though it’s recommended to instead use dataikuapi.dss.llm.DSSLLM.as_langchain_embeddings().

llm_id: str#: LLM identifier to use

embed_documents(texts: List[str]) → List[List[float]]#

Call out to Dataiku-mediated LLM

Args:: texts: The list of texts to embed.
Returns:: List of embeddings, one for each text.

async aembed_documents(texts: List[str]) → List[List[float]]#

embed_query(text: str) → List[float]#

async aembed_query(text: str) → List[float]#

class dataikuapi.dss.langchain.knowledge_bank.DKUKnowledgeBankRetriever(*args: Any, **kwargs: Any)#

Langchain-compatible retriever for a knowledge bank

Important

Do not instantiate directly, use dataikuapi.dss.knowledgebank.DSSKnowledgeBank.as_langchain_retriever() instead

SEARCH_PARAMETERS_NAMES: ClassVar = ['max_documents', 'search_type', 'similarity_threshold', 'mmr_documents_count', 'mmr_factor', 'hybrid_use_advanced_reranking', 'hybrid_rrf_rank_constant', 'hybrid_rrf_rank_window_size', 'filter']#: Valid parameter names for the search method

LLM Mesh Integrations#

LangChain adapters#

Related pages#