mirror of
https://github.com/hwchase17/langchain.git
synced 2026-05-07 03:52:37 +00:00
f027696b5f
**Please tag this issue with `nvidia_genai`**
- **Description:** Added new Runnables for integration NVIDIA Riva into
LCEL chains for Automatic Speech Recognition (ASR) and Text To Speech
(TTS).
- **Issue:** N/A
- **Dependencies:** To use these runnables, the NVIDIA Riva client
libraries are required. It they are not installed, an error will be
raised instructing how to install them. The Runnables can be safely
imported without the riva client libraries.
- **Twitter handle:** N/A
All of the Riva Runnables are inside a single folder in the Utilities
module. In this folder are four files:
- common.py - Contains all code that is common to both TTS and ASR
- stream.py - Contains a class representing an audio stream that allows
the end user to put data into the stream like a queue.
- asr.py - Contains the RivaASR runnable
- tts.py - Contains the RivaTTS runnable
The following Python function is an example of creating a chain that
makes use of both of these Runnables:
```python
def create(
config: Configuration,
audio_encoding: RivaAudioEncoding,
sample_rate: int,
audio_channels: int = 1,
) -> Runnable[ASRInputType, TTSOutputType]:
"""Create a new instance of the chain."""
_LOGGER.info("Instantiating the chain.")
# create the riva asr client
riva_asr = RivaASR(
url=str(config.riva_asr.service.url),
ssl_cert=config.riva_asr.service.ssl_cert,
encoding=audio_encoding,
audio_channel_count=audio_channels,
sample_rate_hertz=sample_rate,
profanity_filter=config.riva_asr.profanity_filter,
enable_automatic_punctuation=config.riva_asr.enable_automatic_punctuation,
language_code=config.riva_asr.language_code,
)
# create the prompt template
prompt = PromptTemplate.from_template("{user_input}")
# model = ChatOpenAI()
model = ChatNVIDIA(model="mixtral_8x7b") # type: ignore
# create the riva tts client
riva_tts = RivaTTS(
url=str(config.riva_asr.service.url),
ssl_cert=config.riva_asr.service.ssl_cert,
output_directory=config.riva_tts.output_directory,
language_code=config.riva_tts.language_code,
voice_name=config.riva_tts.voice_name,
)
# construct and return the chain
return {"user_input": riva_asr} | prompt | model | riva_tts # type: ignore
```
The following code is an example of creating a new audio stream for
Riva:
```python
input_stream = AudioStream(maxsize=1000)
# Send bytes into the stream
for chunk in audio_chunks:
await input_stream.aput(chunk)
input_stream.close()
```
The following code is an example of how to execute the chain with
RivaASR and RivaTTS
```python
output_stream = asyncio.Queue()
while not input_stream.complete:
async for chunk in chain.astream(input_stream):
output_stream.put(chunk)
```
Everything should be async safe and thread safe. Audio data can be put
into the input stream while the chain is running without interruptions.
---------
Co-authored-by: Hayden Wolff <hwolff@nvidia.com>
Co-authored-by: Hayden Wolff <hwolff@Haydens-Laptop.local>
Co-authored-by: Hayden Wolff <haydenwolff99@gmail.com>
Co-authored-by: Erick Friis <erick@langchain.dev>
317 lines
9.8 KiB
TOML
317 lines
9.8 KiB
TOML
[tool.poetry]
|
|
name = "langchain-community"
|
|
version = "0.0.17"
|
|
description = "Community contributed LangChain integrations."
