Conversational Graph
Build deterministic, multi-turn voice and chat AI agents as directed graphs : where you control the flow and the LLM handles natural conversation.
Installation
pip install videosdk-conversational-graph
Features
| Capability | How It Works |
|---|---|
| Predictable flows | Conversations follow the exact path you define. No hallucinated detours. |
| Structured data collection | Extract and validate user data with Pydantic models : types, constraints, custom validators. |
| Conditional branching | Route to different paths based on collected data (e.g., credit score -> approve/reject/review). |
| Human-in-the-loop | Pause the conversation, wait for external input (payment callback, human review), then resume. |
| Checkpointing | Save conversation state after every step. Resume interrupted calls. Time-travel to any past point. |
| Parallel tool execution | Run multiple nodes or tool calls concurrently with fan-out/fan-in transitions. |
| Provider agnostic | Works with any STT, LLM, TTS via the VideoSDK pipeline. |
Metadata
Release files for videosdk-conversational-graph 1.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
Total release size: 28.1 MB
Release files / videosdk_conversational_graph-1.0.1-cp313-cp313-win_amd64.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp313-cp313-win_amd64.whl |
|---|---|
| Size | 764.7 kB |
| Tags | CPython 3.13 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
5b757951590f707e793b9c11819ce804873a14324c8bca48c3d929b6b6c8027c
|
|
BLAKE2b-256 checksum How to use checksums |
69506758f147fbff28c2786b9346a8549a6db67055c617de1c8036f5df97f9be
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp313-cp313-win32.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp313-cp313-win32.whl |
|---|---|
| Size | 664.0 kB |
| Tags | CPython 3.13 Windows x86-32 |
|
SHA-256 checksum How to use checksums |
1c5ada9a90599487e83a90914a4ddaeef5c24f6fb11442204c69616e105b7cf3
|
|
BLAKE2b-256 checksum How to use checksums |
adacebbed3f66c087adf927fb0df7ca661d1a38848c2d146f737360f6d340b8c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 5.9 MB |
| Tags | CPython 3.13 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
2820c8a4377e84e929f973375ad1a0658a44ca0f7fa64dc2a3ba592f47ecd2b6
|
|
BLAKE2b-256 checksum How to use checksums |
99ed4762da28e7479aebf1746cdd8d99947967b836ec919ab01b05a73950223a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl |
|---|---|
| Size | 5.8 MB |
| Tags | CPython 3.13 Linux glibc 2.17+ ARM64 Linux glibc 2.28+ ARM64 |
|
SHA-256 checksum How to use checksums |
5045c894c91f992866310bfab5d02f45c80754515561c243d75cd2afbfb50b69
|
|
BLAKE2b-256 checksum How to use checksums |
6fc6110d6f24db0ea423d4bb806ae32d3187fe5f8e6333ba453ea587b1790a93
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp313-cp313-macosx_11_0_arm64.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp313-cp313-macosx_11_0_arm64.whl |
|---|---|
| Size | 874.0 kB |
| Tags | CPython 3.13 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
cd194be95e6d96b86ed3370e7737093ea794fafbf422ae6dfab8c2e3a4b08e35
|
|
BLAKE2b-256 checksum How to use checksums |
e8d2ce6b4b9a6cac1dc6e9aa428188acb8500fc894ab26184c16ea679744c34d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp312-cp312-win_amd64.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp312-cp312-win_amd64.whl |
|---|---|
| Size | 770.2 kB |
| Tags | CPython 3.12 Windows x86-64 |
|
SHA-256 checksum How to use checksums |
e351cffc4d14f18e9d234795fca8f6faf2d21aec267e7185f3381c06cfa629d8
|
|
BLAKE2b-256 checksum How to use checksums |
8b27af9aeb8cb2f1db1ee91d821082deb466e67de5ed9b9c5edef2101f61aa33
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp312-cp312-win32.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp312-cp312-win32.whl |
|---|---|
| Size | 669.5 kB |
| Tags | CPython 3.12 Windows x86-32 |
|
SHA-256 checksum How to use checksums |
76fa792e58d3d3fa110ef21ec304870db358931269504f9eb99073adda7be299
|
|
BLAKE2b-256 checksum How to use checksums |
f612135a4aa70c645f8d3085643062f554c90071d079417127442ac52b9e56dc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 6.0 MB |
| Tags | CPython 3.12 Linux glibc 2.17+ x86-64 Linux glibc 2.28+ x86-64 |
|
SHA-256 checksum How to use checksums |
0bd4cad1125dc440c2c9650e99dcd5d4e615ccde5df32bb8c0c9d90b257ccf07
|
|
BLAKE2b-256 checksum How to use checksums |
b9c7fca9a698b2a40f238c45348c13363ffb5e33792ec7b796499c728c79e5b3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl |
|---|---|
| Size | 5.9 MB |
| Tags | CPython 3.12 Linux glibc 2.17+ ARM64 Linux glibc 2.28+ ARM64 |
|
SHA-256 checksum How to use checksums |
61572941971dec822f38f39f614ab3ac908edf3f82cf9d67d1c6901877191601
|
|
BLAKE2b-256 checksum How to use checksums |
9768b6ef80fca9525687006f079859a5db546eee2bb4c69d4e4227af2ef62b5a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Release files / videosdk_conversational_graph-1.0.1-cp312-cp312-macosx_11_0_arm64.whl
| Download URL | videosdk_conversational_graph-1.0.1-cp312-cp312-macosx_11_0_arm64.whl |
|---|---|
| Size | 885.0 kB |
| Tags | CPython 3.12 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
d38f8a865f8cc9f4509989049344db4beea68a492003d031067eecdea0b7d611
|
|
BLAKE2b-256 checksum How to use checksums |
fae75c68293fd8f35c46494a2f046c9518fe53f2b872a26f07ab4f880219d1a2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.2
|
Security for videosdk-conversational-graph 1.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.