dwani 0.1.0__py3-none-any.whl

__init__.py

@@ -0,0 +1,44 @@
+from .client import DhwaniClient
+
+api_key = None
+api_base = "http://localhost:7860"
+
+_client = None
+
+def _get_client():
+    global _client
+    if _client is None:
+        _client = DhwaniClient(api_key=api_key, api_base=api_base)
+    return _client
+
+class Chat:
+    @staticmethod
+    def create(prompt):
+        return _get_client().chat(prompt)
+
+class Audio:
+    @staticmethod
+    def speech(input, voice, model, response_format="mp3", output_file=None):
+        return _get_client().speech(input, voice, model, response_format, output_file)
+
+class Vision:
+    @staticmethod
+    def caption(file_path, length="short"):
+        return _get_client().caption(file_path, length)
+    @staticmethod
+    def visual_query(file_path, query):
+        return _get_client().visual_query(file_path, query)
+    @staticmethod
+    def detect(file_path, object_type):
+        return _get_client().detect(file_path, object_type)
+    @staticmethod
+    def point(file_path, object_type):
+        return _get_client().point(file_path, object_type)
+
+class ASR:
+    @staticmethod
+    def transcribe(file_path, language):
+        return _get_client().transcribe(file_path, language)
+    @staticmethod
+    def transcribe_batch(file_paths, language):
+        return _get_client().transcribe_batch(file_paths, language)

client.py

@@ -0,0 +1,127 @@
+import os
+import requests
+from .exceptions import DhwaniAPIError
+
+class DhwaniClient:
+    def __init__(self, api_key=None, api_base=None):
+        self.api_key = api_key or os.getenv("DHWANI_API_KEY")
+        self.api_base = api_base or os.getenv("DHWANI_API_BASE", "http://localhost:7860")
+        if not self.api_key:
+            raise ValueError("DHWANI_API_KEY not set")
+
+    def _headers(self):
+        return {"X-API-Key": self.api_key}
+
+    def chat(self, prompt):
+        resp = requests.post(
+            f"{self.api_base}/chat",
+            headers={**self._headers(), "Content-Type": "application/json"},
+            json={"prompt": prompt}
+        )
+        if resp.status_code != 200:
+            raise DhwaniAPIError(resp)
+        return resp.json()
+
+    def speech(self, input, voice, model, response_format="mp3", output_file=None):
+        data = {
+            "input": input,
+            "voice": voice,
+            "model": model,
+            "response_format": response_format
+        }
+        resp = requests.post(
+            f"{self.api_base}/v1/audio/speech",
+            headers={**self._headers(), "Content-Type": "application/json"},
+            json=data,
+            stream=True
+        )
+        if resp.status_code != 200:
+            raise DhwaniAPIError(resp)
+        if output_file:
+            with open(output_file, "wb") as f:
+                for chunk in resp.iter_content(chunk_size=8192):
+                    f.write(chunk)
+            return output_file
+        return resp.content
+
+    def caption(self, file_path, length="short"):
+        with open(file_path, "rb") as f:
+            files = {"file": f}
+            data = {"length": length}
+            resp = requests.post(
+                f"{self.api_base}/caption/",
+                headers=self._headers(),
+                files=files,
+                data=data
+            )
+        if resp.status_code != 200:
+            raise DhwaniAPIError(resp)
+        return resp.json()
+
+    def visual_query(self, file_path, query):
+        with open(file_path, "rb") as f:
+            files = {"file": f}
+            data = {"query": query}
+            resp = requests.post(
+                f"{self.api_base}/visual_query/",
+                headers=self._headers(),
+                files=files,
+                data=data
+            )
+        if resp.status_code != 200:
+            raise DhwaniAPIError(resp)
+        return resp.json()
+
+    def detect(self, file_path, object_type):
+        with open(file_path, "rb") as f:
+            files = {"file": f}
+            data = {"object_type": object_type}
+            resp = requests.post(
+                f"{self.api_base}/detect/",
+                headers=self._headers(),
+                files=files,
+                data=data
+            )
+        if resp.status_code != 200:
+            raise DhwaniAPIError(resp)
+        return resp.json()
+
+    def point(self, file_path, object_type):
+        with open(file_path, "rb") as f:
+            files = {"file": f}
+            data = {"object_type": object_type}
+            resp = requests.post(
+                f"{self.api_base}/point/",
+                headers=self._headers(),
+                files=files,
+                data=data
+            )
+        if resp.status_code != 200:
+            raise DhwaniAPIError(resp)
+        return resp.json()
+
+    def transcribe(self, file_path, language):
+        with open(file_path, "rb") as f:
+            files = {"file": f}
+            resp = requests.post(
+                f"{self.api_base}/transcribe/?language={language}",
+                headers=self._headers(),
+                files=files
+            )
+        if resp.status_code != 200:
+            raise DhwaniAPIError(resp)
+        return resp.json()
+
+    def transcribe_batch(self, file_paths, language):
+        files = [("files", open(fp, "rb")) for fp in file_paths]
+        resp = requests.post(
+            f"{self.api_base}/transcribe_batch/?language={language}",
+            headers=self._headers(),
+            files=files
+        )
+        # Close all files
+        for _, f in files:
+            f.close()
+        if resp.status_code != 200:
+            raise DhwaniAPIError(resp)
+        return resp.json()