|
|
authors = []
|
|
license = "MIT"
|
|
readme = "README.md"
|
|
repository = "https://github.com/langchain-ai/langchain"
|
|
|
|
[tool.poetry.dependencies]
|
|
python = ">=3.8.1,<4.0"
|
|
langchain-core = ">=0.1.16,<0.2"
|
|
SQLAlchemy = ">=1.4,<3"
|
|
requests = "^2"
|
|
PyYAML = ">=5.3"
|
|
numpy = "^1"
|
|
aiohttp = "^3.8.3"
|
|
tenacity = "^8.1.0"
|
|
dataclasses-json = ">= 0.5.7, < 0.7"
|
|
langsmith = ">=0.0.83,<0.1"
|
|
tqdm = {version = ">=4.48.0", optional = true}
|
|
openapi-pydantic = {version = "^0.3.2", optional = true}
|
|
faiss-cpu = {version = "^1", optional = true}
|
|
beautifulsoup4 = {version = "^4", optional = true}
|
|
jinja2 = {version = "^3", optional = true}
|
|
cohere = {version = "^4", optional = true}
|
|
openai = {version = "<2", optional = true}
|
|
arxiv = {version = "^1.4", optional = true}
|
|
pypdf = {version = "^3.4.0", optional = true}
|
|
aleph-alpha-client = {version="^2.15.0", optional = true}
|
|
gradientai = {version="^1.4.0", optional = true}
|
|
pgvector = {version = "^0.1.6", optional = true}
|
|
atlassian-python-api = {version = "^3.36.0", optional=true}
|
|
html2text = {version="^2020.1.16", optional=true}
|
|
numexpr = {version="^2.8.6", optional=true}
|
|
jq = {version = "^1.4.1", optional = true}
|
|
pdfminer-six = {version = "^20221105", optional = true}
|
|
lxml = {version = "^4.9.2", optional = true}
|
|
pymupdf = {version = "^1.22.3", optional = true}
|
|
rapidocr-onnxruntime = {version = "^1.3.2", optional = true, python = ">=3.8.1,<3.12"}
|
|
pypdfium2 = {version = "^4.10.0", optional = true}
|
|
gql = {version = "^3.4.1", optional = true}
|
|
pandas = {version = "^2.0.1", optional = true}
|
|
telethon = {version = "^1.28.5", optional = true}
|
|
chardet = {version="^5.1.0", optional=true}
|
|
requests-toolbelt = {version = "^1.0.0", optional = true}
|
|
scikit-learn = {version = "^1.2.2", optional = true}
|
|
py-trello = {version = "^0.19.0", optional = true}
|
|
bibtexparser = {version = "^1.4.0", optional = true}
|
|
pyspark = {version = "^3.4.0", optional = true}
|
|
mwparserfromhell = {version = "^0.6.4", optional = true}
|
|
mwxml = {version = "^0.3.3", optional = true}
|
|
esprima = {version = "^4.0.1", optional = true}
|
|
streamlit = {version = "^1.18.0", optional = true, python = ">=3.8.1,<3.9.7 || >3.9.7,<4.0"}
|
|
psychicapi = {version = "^0.8.0", optional = true}
|
|
cassio = {version = "^0.1.0", optional = true}
|
|
sympy = {version = "^1.12", optional = true}
|
|
rapidfuzz = {version = "^3.1.1", optional = true}
|
|
jsonschema = {version = ">1", optional = true}
|
|
rank-bm25 = {version = "^0.2.2", optional = true}
|
|
geopandas = {version = "^0.13.1", optional = true}
|
|
gitpython = {version = "^3.1.32", optional = true}
|
|
feedparser = {version = "^6.0.10", optional = true}
|
|
newspaper3k = {version = "^0.2.8", optional = true}
|
|
xata = {version = "^1.0.0a7", optional = true}
|
|
xmltodict = {version = "^0.13.0", optional = true}
|
|
markdownify = {version = "^0.11.6", optional = true}
|
|
assemblyai = {version = "^0.17.0", optional = true}
|
|
sqlite-vss = {version = "^0.1.2", optional = true}
|
|
motor = {version = "^3.3.1", optional = true}
|
|
timescale-vector = {version = "^0.0.1", optional = true}
|
|
typer = {version= "^0.9.0", optional = true}
|
|
anthropic = {version = "^0.3.11", optional = true}
|
|
aiosqlite = {version = "^0.19.0", optional = true}
|
|
rspace_client = {version = "^2.5.0", optional = true}
|
|
upstash-redis = {version = "^0.15.0", optional = true}
|
|
google-cloud-documentai = {version = "^2.20.1", optional = true}
|
|
fireworks-ai = {version = "^0.9.0", optional = true}
|
|
javelin-sdk = {version = "^0.1.8", optional = true}
|
|
hologres-vector = {version = "^0.0.6", optional = true}
|
|
praw = {version = "^7.7.1", optional = true}
|
|
msal = {version = "^1.25.0", optional = true}
|
|
databricks-vectorsearch = {version = "^0.21", optional = true}
|
|
dgml-utils = {version = "^0.3.0", optional = true}
|
|
datasets = {version = "^2.15.0", optional = true}
|
|
azure-ai-documentintelligence = {version = "^1.0.0b1", optional = true}
|
|
oracle-ads = {version = "^2.9.1", optional = true}
|
|
zhipuai = {version = "^1.0.7", optional = true}
|
|
httpx = {version = "^0.24.1", optional = true}
|
|
elasticsearch = {version = "^8.12.0", optional = true}
|
|
hdbcli = {version = "^2.19.21", optional = true}
|
|
oci = {version = "^2.119.1", optional = true}
|
|
rdflib = {version = "7.0.0", optional = true}
|
|
nvidia-riva-client = {version = "^2.14.0", optional = true}
|
|
|
|
[tool.poetry.group.test]
|
|
optional = true
|
|
|
|
[tool.poetry.group.test.dependencies]
