langchain-sarvam
The langchain-sarvam package provides a LangChain integration for Sarvam AI's language models, optimised for Indian languages and enterprise workloads.
Installation
pip install langchain-sarvam
Setup
Get your API key from Sarvam AI and set it as an environment variable:
export SARVAM_API_KEY="your-api-key"
Usage
Chat Model
from langchain_sarvam import ChatSarvam
llm = ChatSarvam(model="sarvam-105b")
# Invoke
response = llm.invoke("What is the capital of India?")
print(response.content)
# With system message
from langchain_core.messages import HumanMessage, SystemMessage
messages = [
SystemMessage(content="You are a helpful assistant."),
HumanMessage(content="Tell me about Indian languages."),
]
response = llm.invoke(messages)
print(response.content)
# Stream
for chunk in llm.stream("Count from 1 to 5."):
print(chunk.content, end="", flush=True)
# Async
import asyncio
response = asyncio.run(llm.ainvoke("Hello!"))
Available Models
| Model | Description |
|---|---|
sarvam-105b |
Flagship model — best quality (default) |
sarvam-30b |
Faster, lighter model |
Reasoning Mode
llm = ChatSarvam(model="sarvam-105b", reasoning_effort="high")
response = llm.invoke("Explain the Riemann hypothesis.")
# Access reasoning trace
print(response.additional_kwargs.get("reasoning_content"))
Supported values for reasoning_effort: "low", "medium", "high".
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
model |
str |
"sarvam-105b" |
Model name |
temperature |
float |
None |
Sampling temperature [0, 1] |
max_tokens |
int |
None |
Max tokens to generate |
top_p |
float |
None |
Nucleus sampling probability |
streaming |
bool |
False |
Enable streaming |
reasoning_effort |
str |
None |
Reasoning effort: "low", "medium", "high" |
api_key |
str |
env var | Sarvam API key |
base_url |
str |
"https://api.sarvam.ai/v1" |
Custom API base URL |
Development
# Install with dev dependencies
pip install -e ".[test]"
# Run unit tests
pytest tests/unit_tests/ -v
# Run integration tests (requires SARVAM_API_KEY)
pytest tests/integration_tests/ -v
License
MIT
2 maintainers
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
langchain_sarvam-0.1.2.tar.gz
(14.5 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file langchain_sarvam-0.1.2.tar.gz.
File metadata
- Download URL: langchain_sarvam-0.1.2.tar.gz
- Upload date:
- Size: 14.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
2a0dffb1ec152a27d2d8bc332169327ad16185212089c9b81d9aadf092c64207
|
|
| MD5 |
499d1dc9f252ddc1e3db91b631a444b5
|
|
| BLAKE2b-256 |
d4b4912a88315f34b23e776d286380ec19e3428a19e24fccd94b97fda3a126f3
|
Provenance
The following attestation bundles were made for langchain_sarvam-0.1.2.tar.gz:
Publisher:
release.yml on sarvamai/langchain-sarvam
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
langchain_sarvam-0.1.2.tar.gz -
Subject digest:
2a0dffb1ec152a27d2d8bc332169327ad16185212089c9b81d9aadf092c64207 - Sigstore transparency entry: 2217737183
- Sigstore integration time:
-
Permalink:
sarvamai/langchain-sarvam@610f3e75e7db752b021c70d895ddfa9be16d0882 -
Branch / Tag:
refs/tags/v0.1.2 - Owner: https://github.com/sarvamai
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@610f3e75e7db752b021c70d895ddfa9be16d0882 -
Trigger Event:
release
-
Statement type:
File details
Details for the file langchain_sarvam-0.1.2-py3-none-any.whl.
File metadata
- Download URL: langchain_sarvam-0.1.2-py3-none-any.whl
- Upload date:
- Size: 11.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
175836c4aa22013acf60c9e018cdef7a0e8f50825257a30470424b5928c90e22
|
|
| MD5 |
aea4d07b5a0c543dcf8a4420546574bc
|
|
| BLAKE2b-256 |
5fd525b21fdab9ba9151d91d2197f6f2d1fbc4fc8c142f9903d000e735fe4afd
|
Provenance
The following attestation bundles were made for langchain_sarvam-0.1.2-py3-none-any.whl:
Publisher:
release.yml on sarvamai/langchain-sarvam
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
langchain_sarvam-0.1.2-py3-none-any.whl -
Subject digest:
175836c4aa22013acf60c9e018cdef7a0e8f50825257a30470424b5928c90e22 - Sigstore transparency entry: 2217737791
- Sigstore integration time:
-
Permalink:
sarvamai/langchain-sarvam@610f3e75e7db752b021c70d895ddfa9be16d0882 -
Branch / Tag:
refs/tags/v0.1.2 - Owner: https://github.com/sarvamai
-
Access:
private
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
release.yml@610f3e75e7db752b021c70d895ddfa9be16d0882 -
Trigger Event:
release
-
Statement type:
