langchaint
langchaint provides typed generation and embeddings with raw provider responses and per-attempt billing. Alpha: the API is unstable and may change without notice.
Purpose
langchaint provides provider-neutral async BoundLLM and EmbeddingModel interfaces.
langchaint provides no agent class or agent loop.
langchaint uses pyrefly's strict all preset.
Applications should use a strict type checker because langchaint leaves argument-type checks to static checking.
Install and authenticate
langchaint requires Python 3.13 or newer.
Applications install and pin each provider SDK.
langchaint declares no dependency extras.
Top-level import langchaint requires no provider SDK or numpy.
Backend imports report missing dependencies through ModuleNotFoundError.
| Provider | Class | Creates | Depends | Default credentials |
|---|---|---|---|---|
| Anthropic | Anthropic |
LLM |
anthropic |
ANTHROPIC_API_KEY |
| Amazon Bedrock | AnthropicBedrock |
LLM |
anthropic[bedrock] |
AWS credential provider chain |
| Amazon Bedrock | CohereBedrock |
EmbeddingModel |
boto3 and numpy |
AWS credential provider chain |
| DeepSeek | DeepSeek |
LLM |
openai |
DEEPSEEK_API_KEY |
| Gemini | Gemini |
LLM |
google-genai |
GOOGLE_API_KEY or GEMINI_API_KEY |
| OpenAI | OpenAI |
LLM, EmbeddingModel |
openai (numpy and tiktoken for embeddings) |
OPENAI_API_KEY |
| Amazon Bedrock | OpenAIBedrock |
LLM |
openai[bedrock] |
AWS credential provider chain |
Every listed class accepts client=.
Amazon Bedrock classes use the AWS credential provider chain.
It includes environment credentials, profiles, SSO, containers, and instance roles.
Pass aws_region= to select a Bedrock region explicitly.
Generation quickstart
import asyncio
from langchaint.openai import OpenAI
async def main() -> None:
openai = OpenAI()
bound_llm = openai.model("gpt-5.6-terra").bind(system_prompt="Answer clearly and concisely.")
response = await bound_llm.generate_one("Why is the sky blue?")
print(response.output, response.usage.cost_in_usd)
asyncio.run(main())
response.output is assistant text.
regional_processing=False uses the standard 1.0 token-price multiplier.
Use regional_processing=True for an endpoint with regional processing.
Pass a Pydantic model to LLM.bind(response_format=...) for validated structured output.
Embedding quickstart
import asyncio
from langchaint.openai import OpenAI
async def main() -> None:
openai = OpenAI()
embedding_model = openai.embedding_model(
"text-embedding-3-small",
dimension=1024,
)
documents = await embedding_model.embed(
["The Moon orbits Earth.", "Mars has two small moons."],
task="retrieval_document",
)
query = await embedding_model.embed(
["Which object circles Earth?"],
task="retrieval_query",
)
print(documents.shape, query.shape)
asyncio.run(main())
EmbeddingModel.embed() requires task for every adapter.
The OpenAI adapter sends no task request field.
EmbeddingModel.embed() returns normalized Float2D values with numpy.float32 elements.
Each input produces one row.
Use CohereBedrock for Cohere embeddings through Amazon Bedrock.
Share one rate-limit quota
Create one OpenAI per rate-limit quota.
openai = OpenAI(
max_concurrent_requests=8,
max_request_starts_per_second=50.0,
)
terra = openai.model("gpt-5.6-terra")
sol = openai.model("gpt-5.6-sol")
terra and sol share openai.client and one SharedBackoff.
max_concurrent_requests and max_request_starts_per_second apply across both LLM values.
An EmbeddingModel from openai.embedding_model() uses the same client and SharedBackoff.
Pass an SDK client to close it directly.
from openai import AsyncOpenAI
client = AsyncOpenAI()
openai = OpenAI(client=client)
terra = openai.model("gpt-5.6-terra")
# Use terra.
await client.close()
Binding and results
Call LLM.bind() before generate_one, generate_many, or stream_one.
Use BoundLLM.rebind() to replace selected binding fields.
Pass tools=[tool] to LLM.bind() and dispatch through BoundLLM.tool_manager.
LLM.bind(max_attempts=...) limits requests for one GenerationInput, including the first.
embedding_model(max_attempts=...) limits requests for one batch of inputs sent together, including the first.
LLM.bind() uses Adapter.automatic_cache_breakpoints_default unless automatic_cache_breakpoints overrides it.
cache_breakpoint=True requests an explicit breakpoint at that ContentPart.
GenerateResult and GenerationError include paid Usage across attempts.
More examples
examples/README.md indexes migration guidance and examples.
The examples cover structured output, batches, streaming, tools, tracing, pricing, failures, prompt caching, reasoning, embeddings, and application structure.
Development
Run scripts/CI.sh before committing.
The tests are offline and require no API keys.
License
langchaint uses the MIT License.
1 maintainer
Release files for langchaint 0.17.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| langchaint-0.17.1.tar.gz | 166.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| langchaint-0.17.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 350.6 kB
Release files / langchaint-0.17.1.tar.gz
| Download URL | langchaint-0.17.1.tar.gz |
|---|---|
| Size | 166.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
88690df6a95236535c8cf7517a29ca5e5b9b1d257c3ef1689f05c6b285669067
|
|
BLAKE2b-256 checksum How to use checksums |
037bd2092dd4b345fada1b2e852bb4581fc97052c21b24f56aae4eda7995da22
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.5 {"installer":{"name":"uv","version":"0.12.5","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / langchaint-0.17.1-py3-none-any.whl
| Download URL | langchaint-0.17.1-py3-none-any.whl |
|---|---|
| Size | 183.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
fdb7f3b7ac783fe765dab609e1b9779d6a1f7d80238a900a6d61f8749a8e0d2e
|
|
BLAKE2b-256 checksum How to use checksums |
f202e8c2700c232da5f6f97ea5223bdadd80b52ac54d1dc2cf17023f78fe48c0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.5 {"installer":{"name":"uv","version":"0.12.5","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
