Path to the directory containing the documents to be ingested. This is either an absolute or relative path in the filesystem. A relative path is resolved against the current working directory at runtime.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_PATH

Does path() represent a filesystem reference or a classpath reference?

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_PATH_TYPE

Matcher used for filtering which files from the directory should be ingested. This uses the java.nio.file.FileSystem path matcher syntax. Example: glob:**.txt to recursively match all files with the .txt extension. The default is glob:**, recursively matching all files.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_PATH_MATCHER

Whether to recursively ingest documents from subdirectories.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_RECURSIVE

Maximum segment size when splitting documents, in tokens.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_MAX_SEGMENT_SIZE

Maximum overlap (in tokens) when splitting documents.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_MAX_OVERLAP_SIZE

Maximum number of results to return when querying the retrieval augmentor.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_MAX_RESULTS

The minimum score for results to return when querying the retrieval augmentor.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_MIN_SCORE

The strategy to decide whether document ingestion into the store should happen at startup or not. The default is ON. Changing to OFF generally only makes sense if running against a persistent embedding store that was already populated. When set to MANUAL, it is expected that the application will inject and call the io.quarkiverse.langchain4j.easyrag.EasyRagManualIngestion bean to trigger the ingestion when desired.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_INGESTION_STRATEGY

Whether or not to reuse embeddings. Defaults to false.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_REUSE_EMBEDDINGS_ENABLED

The file path to load/save embeddings, assuming quarkus.langchain4j.easy-rag.reuse-embeddings.enabled == true.

Defaults to easy-rag-embeddings.json in the current directory.

Environment variable: QUARKUS_LANGCHAIN4J_EASY_RAG_REUSE_EMBEDDINGS_FILE

Whether the MCP extension should automatically generate a ToolProvider that is wired up to all the configured MCP clients. The default is true if at least one MCP client is configured, false otherwise.

Environment variable: QUARKUS_LANGCHAIN4J_MCP_GENERATE_TOOL_PROVIDER

File containing the MCP servers configuration in the Claude Desktop format. This configuration can only be used to configure stdio transport type MCP servers.

This file is read at build time which means that which MCP servers the client will use, is determined at build time. However, specific configuration of each MCP server can be overridden at runtime.

Environment variable: QUARKUS_LANGCHAIN4J_MCP_CONFIG_FILE

Whether the MCP extension should automatically register a health check for configured MCP clients. The default is true if at least one MCP client is configured, false otherwise.

Environment variable: QUARKUS_LANGCHAIN4J_MCP_HEALTH_ENABLED

Whether resources should be exposed as MCP tools.

Environment variable: QUARKUS_LANGCHAIN4J_MCP_EXPOSE_RESOURCES_AS_TOOLS

Transport type

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__TRANSPORT_TYPE

The URL of the SSE endpoint. This only applies to MCP clients using the HTTP transport.

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__URL

The command to execute to spawn the MCP server process. This only applies to MCP clients using the STDIO transport.

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__COMMAND

Environment variables for the spawned MCP server process. This only applies to MCP clients using the STDIO transport.

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__ENVIRONMENT__ENV_VAR_

Whether to log requests

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__LOG_REQUESTS

Whether to log responses

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__LOG_RESPONSES

Whether to prefer MicroProfile health checks. Applies to MCP HTTP clients only.

If this property is enabled, an HTTP GET call is made to an MCP Server MicroProfile Health endpoint. MicroProfile Health endpoint URL is calculated by extracting a base URL that has no path component from the url() property and adding the microprofile-health-check-path() path to it.

Default MCP Client health check that opens a Streamable HTTP or SSE transport channel is attempted when a MicroProfile health check returns an HTTP 404 or other error status.

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__MICROPROFILE_HEALTH_CHECK

Relative path of an MCP Server MicroProfile Health endpoint. This property is effective only when the microprofile-health-check() property is enabled.

MicroProfile Health endpoint URL is calculated by extracting the base URL that has no path component from the url() property and adding a value of this property to it.

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__MICROPROFILE_HEALTH_CHECK_PATH

Timeout for tool executions performed by the MCP client

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__TOOL_EXECUTION_TIMEOUT

Timeout for resource-related operations (retrieving a list of resources as well as the actual contents of resources).

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__RESOURCES_TIMEOUT

Timeout for pinging the MCP server process to check if it’s still alive. If a ping times out, the client’s health check will start failing.

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__PING_TIMEOUT

The initial list of MCP roots that the client can present to the server. The list can be later updated programmatically during runtime. The list is formatted as key-value pairs separated by commas. For example: workspace1=/path/to/workspace1,workspace2=/path/to/workspace2

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__ROOTS

The name of the TLS configuration (bucket) used for client authentication in the TLS registry. This does not have any effect when the stdio transport is used.

