LangChain - Mindsdb — ContextQMD

This documentation describes the integration of MindsDB with LangChain, a framework for developing applications powered by language models. The integration allows for the deployment of LangChain models within MindsDB, providing the models with access to data from various data sources.

Prerequisites

Before proceeding, ensure the following prerequisites are met:

Install MindsDB locally via Docker or Docker Desktop.
To use LangChain within MindsDB, install the required dependencies following this instruction.
Obtain the API key for a selected model provider that you want to use through LangChain.

<Info> Available models include the following:

OpenAI (how to get the API key)
Anthropic (how to get the API key)
Google (how to get the API key)
Ollama (how to download Ollama)
LiteLLM (use the API key of the model used via LiteLLM)
MindsDB (use any model created within MindsDB) </Info>

Setup

Create an AI engine from the LangChain handler.

sql

CREATE ML_ENGINE langchain_engine
FROM langchain
USING
      serper_api_key = 'your-serper-api-key'; -- it is an optional parameter (if provided, the model will use serper.dev search to enhance the output)

Create a model using langchain_engine as an engine and a selected model provider.

sql

CREATE MODEL langchain_model
PREDICT target_column
USING
      engine = 'langchain_engine',           -- engine name as created via CREATE ML_ENGINE
      <provider>_api_key = 'api-key-value',  -- replace <provider> with one of the available values (openai, anthropic, google, litellm)
      model_name = 'model-name',             -- optional, model to be used (for example, 'gpt-4' if 'openai_api_key' provided)
      prompt_template = 'message to the model that may include some {{input}} columns as variables',
      max_tokens = 4096; -- defines the maximum number of tokens

<Info> This handler supports [tracing features for LangChain via LangFuse](https://langfuse.com/docs/integrations/langchain/tracing). To use it, provide the following parameters in the `USING` clause:

langfuse_host,
langfuse_public_key,
langfuse_secret_key. </Info>

<Info> There are three different tools utilized by this agent:

MindsDB is the internal MindsDB executor.
Metadata fetches the metadata information for the available tables.
Write is able to write agent responses into a MindsDB data source.

Each tool exposes the internal MindsDB executor in a different way to perform its tasks, effectively enabling the agent model to read from (and potentially write to) data sources or models available in the active MindsDB project. </Info>

Create a conversational model using langchain_engine as an engine and a selected model provider.

<AccordionGroup> <Accordion title="OpenAI"> ```sql CREATE MODEL langchain_openai_model PREDICT answer USING engine = 'langchain_engine', -- engine name as created via CREATE ML_ENGINE provider = 'openai', -- one of the available providers openai_api_key = 'api-key-value', model_name = 'gpt-3.5-turbo', -- choose one of the available OpenAI models mode = 'conversational', -- conversational mode user_column = 'question', -- column name that stores input from the user assistant_column = 'answer', -- column name that stores output of the model (see PREDICT column) base_url = 'base-url-value', -- optional, default is https://api.openai.com/v1/ verbose = True, prompt_template = 'Answer the users input in a helpful way: {{question}}', max_tokens = 4096; ``` </Accordion> <Accordion title="Anthropic"> ```sql CREATE MODEL langchain_anthropic_model PREDICT answer USING engine = 'langchain_engine', -- engine name as created via CREATE ML_ENGINE provider = 'anthropic', -- one of the available providers anthropic_api_key = 'api-key-value', model_name = 'claude-2.1', -- choose one of the available OpenAI models mode = 'conversational', -- conversational mode user_column = 'question', -- column name that stores input from the user assistant_column = 'answer', -- column name that stores output of the model (see PREDICT column) verbose = True, prompt_template = 'Answer the users input in a helpful way: {{question}}', max_tokens = 4096; ``` </Accordion> <Accordion title="Ollama"> ```sql CREATE MODEL langchain_ollama_model PREDICT answer USING engine = 'langchain_engine', -- engine name as created via CREATE ML_ENGINE provider = 'ollama', -- one of the available providers model_name = 'llama2', -- choose one of the models available from Ollama mode = 'conversational', -- conversational mode user_column = 'question', -- column name that stores input from the user assistant_column = 'answer', -- column name that stores output of the model (see PREDICT column) verbose = True, prompt_template = 'Answer the users input in a helpful way: {{question}}', max_tokens = 4096; ``` Ensure to have Ollama set up locally by following this guide on [how to download Ollama](https://ollama.com/download). </Accordion> <Accordion title="LiteLLM"> ```sql CREATE MODEL langchain_litellm_model PREDICT answer USING engine = 'langchain_engine', -- engine name as created via CREATE ML_ENGINE provider = 'litellm', -- one of the available providers litellm_api_key = 'api-key-value', model_name = 'gpt-4', -- choose one of the models available from LiteLLM mode = 'conversational', -- conversational mode user_column = 'question', -- column name that stores input from the user assistant_column = 'answer', -- column name that stores output of the model (see PREDICT column) base_url = 'https://ai.dev.mindsdb.com', verbose = True, prompt_template = 'Answer the users input in a helpful way: {{question}}', max_tokens = 4096; ``` </Accordion> <Accordion title="Google"> ```sql CREATE MODEL langchain_google_model PREDICT answer USING engine = 'langchain_engine', -- engine name as created via CREATE ML_ENGINE provider = 'google', -- one of the available providers google_api_key = 'api-key-value', model_name = 'gemini-1.5-flash', -- choose one of the models available from Google mode = 'conversational', -- conversational mode user_column = 'question', -- column name that stores input from the user assistant_column = 'answer', -- column name that stores output of the model (see PREDICT column) verbose = True, prompt_template = 'Answer the users input in a helpful way: {{question}}', max_tokens = 4096; ``` </Accordion> <Accordion title="MindsDB"> ```sql CREATE MODEL langchain_mindsdb_model PREDICT answer USING engine = 'langchain_engine', -- engine name as created via CREATE ML_ENGINE provider = 'mindsdb', -- one of the available providers model_name = 'mindsdb_model', -- any model created within MindsDB mode = 'conversational', -- conversational mode user_column = 'question', -- column name that stores input from the user assistant_column = 'answer', -- column name that stores output of the model (see PREDICT column) verbose = True, prompt_template = 'Answer the users input in a helpful way: {{question}}', max_tokens = 4096; ``` </Accordion> </AccordionGroup>

Usage

The following usage examples utilize langchain_engine to create a model with the CREATE MODEL statement.

Create a model that will be used to ask questions.

sql

CREATE ML_ENGINE langchain_engine_google
FROM langchain;

CREATE MODEL langchain_google_model
PREDICT answer 
USING
     engine = 'langchain_engine_google',
     provider = 'google',
     google_api_key = 'api-key-value',
     model_name = 'gemini-1.5-flash',
     mode = 'conversational',
     user_column = 'question',
     assistant_column = 'answer',
     verbose = True,
     prompt_template = 'Answer the users input in a helpful way: {{question}}',
     max_tokens = 4096;

Ask questions.

sql

SELECT question, answer
FROM langchain_google_model
WHERE question = 'How many planets are in the solar system?';

<Tip> **Next Steps**

Go to the Use Cases section to see more examples. </Tip>