dwani-0.1.0.dist-info/METADATA

@@ -0,0 +1,181 @@
+Metadata-Version: 2.4
+Name: dwani
+Version: 0.1.0
+Summary: Multimodal AI server for Indian languages (speech, vision, LLMs, TTS, ASR, etc.)
+Author-email: sachin <python@dwani.ai>
+Project-URL: Homepage, https://github.com/dwani-ai/dwani-server
+Project-URL: Source, https://github.com/dwani-ai/dwani-server
+Project-URL: Issues, https://github.com/dwani-ai/dwani-server/issues
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: torch==2.6.0
+Requires-Dist: torchvision
+Requires-Dist: torchaudio==2.6.0
+Requires-Dist: accelerate==1.6.0
+Requires-Dist: bitsandbytes==0.45.5
+Requires-Dist: pillow==11.1.0
+Requires-Dist: uvicorn==0.34.0
+Requires-Dist: fastapi==0.115.12
+Requires-Dist: pydantic-settings
+Requires-Dist: slowapi
+Requires-Dist: python-multipart==0.0.20
+Requires-Dist: packaging==24.2
+Requires-Dist: tenacity
+Requires-Dist: num2words
+Requires-Dist: sentencepiece
+Requires-Dist: huggingface-hub==0.27.1
+Requires-Dist: openai
+Requires-Dist: flash-attn
+Requires-Dist: onnx==1.16.2
+Requires-Dist: onnxruntime==1.21.0
+Requires-Dist: onnxruntime-gpu==1.21.0
+Requires-Dist: pydub==0.25.1
+Requires-Dist: hf_xet
+Requires-Dist: aiofiles==23.2.1
+Requires-Dist: aiohappyeyeballs==2.6.1
+Requires-Dist: aiohttp==3.11.16
+Requires-Dist: aiosignal==1.3.2
+Requires-Dist: annotated-types==0.7.0
+Requires-Dist: antlr4-python3-runtime==4.9.3
+Requires-Dist: anyio==4.9.0
+Requires-Dist: async-timeout==5.0.1
+Requires-Dist: attrs==25.3.0
+Requires-Dist: audioread==3.0.1
+Requires-Dist: boto3==1.37.29
+Requires-Dist: botocore==1.37.29
+Requires-Dist: cached_path==1.7.1
+Requires-Dist: cachetools==5.5.2
+Requires-Dist: certifi==2025.1.31
+Requires-Dist: cffi==1.17.1
+Requires-Dist: charset-normalizer==3.4.1
+Requires-Dist: click==8.1.8
+Requires-Dist: contourpy==1.3.1
+Requires-Dist: cycler==0.12.1
+Requires-Dist: datasets==3.5.0
+Requires-Dist: decorator==5.2.1
+Requires-Dist: dill==0.3.8
+Requires-Dist: docker-pycreds==0.4.0
+Requires-Dist: einops==0.8.1
+Requires-Dist: einx==0.3.0
+Requires-Dist: ema-pytorch==0.7.7
+Requires-Dist: encodec==0.1.1
+Requires-Dist: exceptiongroup==1.2.2
+Requires-Dist: f5-tts==1.1.0
+Requires-Dist: ffmpy==0.5.0
+Requires-Dist: filelock==3.18.0
+Requires-Dist: fonttools==4.57.0
+Requires-Dist: frozendict==2.4.6
+Requires-Dist: frozenlist==1.5.0
+Requires-Dist: fsspec==2024.12.0
+Requires-Dist: gitdb==4.0.12
+Requires-Dist: GitPython==3.1.44
+Requires-Dist: google-api-core==2.24.2
+Requires-Dist: google-auth==2.38.0
+Requires-Dist: google-cloud-core==2.4.3
+Requires-Dist: google-cloud-storage==2.19.0
+Requires-Dist: google-crc32c==1.7.1
+Requires-Dist: google-resumable-media==2.7.2
+Requires-Dist: googleapis-common-protos==1.69.2
+Requires-Dist: gradio==5.14.0
+Requires-Dist: gradio_client==1.7.0
+Requires-Dist: groovy==0.1.2
+Requires-Dist: h11==0.14.0
+Requires-Dist: httpcore==1.0.7
+Requires-Dist: httpx==0.28.1
+Requires-Dist: hydra-core==1.3.2
+Requires-Dist: idna==3.10
+Requires-Dist: jieba==0.42.1
+Requires-Dist: Jinja2==3.1.6
+Requires-Dist: jmespath==1.0.1
+Requires-Dist: joblib==1.4.2
+Requires-Dist: kiwisolver==1.4.8