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__TLS_CONFIGURATION_NAME

Whether to cache the tool list obtained from the MCP server. When set to true (the default), the tool list is cached until the server notifies of changes or the cache is manually evicted. When false, the client always fetches a fresh tool list from the server. This is useful when using MCP servers that don’t support tool list change notifications.

Environment variable: QUARKUS_LANGCHAIN4J_MCP__CLIENT_NAME__CACHE_TOOL_LIST

The base URL of the MCP registry, without the API version segment. The default value points at the official registry (https://registry.modelcontextprotocol.io).

Environment variable: QUARKUS_LANGCHAIN4J_MCP_REGISTRY_CLIENT__REGISTRY_CLIENT_NAME__BASE_URL

Whether to log requests

Environment variable: QUARKUS_LANGCHAIN4J_MCP_REGISTRY_CLIENT__REGISTRY_CLIENT_NAME__LOG_REQUESTS

Whether to log responses

Environment variable: QUARKUS_LANGCHAIN4J_MCP_REGISTRY_CLIENT__REGISTRY_CLIENT_NAME__LOG_RESPONSES

The name of the TLS configuration (bucket) that this MCP client registry will use.

Environment variable: QUARKUS_LANGCHAIN4J_MCP_REGISTRY_CLIENT__REGISTRY_CLIENT_NAME__TLS_CONFIGURATION_NAME

The read timeout for the MCP registry’s underlying http client

Environment variable: QUARKUS_LANGCHAIN4J_MCP_REGISTRY_CLIENT__REGISTRY_CLIENT_NAME__READ_TIMEOUT

The connect timeout for the MCP registry’s underlying http client

Environment variable: QUARKUS_LANGCHAIN4J_MCP_REGISTRY_CLIENT__REGISTRY_CLIENT_NAME__CONNECT_TIMEOUT

Dimension of the embeddings that will be stored in the Neo4j store.

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_DIMENSION

Label for the created nodes.

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_LABEL

Name of the property to store the embedding vectors.

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_EMBEDDING_PROPERTY

Name of the property to store embedding IDs.

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_ID_PROPERTY

Prefix to be added to the metadata keys. By default, no prefix is used.

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_METADATA_PREFIX

Name of the property to store the embedding text.

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_TEXT_PROPERTY

Name of the index to be created for vector search.

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_INDEX_NAME

Name of the database to connect to.

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_DATABASE_NAME

The query to use when retrieving embeddings. This query has to return the following columns:

Environment variable: QUARKUS_LANGCHAIN4J_NEO4J_RETRIEVAL_QUERY

The API key to Pinecone.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_API_KEY

Environment name, e.g. gcp-starter or northamerica-northeast1-gcp.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_ENVIRONMENT

ID of the project.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_PROJECT_ID

Name of the index within the project. If the index doesn’t exist, it will be created.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_INDEX_NAME

Dimension of the embeddings in the index. This is required only in case that the index doesn’t exist yet and needs to be created.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_DIMENSION

The type of the pod to use. This is only used if the index doesn’t exist yet and needs to be created. The format: One of s1, p1, or p2 appended with . and one of x1, x2, x4, or x8.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_POD_TYPE

The timeout duration for the index to become ready. Only relevant if the index doesn’t exist yet and needs to be created. If not specified, 1 minute will be used.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_INDEX_READINESS_TIMEOUT

The namespace.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_NAMESPACE

The name of the field that contains the text segment.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_TEXT_FIELD_NAME

The timeout duration for the Pinecone client. If not specified, 5 seconds will be used.

Environment variable: QUARKUS_LANGCHAIN4J_PINECONE_TIMEOUT

Base URL of the Tavily API

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_BASE_URL

API key for the Tavily API

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_API_KEY

Maximum number of results to return

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_MAX_RESULTS

The timeout duration for Tavily requests.

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_TIMEOUT

Whether requests to Tavily should be logged

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_LOG_REQUESTS

Whether responses from Tavily should be logged

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_LOG_RESPONSES

The search depth to use. This can be "basic" or "advanced". Basic is the default.

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_SEARCH_DEPTH

Include a short answer to original query. Default is false.

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_INCLUDE_ANSWER

Include the cleaned and parsed HTML content of each search result. Default is false.

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_INCLUDE_RAW_CONTENT

A list of domains to specifically include in the search results. By default all domains are included.

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_INCLUDE_DOMAINS

A list of domains to specifically exclude from the search results. By default no domains are excluded.

