# `LangChain.ChatModels.ChatOrq`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L1)

Chat adapter for orq.ai Deployments API.

Non-streaming:
- POST https://api.orq.ai/v2/deployments/invoke

Streaming (SSE, sentinel "[DONE]"):
- POST https://api.orq.ai/v2/deployments/stream

Security:
- HTTP Bearer token (Authorization: Bearer ...). Configure via application env :langchain, :orq_key

Required body field:
- key: Deployment key to invoke.

Messages:
- Accepts roles: developer | system | user | assistant | tool
- Content supports text, image_url, file, input_audio
- Assistant may include tool_calls; Tool results are role: tool with tool_call_id

Notes:
- Azure is not supported.

## Connection Retry Behavior

The `retry_count` option controls how many times a request is retried when
a pooled HTTP connection turns out to be stale (server closed it between
requests). This is a transport-level issue where retrying with a fresh
connection is the correct response.

**Only closed-connection errors are retried.** Timeouts, rate limits (429),
overloaded (529), authentication errors, and invalid requests all return
immediately -- they are not problems that a simple retry will fix.

| `retry_count` | Total HTTP requests |
|---|---|
| `0` | 1 (no retries) |
| `1` | 2 (1 initial + 1 retry) |
| `2` (default) | 3 (1 initial + 2 retries) |

Req's built-in HTTP retry is disabled to prevent the two retry layers from
compounding. See [GitHub issue #503](https://github.com/brainlid/langchain/issues/503).

When running LLM calls from a background job queue (e.g., Oban) that has its
own retry logic, set `retry_count: 0` so there are no hidden retries:

    ChatOrq.new!(%{model: "...", retry_count: 0})

# `t`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L124)

```elixir
@type t() :: %LangChain.ChatModels.ChatOrq{
  api_key: term(),
  callbacks: term(),
  context: term(),
  documents: term(),
  endpoint: term(),
  extra_params: term(),
  file_ids: term(),
  inputs: term(),
  invoke_options: term(),
  key: term(),
  knowledge_filter: term(),
  messages_passthrough: term(),
  metadata: term(),
  model: term(),
  prefix_messages: term(),
  receive_timeout: term(),
  retry_count: term(),
  stream: term(),
  stream_endpoint: term(),
  thread: term(),
  verbose_api: term()
}
```

# `call`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L567)

Calls the orq.ai API passing the ChatOrq struct with configuration, plus
either a simple message or the list of messages to act as the prompt.

Optionally pass in a list of tools available to the LLM for requesting
execution in response (tools schema is not sent to orq; tool messages are included in messages).

# `content_part_for_api`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L427)

Convert a ContentPart to the expected map of data for the API.

# `content_parts_for_api`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L359)

Convert a list of ContentParts to the expected map of data for the API.

# `content_parts_to_string`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L367)

Convert a list of ContentParts to a string for tool results.
ORQ API expects tool result content to be a string, not an array.

# `content_to_parts`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L381)

Convert content to a list of ContentParts. Content may be a string or already a list of ContentParts.

# `content_to_single_part`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L394)

Convert content to a single ContentPart for MessageDelta. Content may be a string or already a ContentPart.

# `decode_stream`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L778)

```elixir
@spec decode_stream(
  {String.t(), String.t()},
  list()
) :: {[%{required(String.t()) => any()}], String.t()}
```

Decode a streamed response (SSE). Delegates to ChatOpenAI-compatible decoder.

# `for_api`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L273)

```elixir
@spec for_api(
  struct(),
  LangChain.Message.t()
  | LangChain.Message.ToolCall.t()
  | LangChain.Message.ToolResult.t()
  | LangChain.Message.ContentPart.t()
  | LangChain.Function.t()
) :: %{required(String.t()) => any()} | [%{required(String.t()) => any()}]
```

# `for_api`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L198)

```elixir
@spec for_api(
  t()
  | LangChain.Message.t()
  | LangChain.Message.ToolCall.t()
  | LangChain.Message.ToolResult.t()
  | LangChain.Message.ContentPart.t(),
  message :: [map()],
  LangChain.ChatModels.ChatModel.tools()
) :: %{required(atom()) => any()}
```

Return the params formatted for an API request.

# `new`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L161)

```elixir
@spec new(attrs :: map()) :: {:ok, t()} | {:error, Ecto.Changeset.t()}
```

Setup a ChatOrq client configuration.

# `new!`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L172)

```elixir
@spec new!(attrs :: map()) :: t() | no_return()
```

Setup a ChatOrq client configuration and return it or raise an error if invalid.

# `restore_from_map`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L1291)

Restores the model from the config.

# `retry_on_fallback?`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L1250)

```elixir
@spec retry_on_fallback?(LangChain.LangChainError.t()) :: boolean()
```

Determine if an error should be retried. If `true`, a fallback LLM may be
used. If `false`, the error is understood to be more fundamental with the
request rather than a service issue and it should not be retried or fallback
to another service.

# `serialize_config`
[🔗](https://github.com/brainlid/langchain/blob/v0.13.0/lib/chat_models/chat_orq.ex#L1261)

```elixir
@spec serialize_config(t()) :: %{required(String.t()) => any()}
```

Generate a config map that can later restore the model's configuration.

---

*Consult [api-reference.md](api-reference.md) for complete listing*