+Requires-Dist: lazy_loader==0.4
+Requires-Dist: librosa==0.11.0
+Requires-Dist: llvmlite==0.44.0
+Requires-Dist: loguru==0.7.3
+Requires-Dist: markdown-it-py==3.0.0
+Requires-Dist: MarkupSafe==2.1.5
+Requires-Dist: matplotlib==3.10.1
+Requires-Dist: mdurl==0.1.2
+Requires-Dist: mpmath==1.3.0
+Requires-Dist: msgpack==1.1.0
+Requires-Dist: multidict==6.3.2
+Requires-Dist: multiprocess==0.70.16
+Requires-Dist: networkx==3.4.2
+Requires-Dist: numba==0.61.0
+Requires-Dist: numpy==1.26.4
+Requires-Dist: nvidia-cublas-cu12==12.4.5.8
+Requires-Dist: nvidia-cuda-cupti-cu12==12.4.127
+Requires-Dist: nvidia-cuda-nvrtc-cu12==12.4.127
+Requires-Dist: nvidia-cuda-runtime-cu12==12.4.127
+Requires-Dist: nvidia-cudnn-cu12==9.1.0.70
+Requires-Dist: nvidia-cufft-cu12==11.2.1.3
+Requires-Dist: nvidia-curand-cu12==10.3.5.147
+Requires-Dist: nvidia-cusolver-cu12==11.6.1.9
+Requires-Dist: nvidia-cusparse-cu12==12.3.1.170
+Requires-Dist: nvidia-cusparselt-cu12==0.6.2
+Requires-Dist: nvidia-nccl-cu12==2.21.5
+Requires-Dist: nvidia-nvjitlink-cu12==12.4.127
+Requires-Dist: nvidia-nvtx-cu12==12.4.127
+Requires-Dist: omegaconf==2.3.0
+Requires-Dist: orjson==3.10.16
+Requires-Dist: pandas==2.2.3
+Requires-Dist: platformdirs==4.3.7
+Requires-Dist: pooch==1.8.2
+Requires-Dist: propcache==0.3.1
+Requires-Dist: proto-plus==1.26.1
+Requires-Dist: protobuf
+Requires-Dist: psutil==7.0.0
+Requires-Dist: pyarrow==19.0.1
+Requires-Dist: pyasn1==0.6.1
+Requires-Dist: pyasn1_modules==0.4.2
+Requires-Dist: pycparser==2.22
+Requires-Dist: pydantic==2.10.6
+Requires-Dist: pydantic_core==2.27.2
+Requires-Dist: Pygments==2.19.1
+Requires-Dist: pyparsing==3.2.3
+Requires-Dist: pypinyin==0.54.0
+Requires-Dist: python-dateutil==2.9.0.post0
+Requires-Dist: pytz==2025.2
+Requires-Dist: PyYAML==6.0.2
+Requires-Dist: regex==2024.11.6
+Requires-Dist: requests==2.32.3
+Requires-Dist: rich==13.9.4
+Requires-Dist: rsa==4.9
+Requires-Dist: ruff==0.11.4
+Requires-Dist: s3transfer==0.11.4
+Requires-Dist: safehttpx==0.1.6
+Requires-Dist: safetensors==0.5.3
+Requires-Dist: scikit-learn==1.6.1
+Requires-Dist: scipy==1.15.2
+Requires-Dist: semantic-version==2.10.0
+Requires-Dist: sentry-sdk==2.25.1
+Requires-Dist: setproctitle==1.3.5
+Requires-Dist: shellingham==1.5.4
+Requires-Dist: six==1.17.0
+Requires-Dist: smmap==5.0.2
+Requires-Dist: sniffio==1.3.1
+Requires-Dist: soundfile==0.13.1
+Requires-Dist: soxr==0.5.0.post1
+Requires-Dist: starlette==0.46.1
+Requires-Dist: sympy==1.13.1
+Requires-Dist: threadpoolctl==3.6.0
+Requires-Dist: tokenizers==0.21.1
+Requires-Dist: tomli==2.2.1
+Requires-Dist: tomlkit==0.13.2
+Requires-Dist: torchdiffeq==0.2.5
+Requires-Dist: tqdm==4.67.1
+Requires-Dist: transformers==4.50.3
+Requires-Dist: transformers-stream-generator==0.0.5
+Requires-Dist: triton==3.2.0
+Requires-Dist: typer==0.15.2
+Requires-Dist: typing-inspection==0.4.0
+Requires-Dist: typing_extensions==4.13.1
+Requires-Dist: tzdata==2025.2
+Requires-Dist: urllib3==2.3.0
+Requires-Dist: vocos==0.1.0
+Requires-Dist: wandb==0.19.9
+Requires-Dist: websockets==14.2
+Requires-Dist: x-transformers==2.2.8
+Requires-Dist: xxhash==3.5.0
+Requires-Dist: yarl==1.19.0