Environment variable: QUARKUS_LANGCHAIN4J_TAVILY_EXCLUDE_DOMAINS

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_ENABLED

Base URL of the Anthropic API

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_BASE_URL

Anthropic API key

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_API_KEY

The Anthropic version

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_VERSION

Timeout for Anthropic calls

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_TIMEOUT

Whether the Anthropic client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_LOG_REQUESTS

Whether the Anthropic client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_LOG_RESPONSES

Whether to enable the integration. Defaults to true, which means requests are made to the Anthropic provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_ENABLE_INTEGRATION

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_MODEL_NAME

What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

It is generally recommended to set this or the top-k property but not both.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_TEMPERATURE

The maximum number of tokens to generate in the completion.

The token count of your prompt plus max_tokens cannot exceed the model’s context length

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_MAX_TOKENS

Double (0.0-1.0). Nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

It is generally recommended to set this or the temperature property but not both.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_TOP_P

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_TOP_K

The maximum number of times to retry. 1 means exactly one attempt, with retrying disabled.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_MAX_RETRIES

The custom text sequences that will cause the model to stop generating

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_STOP_SEQUENCES

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_LOG_RESPONSES

Cache system messages to reduce costs for repeated prompts. Requires minimum 1024 tokens (Claude Opus/Sonnet) or 2048-4096 tokens (Haiku). Supported models: Claude Opus 4.1, Sonnet 4.5, Haiku 4.5, and later models.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_CACHE_SYSTEM_MESSAGES

Cache tool definitions to reduce costs. Requires minimum 1024 tokens (Claude Opus/Sonnet) or 2048-4096 tokens (Haiku). Supported models: Claude Opus 4.1, Sonnet 4.5, Haiku 4.5, and later models.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_CACHE_TOOLS

The thinking type to enable Claude’s reasoning process

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_THINKING_TYPE

The token budget for the model’s thinking process

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_THINKING_BUDGET_TOKENS

Whether thinking results should be returned in the response

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_THINKING_RETURN_THINKING

Whether previously stored thinking should be sent in follow-up requests

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_THINKING_SEND_THINKING

Enable interleaved thinking for Claude 4 models, allowing reasoning between tool calls. Requires Claude 4 model (e.g., claude-opus-4-20250514) and thinking.type: enabled.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC_CHAT_MODEL_THINKING_INTERLEAVED

Base URL of the Anthropic API

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__BASE_URL

Anthropic API key

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__API_KEY

The Anthropic version

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__VERSION

Timeout for Anthropic calls

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__TIMEOUT

Whether the Anthropic client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__LOG_REQUESTS

Whether the Anthropic client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__LOG_RESPONSES

Whether to enable the integration. Defaults to true, which means requests are made to the Anthropic provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__ENABLE_INTEGRATION

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_MODEL_NAME

What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

It is generally recommended to set this or the top-k property but not both.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_TEMPERATURE

The maximum number of tokens to generate in the completion.

The token count of your prompt plus max_tokens cannot exceed the model’s context length

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_MAX_TOKENS

Double (0.0-1.0). Nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

It is generally recommended to set this or the temperature property but not both.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_TOP_P

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_TOP_K

The maximum number of times to retry. 1 means exactly one attempt, with retrying disabled.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_MAX_RETRIES

The custom text sequences that will cause the model to stop generating

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_STOP_SEQUENCES

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_LOG_RESPONSES

Cache system messages to reduce costs for repeated prompts. Requires minimum 1024 tokens (Claude Opus/Sonnet) or 2048-4096 tokens (Haiku). Supported models: Claude Opus 4.1, Sonnet 4.5, Haiku 4.5, and later models.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_CACHE_SYSTEM_MESSAGES

Cache tool definitions to reduce costs. Requires minimum 1024 tokens (Claude Opus/Sonnet) or 2048-4096 tokens (Haiku). Supported models: Claude Opus 4.1, Sonnet 4.5, Haiku 4.5, and later models.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_CACHE_TOOLS

The thinking type to enable Claude’s reasoning process

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_THINKING_TYPE

The token budget for the model’s thinking process

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_THINKING_BUDGET_TOKENS

Whether thinking results should be returned in the response

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_THINKING_RETURN_THINKING

Whether previously stored thinking should be sent in follow-up requests

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_THINKING_SEND_THINKING

Enable interleaved thinking for Claude 4 models, allowing reasoning between tool calls. Requires Claude 4 model (e.g., claude-opus-4-20250514) and thinking.type: enabled.

Environment variable: QUARKUS_LANGCHAIN4J_ANTHROPIC__MODEL_NAME__CHAT_MODEL_THINKING_INTERLEAVED

If DevServices has been explicitly enabled or disabled. DevServices is generally enabled by default, unless there is an existing configuration present.

When DevServices is enabled Quarkus will attempt to automatically configure and start a database when running in Dev or Test mode and when Docker is running.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_ENABLED

The container image name to use, for container based DevServices providers.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_IMAGE_NAME

Optional fixed port the dev service will listen to.