|
|
# The only dependencies that should be added are
|
|
# dependencies used for running tests (e.g., pytest, freezegun, response).
|
|
# Any dependencies that do not meet that criteria will be removed.
|
|
pytest = "^7.3.0"
|
|
pytest-cov = "^4.1.0"
|
|
pytest-dotenv = "^0.5.2"
|
|
duckdb-engine = "^0.9.2"
|
|
pytest-watcher = "^0.2.6"
|
|
freezegun = "^1.2.2"
|
|
responses = "^0.22.0"
|
|
pytest-asyncio = "^0.20.3"
|
|
lark = "^1.1.5"
|
|
pandas = "^2.0.0"
|
|
pytest-mock = "^3.10.0"
|
|
pytest-socket = "^0.6.0"
|
|
syrupy = "^4.0.2"
|
|
requests-mock = "^1.11.0"
|
|
langchain-core = {path = "../core", develop = true}
|
|
|
|
[tool.poetry.group.codespell]
|
|
optional = true
|
|
|
|
[tool.poetry.group.codespell.dependencies]
|
|
codespell = "^2.2.0"
|
|
|
|
[tool.poetry.group.test_integration]
|
|
optional = true
|
|
|
|
[tool.poetry.group.test_integration.dependencies]
|
|
# Do not add dependencies in the test_integration group
|
|
# Instead:
|
|
# 1. Add an optional dependency to the main group
|
|
# poetry add --optional [package name]
|
|
# 2. Add the package name to the extended_testing extra (find it below)
|
|
# 3. Relock the poetry file
|
|
# poetry lock --no-update
|
|
# 4. Favor unit tests not integration tests.
|
|
# Use the @pytest.mark.requires(pkg_name) decorator in unit_tests.
|
|
# Your tests should not rely on network access, as it prevents other
|
|
# developers from being able to easily run them.
|
|
# Instead write unit tests that use the `responses` library or mock.patch with
|
|
# fixtures. Keep the fixtures minimal.
|
|
# See Contributing Guide for more instructions on working with optional dependencies.
|
|
# https://python.langchain.com/docs/contributing/code#working-with-optional-dependencies
|
|
pytest-vcr = "^1.0.2"
|
|
wrapt = "^1.15.0"
|
|
openai = "^1"
|
|
python-dotenv = "^1.0.0"
|
|
cassio = "^0.1.0"
|
|
tiktoken = ">=0.3.2,<0.6.0"
|
|
anthropic = "^0.3.11"
|
|
langchain-core = { path = "../core", develop = true }
|
|
fireworks-ai = "^0.9.0"
|
|
boto3 = ">=1.28.57,<2"
|
|
google-cloud-aiplatform = ">=1.37.0,<2"
|
|
|
|
[tool.poetry.group.lint]
|
|
optional = true
|
|
|
|
[tool.poetry.group.lint.dependencies]
|
|
ruff = "^0.1.5"
|
|
|
|
[tool.poetry.group.typing.dependencies]
|
|
mypy = "^0.991"
|
|
types-pyyaml = "^6.0.12.2"
|
|
types-requests = "^2.28.11.5"
|
|
types-toml = "^0.10.8.1"
|
|
types-pytz = "^2023.3.0.0"
|
|
types-chardet = "^5.0.4.6"
|
|
types-redis = "^4.3.21.6"
|
|
mypy-protobuf = "^3.0.0"
|
|
langchain-core = {path = "../core", develop = true}
|
|
|
|
[tool.poetry.group.dev]
|
|
optional = true
|
|
|
|
[tool.poetry.group.dev.dependencies]
|
|
jupyter = "^1.0.0"
|
|
setuptools = "^67.6.1"
|
|
langchain-core = {path = "../core", develop = true}
|
|
|
|
[tool.poetry.extras]
|
|
|
|
cli = ["typer"]