dwani-0.1.0.dist-info/RECORD

@@ -0,0 +1,12 @@
+__init__.py,sha256=2tm2TJE5xuE6thkMj7um0xxCCmLE4OHtUM-M3M0H8Yo,1294
+asr.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+audio.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+chat.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+client.py,sha256=BLWnHoehLZhXuDd8IPitLyuo3STmhn3TQWBziz5TXZ4,4219
+docs.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+exceptions.py,sha256=qEN5ukqlnN7v-kHNEnISWFMpPMt6uTft9mPsTXJ4LVA,227
+vision.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+dwani-0.1.0.dist-info/METADATA,sha256=XQXwaL4Yk7_ufDAZwfg1AZDWbRt4ZpcXnnDiqEeQCRE,6100
+dwani-0.1.0.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
+dwani-0.1.0.dist-info/top_level.txt,sha256=7MBQ5IZg4CXEAt-rxOplIWS0HQcybyibcos1F-zrfOY,54
+dwani-0.1.0.dist-info/RECORD,,

dwani-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.3.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

dwani-0.1.0.dist-info/top_level.txt

@@ -0,0 +1,8 @@
+__init__
+asr
+audio
+chat
+client
+docs
+exceptions
+vision

exceptions.py

@@ -0,0 +1,5 @@
+class DhwaniAPIError(Exception):
+    def __init__(self, response):
+        super().__init__(f"API Error {response.status_code}: {response.text}")
+        self.status_code = response.status_code
+        self.response = response