If not defined, the port will be chosen randomly.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_PORT

Indicates if the Chroma server managed by Quarkus Dev Services is shared. When shared, Quarkus looks for running containers using label-based service discovery. If a matching container is found, it is used, and so a second one is not started. Otherwise, Dev Services for Chroma starts a new container.

The discovery uses the quarkus-dev-service-chroma label. The value is configured using the service-name property.

Container sharing is only used in dev mode.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_SHARED

The value of the quarkus-dev-service-chroma label attached to the started container. This property is used when shared is set to true. In this case, before starting a container, Dev Services for Chroma looks for a container with the quarkus-dev-service-chroma label set to the configured value. If found, it will use this container instead of starting a new one. Otherwise, it starts a new container with the quarkus-dev-service-chroma label set to the specified value.

This property is used when you need multiple shared Chroma servers.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_SERVICE_NAME

Environment variables that are passed to the container.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_DEVSERVICES_CONTAINER_ENV__CONTAINER_ENV_

URL where the Chroma database is listening for requests

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_URL

The collection name.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_COLLECTION_NAME

The timeout duration for the Chroma client. If not specified, 5 seconds will be used.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_TIMEOUT

Whether requests to Chroma should be logged

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_LOG_REQUESTS

Whether responses from Chroma should be logged

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_LOG_RESPONSES

The Chroma API version to use. V1 is deprecated (Chroma 0.x) and its support will be removed in the future. Please use Chroma 1.x which uses the V2 API.

Environment variable: QUARKUS_LANGCHAIN4J_CHROMA_API_VERSION

Whether the scoring model should be enabled.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_SCORING_MODEL_ENABLED

Base URL of the Cohere API.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_BASE_URL

Cohere API key.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_API_KEY

Timeout for Cohere calls.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_TIMEOUT

Reranking model to use. The current list of supported models can be found in the Cohere docs

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_SCORING_MODEL_MODEL_NAME

Timeout for Cohere calls

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_SCORING_MODEL_TIMEOUT

Whether embedding model requests should be logged.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_SCORING_MODEL_LOG_REQUESTS

Whether embedding model responses should be logged.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_SCORING_MODEL_LOG_RESPONSES

The maximum number of times to retry. 1 means exactly one attempt, with retrying disabled.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE_SCORING_MODEL_MAX_RETRIES

Base URL of the Cohere API.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE__MODEL_NAME__BASE_URL

Cohere API key.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE__MODEL_NAME__API_KEY

Timeout for Cohere calls.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE__MODEL_NAME__TIMEOUT

Reranking model to use. The current list of supported models can be found in the Cohere docs

Environment variable: QUARKUS_LANGCHAIN4J_COHERE__MODEL_NAME__SCORING_MODEL_MODEL_NAME

Timeout for Cohere calls

Environment variable: QUARKUS_LANGCHAIN4J_COHERE__MODEL_NAME__SCORING_MODEL_TIMEOUT

Whether embedding model requests should be logged.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE__MODEL_NAME__SCORING_MODEL_LOG_REQUESTS

Whether embedding model responses should be logged.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE__MODEL_NAME__SCORING_MODEL_LOG_RESPONSES

The maximum number of times to retry. 1 means exactly one attempt, with retrying disabled.

Environment variable: QUARKUS_LANGCHAIN4J_COHERE__MODEL_NAME__SCORING_MODEL_MAX_RETRIES

Configure the type of ChatMemory that will be used by default by the default ChatMemoryProvider bean.

The extension provides a default bean that configures ChatMemoryProvider for use with AI services registered with RegisterAiService. This bean depends uses the quarkus.langchain4j.chat-memory configuration to set things up while also depending on the presence of a bean of type ChatMemoryStore (for which the extension also provides a default in the form of InMemoryChatMemoryStore).

If token-window is used, then the application must also provide a bean of type TokenCountEstimator.

Users can choose to provide their own ChatMemoryStore bean or even their own ChatMemoryProvider bean if full control over the details is needed.

Environment variable: QUARKUS_LANGCHAIN4J_CHAT_MEMORY_TYPE

If DevServices has been explicitly enabled or disabled. DevServices is generally enabled by default, unless there is an existing configuration present.

When DevServices is enabled Quarkus will attempt to automatically serve a model if there are any matching ones.

Environment variable: QUARKUS_LANGCHAIN4J_DEVSERVICES_ENABLED

The default port where the inference server listens for requests

Environment variable: QUARKUS_LANGCHAIN4J_DEVSERVICES_PORT

Instructs Ollama to preload a model in order to get faster response times

Environment variable: QUARKUS_LANGCHAIN4J_DEVSERVICES_PRELOAD

Configuration property to enable or disable the use of the {response schema} placeholder in the @SystemMessage/@UserMessage.