|
|
|
|
# An extra used to be able to add extended testing.
|
|
# Please use new-line on formatting to make it easier to add new packages without
|
|
# merge-conflicts
|
|
extended_testing = [
|
|
"aleph-alpha-client",
|
|
"aiosqlite",
|
|
"assemblyai",
|
|
"beautifulsoup4",
|
|
"bibtexparser",
|
|
"cassio",
|
|
"chardet",
|
|
"datasets",
|
|
"google-cloud-documentai",
|
|
"esprima",
|
|
"jq",
|
|
"pdfminer-six",
|
|
"pgvector",
|
|
"pypdf",
|
|
"pymupdf",
|
|
"pypdfium2",
|
|
"tqdm",
|
|
"lxml",
|
|
"atlassian-python-api",
|
|
"mwparserfromhell",
|
|
"mwxml",
|
|
"msal",
|
|
"pandas",
|
|
"telethon",
|
|
"psychicapi",
|
|
"gql",
|
|
"gradientai",
|
|
"requests-toolbelt",
|
|
"html2text",
|
|
"numexpr",
|
|
"py-trello",
|
|
"scikit-learn",
|
|
"streamlit",
|
|
"pyspark",
|
|
"openai",
|
|
"sympy",
|
|
"rapidfuzz",
|
|
"jsonschema",
|
|
"rank-bm25",
|
|
"geopandas",
|
|
"jinja2",
|
|
"gitpython",
|
|
"newspaper3k",
|
|
"nvidia-riva-client",
|
|
"feedparser",
|
|
"xata",
|
|
"xmltodict",
|
|
"faiss-cpu",
|
|
"openapi-pydantic",
|
|
"markdownify",
|
|
"arxiv",
|
|
"sqlite-vss",
|
|
"rapidocr-onnxruntime",
|
|
"motor",
|
|
"timescale-vector",
|
|
"anthropic",
|
|
"upstash-redis",
|
|
"rspace_client",
|
|
"fireworks-ai",
|
|
"javelin-sdk",
|
|
"hologres-vector",
|
|
"praw",
|
|
"databricks-vectorsearch",
|
|
"dgml-utils",
|
|
"cohere",
|
|
"azure-ai-documentintelligence",
|
|
"oracle-ads",
|
|
"zhipuai",
|
|
"httpx",
|
|
"elasticsearch",
|
|
"hdbcli",
|
|
"oci",
|
|
"rdflib"
|
|
]
|
|
|
|
[tool.ruff]
|
|
select = [
|
|
"E", # pycodestyle
|
|
"F", # pyflakes
|
|
"I", # isort
|
|
]
|
|
exclude = [
|
|
"tests/examples/non-utf8-encoding.py",
|
|
"tests/integration_tests/examples/non-utf8-encoding.py",
|
|
]
|
|
|
|
[tool.mypy]
|
|
ignore_missing_imports = "True"
|
|
disallow_untyped_defs = "True"
|
|
exclude = ["notebooks", "examples", "example_data"]
|
|
|
|
[tool.coverage.run]
|
|
omit = [
|
|
"tests/*",
|
|
]
|
|
|
|
[build-system]
|
|
requires = ["poetry-core>=1.0.0"]
|
|
build-backend = "poetry.core.masonry.api"
|
|
|
|
[tool.pytest.ini_options]
|
|
# --strict-markers will raise errors on unknown marks.
|
|
# https://docs.pytest.org/en/7.1.x/how-to/mark.html#raising-errors-on-unknown-marks
|
|
#
|
|
# https://docs.pytest.org/en/7.1.x/reference/reference.html
|
|
# --strict-config any warnings encountered while parsing the `pytest`
|
|
# section of the configuration file raise errors.
|
|
#
|
|
# https://github.com/tophat/syrupy
|
|
# --snapshot-warn-unused Prints a warning on unused snapshots rather than fail the test suite.
|
|
addopts = "--strict-markers --strict-config --durations=5 --snapshot-warn-unused -vv"
|
|
# Registering custom markers.
|
|
# https://docs.pytest.org/en/7.1.x/example/markers.html#registering-markers
|
|
markers = [
|
|
"requires: mark tests as requiring a specific library",
|
|
"scheduled: mark tests to run in scheduled testing",
|
|
"compile: mark placeholder test used to compile integration tests without running them"
|
|
]
|
|
asyncio_mode = "auto"
|
|
|
|
[tool.codespell]
|
|
skip = '.git,*.pdf,*.svg,*.pdf,*.yaml,*.ipynb,poetry.lock,*.min.js,*.css,package-lock.json,example_data,_dist,examples,*.trig'
|
|
# Ignore latin etc
|
|
ignore-regex = '.*(Stati Uniti|Tense=Pres).*'
|
|
# whats is a typo but used frequently in queries so kept as is
|
|
# aapply - async apply
|
|
# unsecure - typo but part of API, decided to not bother for now
|
|
ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogyny,unsecure,damon,crate,aadd,symbl,precesses,accademia,nin'
|