Environment variable: QUARKUS_LANGCHAIN4J_RESPONSE_SCHEMA

The maximum number of messages the configured MessageWindowChatMemory will hold

Environment variable: QUARKUS_LANGCHAIN4J_CHAT_MEMORY_MEMORY_WINDOW_MAX_MESSAGES

The maximum number of tokens the configured TokenWindowChatMemory will hold

Environment variable: QUARKUS_LANGCHAIN4J_CHAT_MEMORY_TOKEN_WINDOW_MAX_TOKENS

Whether clients should log requests

Environment variable: QUARKUS_LANGCHAIN4J_LOG_REQUESTS

Whether clients should log responses

Environment variable: QUARKUS_LANGCHAIN4J_LOG_RESPONSES

Global timeout for requests to LLM APIs

Environment variable: QUARKUS_LANGCHAIN4J_TIMEOUT

Global temperature for LLM APIs

Environment variable: QUARKUS_LANGCHAIN4J_TEMPERATURE

Configures the maximum number of retries for the guardrail. Sets it to 0 to disable retries.

Environment variable: QUARKUS_LANGCHAIN4J_GUARDRAILS_MAX_RETRIES

If enabled, the prompt is included on the generated spans

Environment variable: QUARKUS_LANGCHAIN4J_TRACING_INCLUDE_PROMPT

If enabled, the completion is included on the generated spans

Environment variable: QUARKUS_LANGCHAIN4J_TRACING_INCLUDE_COMPLETION

If enabled, tool call arguments are included on the generated spans

Environment variable: QUARKUS_LANGCHAIN4J_TRACING_INCLUDE_TOOL_ARGUMENTS

If enabled, tool call results are included on the generated spans

Environment variable: QUARKUS_LANGCHAIN4J_TRACING_INCLUDE_TOOL_RESULT

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_CHAT_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_SCORING_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_EMBEDDING_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_MODERATION_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J_IMAGE_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__CHAT_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__SCORING_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__EMBEDDING_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__MODERATION_MODEL_PROVIDER

The model provider to use

Environment variable: QUARKUS_LANGCHAIN4J__MODEL_NAME__IMAGE_MODEL_PROVIDER

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_ENABLED

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_EMBEDDING_MODEL_ENABLED

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_MODERATION_MODEL_ENABLED

HuggingFace API key

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_API_KEY

Timeout for HuggingFace calls

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_TIMEOUT

The URL of the inference endpoint for the chat model.

When using Hugging Face with the inference API, the URL is https://api-inference.huggingface.co/models/<model-id>;, for example https://api-inference.huggingface.co/models/google/flan-t5-small.

When using a deployed inference endpoint, the URL is the URL of the endpoint. When using a local hugging face model, the URL is the URL of the local model.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_INFERENCE_ENDPOINT_URL

Float (0.0-100.0). The temperature of the sampling operation. 1 means regular sampling, 0 means always take the highest score, 100.0 is getting closer to uniform probability

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_TEMPERATURE

Int (0-250). The amount of new tokens to be generated, this does not include the input length it is a estimate of the size of generated text you want. Each new tokens slows down the request, so look for balance between response times and length of text generated

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_MAX_NEW_TOKENS

If set to false, the return results will not contain the original query making it easier for prompting

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_RETURN_FULL_TEXT

If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error as it will limit hanging in your application to known places

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_WAIT_FOR_MODEL

Whether or not to use sampling ; use greedy decoding otherwise.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_DO_SAMPLE

The number of highest probability vocabulary tokens to keep for top-k-filtering.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_TOP_K

If set to less than 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_TOP_P

The parameter for repetition penalty. 1.0 means no penalty. See this paper for more details.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_REPETITION_PENALTY

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_CHAT_MODEL_LOG_RESPONSES

The URL of the inference endpoint for the embedding.

When using Hugging Face with the inference API, the URL is https://api-inference.huggingface.co/pipeline/feature-extraction/<model-id>;, for example https://api-inference.huggingface.co/pipeline/feature-extraction/sentence-transformers/all-mpnet-base-v2.

When using a deployed inference endpoint, the URL is the URL of the endpoint. When using a local hugging face model, the URL is the URL of the local model.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_EMBEDDING_MODEL_INFERENCE_ENDPOINT_URL

If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error as it will limit hanging in your application to known places

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_EMBEDDING_MODEL_WAIT_FOR_MODEL

Whether the HuggingFace client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_LOG_REQUESTS

Whether the HuggingFace client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_LOG_RESPONSES

Whether or not to enable the integration. Defaults to true, which means requests are made to the OpenAI provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE_ENABLE_INTEGRATION

HuggingFace API key

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__API_KEY

Timeout for HuggingFace calls

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__TIMEOUT

The URL of the inference endpoint for the chat model.

When using Hugging Face with the inference API, the URL is https://api-inference.huggingface.co/models/<model-id>;, for example https://api-inference.huggingface.co/models/google/flan-t5-small.

When using a deployed inference endpoint, the URL is the URL of the endpoint. When using a local hugging face model, the URL is the URL of the local model.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_INFERENCE_ENDPOINT_URL

Float (0.0-100.0). The temperature of the sampling operation. 1 means regular sampling, 0 means always take the highest score, 100.0 is getting closer to uniform probability

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_TEMPERATURE

Int (0-250). The amount of new tokens to be generated, this does not include the input length it is a estimate of the size of generated text you want. Each new tokens slows down the request, so look for balance between response times and length of text generated

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_MAX_NEW_TOKENS

If set to false, the return results will not contain the original query making it easier for prompting

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_RETURN_FULL_TEXT

If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error as it will limit hanging in your application to known places

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_WAIT_FOR_MODEL

Whether or not to use sampling ; use greedy decoding otherwise.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_DO_SAMPLE

The number of highest probability vocabulary tokens to keep for top-k-filtering.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_TOP_K

If set to less than 1, only the most probable tokens with probabilities that add up to top_p or higher are kept for generation.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_TOP_P

The parameter for repetition penalty. 1.0 means no penalty. See this paper for more details.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_REPETITION_PENALTY

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__CHAT_MODEL_LOG_RESPONSES

The URL of the inference endpoint for the embedding.

When using Hugging Face with the inference API, the URL is https://api-inference.huggingface.co/pipeline/feature-extraction/<model-id>;, for example https://api-inference.huggingface.co/pipeline/feature-extraction/sentence-transformers/all-mpnet-base-v2.

When using a deployed inference endpoint, the URL is the URL of the endpoint. When using a local hugging face model, the URL is the URL of the local model.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__EMBEDDING_MODEL_INFERENCE_ENDPOINT_URL

If the model is not ready, wait for it instead of receiving 503. It limits the number of requests required to get your inference done. It is advised to only set this flag to true after receiving a 503 error as it will limit hanging in your application to known places

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__EMBEDDING_MODEL_WAIT_FOR_MODEL

Whether the HuggingFace client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__LOG_REQUESTS

Whether the HuggingFace client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__LOG_RESPONSES

Whether or not to enable the integration. Defaults to true, which means requests are made to the OpenAI provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_HUGGINGFACE__MODEL_NAME__ENABLE_INTEGRATION

The name of the Infinispan client to use. These clients are configured by means of the infinispan-client extension. If unspecified, it will use the default Infinispan client.

Environment variable: QUARKUS_LANGCHAIN4J_INFINISPAN_CLIENT_NAME

The dimension of the embedding vectors. This has to be the same as the dimension of vectors produced by the embedding model that you use. For example, AllMiniLmL6V2QuantizedEmbeddingModel produces vectors of dimension 384. OpenAI’s text-embedding-ada-002 produces vectors of dimension 1536.

Environment variable: QUARKUS_LANGCHAIN4J_INFINISPAN_DIMENSION

Name of the cache that will be used in Infinispan when searching for related embeddings. If this cache doesn’t exist, it will be created.

Environment variable: QUARKUS_LANGCHAIN4J_INFINISPAN_CACHE_NAME

The maximum distance. The most distance between vectors is how close or far apart two embeddings are.

Environment variable: QUARKUS_LANGCHAIN4J_INFINISPAN_DISTANCE

Whether Dev Services for Milvus are enabled or not.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_DEVSERVICES_ENABLED

Container image for Milvus.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_DEVSERVICES_MILVUS_IMAGE_NAME

Optional fixed port the Milvus dev service will listen to. If not defined, the port will be chosen randomly.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_DEVSERVICES_PORT

Indicates if the Dev Service containers managed by Quarkus for Milvus are shared.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_DEVSERVICES_SHARED

Service label to apply to created Dev Services containers.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_DEVSERVICES_SERVICE_NAME

The URL of the Milvus server.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_HOST

The port of the Milvus server.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_PORT

The authentication token for the Milvus server.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_TOKEN

The username for the Milvus server.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_USERNAME

The password for the Milvus server.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_PASSWORD

The timeout duration for the Milvus client. If not specified, 5 seconds will be used.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_TIMEOUT

Name of the database.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_DB_NAME

Create the collection if it does not exist yet.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_CREATE_COLLECTION

Name of the collection.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_COLLECTION_NAME

Dimension of the vectors. Only applicable when the collection yet has to be created.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_DIMENSION

Name of the field that contains the ID of the vector.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_PRIMARY_FIELD

Name of the field that contains the text from which the vector was calculated.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_TEXT_FIELD

Name of the field that contains JSON metadata associated with the text.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_METADATA_FIELD

Name of the field to store the vector in.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_VECTOR_FIELD

Description of the collection.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_DESCRIPTION

The index type to use for the collection.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_INDEX_TYPE

The metric type to use for searching.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_METRIC_TYPE

The consistency level.

Environment variable: QUARKUS_LANGCHAIN4J_MILVUS_CONSISTENCY_LEVEL

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_ENABLED

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_EMBEDDING_MODEL_ENABLED

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_MODERATION_MODEL_ENABLED

Base URL of Mistral API

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_BASE_URL

Mistral API key

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_API_KEY

Timeout for Mistral calls

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_TIMEOUT

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_MODEL_NAME

What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

It is generally recommended to set this or the top-k property but not both.

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_TEMPERATURE

The maximum number of tokens to generate in the completion.

The token count of your prompt plus max_tokens cannot exceed the model’s context length

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_MAX_TOKENS

Double (0.0-1.0). Nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

It is generally recommended to set this or the temperature property but not both.

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_TOP_P

Whether to inject a safety prompt before all conversations

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_SAFE_PROMPT

The seed to use for random sampling. If set, different calls will generate deterministic results.

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_RANDOM_SEED

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_CHAT_MODEL_LOG_RESPONSES

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_EMBEDDING_MODEL_MODEL_NAME

Whether embedding model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_EMBEDDING_MODEL_LOG_REQUESTS

Whether embedding model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_EMBEDDING_MODEL_LOG_RESPONSES

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_MODERATION_MODEL_MODEL_NAME

Whether moderation model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_MODERATION_MODEL_LOG_REQUESTS

Whether moderation model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_MODERATION_MODEL_LOG_RESPONSES

Whether the Mistral client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_LOG_REQUESTS

Whether the Mistral client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_LOG_RESPONSES

Whether to enable the integration. Defaults to true, which means requests are made to the Mistral AI provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI_ENABLE_INTEGRATION

Base URL of Mistral API

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__BASE_URL

Mistral API key

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__API_KEY

Timeout for Mistral calls

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__TIMEOUT

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__CHAT_MODEL_MODEL_NAME

What sampling temperature to use, between 0.0 and 1.0. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

It is generally recommended to set this or the top-k property but not both.

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__CHAT_MODEL_TEMPERATURE

The maximum number of tokens to generate in the completion.

The token count of your prompt plus max_tokens cannot exceed the model’s context length

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__CHAT_MODEL_MAX_TOKENS

Double (0.0-1.0). Nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

It is generally recommended to set this or the temperature property but not both.

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__CHAT_MODEL_TOP_P

Whether to inject a safety prompt before all conversations

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__CHAT_MODEL_SAFE_PROMPT

The seed to use for random sampling. If set, different calls will generate deterministic results.

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__CHAT_MODEL_RANDOM_SEED

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__CHAT_MODEL_LOG_RESPONSES

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__EMBEDDING_MODEL_MODEL_NAME

Whether embedding model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__EMBEDDING_MODEL_LOG_REQUESTS

Whether embedding model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__EMBEDDING_MODEL_LOG_RESPONSES

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__MODERATION_MODEL_MODEL_NAME

Whether moderation model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__MODERATION_MODEL_LOG_REQUESTS

Whether moderation model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__MODERATION_MODEL_LOG_RESPONSES

Whether the Mistral client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__LOG_REQUESTS

Whether the Mistral client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__LOG_RESPONSES

Whether to enable the integration. Defaults to true, which means requests are made to the Mistral AI provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_MISTRALAI__MODEL_NAME__ENABLE_INTEGRATION

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_ENABLED

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_ENABLED

If Dev Services for Ollama has been explicitly enabled or disabled. Dev Services are generally enabled by default, unless there is an existing configuration present.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_DEVSERVICES_ENABLED

The Ollama container image to use.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_DEVSERVICES_IMAGE_NAME

Model to use

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_MODEL_ID

Model to use. According to Ollama docs, the default value is nomic-embed-text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_MODEL_ID

Base URL where the Ollama serving is running

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_BASE_URL

If set, the named TLS configuration with the configured name will be applied to the REST Client

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_TLS_CONFIGURATION_NAME

Timeout for Ollama calls

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_TIMEOUT

Whether the Ollama client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_LOG_REQUESTS

Whether the Ollama client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_LOG_RESPONSES

Whether to enable the integration. Defaults to true, which means requests are made to the OpenAI provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_ENABLE_INTEGRATION

The temperature of the model. Increasing the temperature will make the model answer with more variability. A lower temperature will make the model answer more conservatively.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_TEMPERATURE

Maximum number of tokens to predict when generating text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_NUM_PREDICT

Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_STOP

Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_TOP_P

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_TOP_K

With a static number the result is always the same. With a random number the result varies Example:

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_SEED

The format to return a response in. Format can be json or a JSON schema.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_FORMAT

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_CHAT_MODEL_LOG_RESPONSES

The temperature of the model. Increasing the temperature will make the model answer with more variability. A lower temperature will make the model answer more conservatively.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_TEMPERATURE

Maximum number of tokens to predict when generating text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_NUM_PREDICT

Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_STOP

Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_TOP_P

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_TOP_K

Whether embedding model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_LOG_REQUESTS

Whether embedding model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA_EMBEDDING_MODEL_LOG_RESPONSES

Model to use

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_MODEL_ID

Model to use. According to Ollama docs, the default value is nomic-embed-text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__EMBEDDING_MODEL_MODEL_ID

Base URL where the Ollama serving is running

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__BASE_URL

If set, the named TLS configuration with the configured name will be applied to the REST Client

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__TLS_CONFIGURATION_NAME

Timeout for Ollama calls

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__TIMEOUT

Whether the Ollama client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__LOG_REQUESTS

Whether the Ollama client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__LOG_RESPONSES

Whether to enable the integration. Defaults to true, which means requests are made to the OpenAI provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__ENABLE_INTEGRATION

The temperature of the model. Increasing the temperature will make the model answer with more variability. A lower temperature will make the model answer more conservatively.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_TEMPERATURE

Maximum number of tokens to predict when generating text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_NUM_PREDICT

Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_STOP

Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_TOP_P

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_TOP_K

With a static number the result is always the same. With a random number the result varies Example:

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_SEED

The format to return a response in. Format can be json or a JSON schema.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_FORMAT

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__CHAT_MODEL_LOG_RESPONSES

The temperature of the model. Increasing the temperature will make the model answer with more variability. A lower temperature will make the model answer more conservatively.

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__EMBEDDING_MODEL_TEMPERATURE

Maximum number of tokens to predict when generating text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__EMBEDDING_MODEL_NUM_PREDICT

Sets the stop sequences to use. When this pattern is encountered the LLM will stop generating text and return

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__EMBEDDING_MODEL_STOP

Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__EMBEDDING_MODEL_TOP_P

Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__EMBEDDING_MODEL_TOP_K

Whether embedding model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__EMBEDDING_MODEL_LOG_REQUESTS

Whether embedding model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OLLAMA__MODEL_NAME__EMBEDDING_MODEL_LOG_RESPONSES

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_ENABLED

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_EMBEDDING_MODEL_ENABLED

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_MODERATION_MODEL_ENABLED

Whether the model should be enabled

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_IMAGE_MODEL_ENABLED

Base URL of OpenAI API

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_BASE_URL

If set, the named TLS configuration with the configured name will be applied to the REST Client

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_TLS_CONFIGURATION_NAME

OpenAI API key

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_API_KEY

OpenAI Organization ID (https://platform.openai.com/docs/api-reference/organization-optional)

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_ORGANIZATION_ID

Timeout for OpenAI calls

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_TIMEOUT

The maximum number of times to retry. 1 means exactly one attempt, with retrying disabled.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_MAX_RETRIES

Whether the OpenAI client should log requests

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_LOG_REQUESTS

Whether the OpenAI client should log responses

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_LOG_RESPONSES

Whether to enable the integration. Defaults to true, which means requests are made to the OpenAI provider. Set to false to disable all requests.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_ENABLE_INTEGRATION

The Proxy type

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_PROXY_TYPE

The Proxy host

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_PROXY_HOST

The Proxy port

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_PROXY_PORT

Model name to use

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_MODEL_NAME

What sampling temperature to use, with values between 0 and 2. Higher values means the model will take more risks. A value of 0.9 is good for more creative applications, while 0 (argmax sampling) is good for ones with a well-defined answer. It is recommended to alter this or topP, but not both.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_TEMPERATURE

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with topP probability mass. 0.1 means only the tokens comprising the top 10% probability mass are considered. It is recommended to alter this or temperature, but not both.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_TOP_P

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_MAX_COMPLETION_TOKENS

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model’s likelihood to talk about new topics.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_PRESENCE_PENALTY

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model’s likelihood to repeat the same line verbatim.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_FREQUENCY_PENALTY

Whether chat model requests should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_LOG_REQUESTS

Whether chat model responses should be logged

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_LOG_RESPONSES

The response format the model should use. Some models are not compatible with some response formats, make sure to review OpenAI documentation.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_RESPONSE_FORMAT

Whether responses follow JSON Schema for Structured Outputs

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_STRICT_JSON_SCHEMA

The list of stop words to use.

Environment variable: QUARKUS_LANGCHAIN4J_OPENAI_CHAT_MODEL_STOP

Constrains effort on reasoning for reasoning models. Currently supported values are minimal, low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.