commoncompute 0.1.2__tar.gz → 0.2.0__tar.gz

commoncompute-0.2.0/PKG-INFO

@@ -0,0 +1,329 @@
+Metadata-Version: 2.4
+Name: commoncompute
+Version: 0.2.0
+Summary: Official Python SDK for Common Compute — the batch AI bill you shouldn't be paying.
+Project-URL: Homepage, https://commoncompute.ai
+Project-URL: Documentation, https://commoncompute.ai/docs
+Project-URL: Source, https://github.com/Ikaikaalika/commoncomputeai
+Project-URL: Changelog, https://commoncompute.ai/changelog
+Author-email: Common Compute <support@commoncompute.ai>
+License: MIT
+License-File: LICENSE
+Keywords: ai,apple-silicon,embeddings,inference,llm,openai-compatible
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.9
+Requires-Dist: httpx<1.0,>=0.24
+Requires-Dist: pydantic<3.0,>=2.0
+Provides-Extra: cli
+Requires-Dist: rich>=13; extra == 'cli'
+Requires-Dist: typer>=0.9; extra == 'cli'
+Provides-Extra: test
+Requires-Dist: pytest-asyncio>=0.21; extra == 'test'
+Requires-Dist: pytest>=7.0; extra == 'test'
+Requires-Dist: respx>=0.20; extra == 'test'
+Description-Content-Type: text/markdown
+
+# Common Compute — Python SDK
+
+The official Python SDK + CLI for [Common Compute](https://commoncompute.ai) —
+batch AI compute without the AWS tax, on Apple Silicon hardware AWS can't offer.
+
+One SDK call replaces the IAM roles, compute environments, and job definitions.
+Every job returns its **price and ETA before it runs**, and you're only billed
+for **successful** jobs — each with a verifiable receipt.
+
+```bash
+pip install commoncompute          # core: httpx + pydantic only
+pip install "commoncompute[cli]"   # + the `cc` command line
+cc login                           # opens the browser — no key to copy-paste
+```
+
+`cc login` (or `commoncompute.connect()` from a script or notebook) opens an
+approval page in your browser; click **Approve** and a fresh API key is saved
+to `~/.config/commoncompute/credentials`, where the SDK finds it automatically.
+Prefer explicit config? `export CC_API_KEY=cc_live_...` works everywhere and
+takes precedence.
+
+## The 10-minute path
+
+```python
+import commoncompute as cc
+
+client = cc.Client()   # reads CC_API_KEY, or the saved credentials file
+
+job = client.transcription.create("s3://my-bucket/meeting.mp3", timestamps=True)
+print(job.job_id, job.locked_price_usd, job.eta_seconds)   # price known BEFORE it runs
+
+result = client.result(job)          # waits, downloads, attaches the receipt
+print(result.output)
+print(result.receipt)                # signed proof of what ran, where, for how much
+```
+
+## Examples
+
+### 1. OCR / document extraction — vs AWS Textract
+
+```python
+job = client.ocr.extract("https://example.com/contracts.pdf", structured=True)
+result = client.result(job)          # blocks + bounding boxes as JSON
+```
+
+### 2. Transcription in bulk
+
+```python
+jobs = client.transcription.create_many(
+    [f"s3://recordings/call-{i}.mp3" for i in range(200)],
+    language="en",
+    max_concurrent=16,
+)
+```
+
+### 3. Reranking — sharpen RAG retrieval
+
+```python
+job = client.rerank("what is the neural engine?", documents, top_n=5)
+top = client.result(job).output
+```
+
+### 4. Translation
+
+```python
+job = client.translate(catalog_descriptions, target_lang="de")
+```
+
+### 5. Background removal
+
+```python
+job = client.images.remove_background("product-shot.png")
+```
+
+Also available: `client.video.transcode(...)`, `client.build.ios_test(...)`,
+`client.images.generate(...)`, `client.embeddings.create(...)`, and the
+generic `client.submit(workload_id, payload)` for anything in
+[the catalog](https://commoncompute.ai/workloads).
+
+## Price before execution, hard caps, dry runs
+
+```python
+quote = client.ocr.extract("scan.pdf", dry_run=True)     # price + ETA, no job
+job = client.ocr.extract("scan.pdf", max_spend_usd=1.0)  # refused if it would exceed
+```
+
+## Batches that stream back
+
+```python
+for result in client.submit_many("vision_bgremove", images, max_concurrent=8):
+    save(result.output)              # results stream as they complete
+```
+
+## Receipts
+
+Every successful job carries a receipt (`job_id`, cost, provider id,
+timestamps, input/output hashes, signature):
+
+```python
+client.receipts.list()
+csv_blob = client.receipts.export(format="csv")
+```
+
+## Account
+
+```python
+client.account.balance()         # card-on-file billing state (cash only)
+client.account.spend(days=30)    # spend summary by workload
+client.account.tier()            # your volume tier + the next threshold
+```
+
+Per-task prices step down automatically as your monthly usage grows —
+your current rate is always the one a quote returns.
+
+## Async
+
+`AsyncClient` mirrors `Client` method-for-method — `submit`, `wait`, `result`,
+and `submit_many` all have `await`-able twins. Use it as an async context
+manager so the underlying HTTP pool is closed for you:
+
+```python
+import asyncio
+import commoncompute as cc
+
+async def main():
+    async with cc.AsyncClient() as client:          # closes the pool on exit
+        job = await client.submit("coreml_embed", {"input": ["hello world"]})
+        print(job.job_id, job.locked_price_usd, job.eta_seconds)  # price BEFORE it runs
+
+        await client.wait(job)                       # poll until terminal
+        result = await client.result(job)            # + download output & receipt
+        print(result.output)
+
+asyncio.run(main())
+```
+
+Batches stream back the same way — `submit_many` is an async generator:
+
+```python
+async with cc.AsyncClient() as client:
+    async for r in client.submit_many("coreml_embed", batches, max_concurrent=8):
+        save(r.output)                               # each result as it completes
+```
+
+The lower-level `client.jobs.*` namespace (`jobs.submit`, `jobs.wait`,
+`jobs.get`, `jobs.events`, `jobs.download`) is async here too when you want the
+raw request/response dicts instead of typed `Job`/`TaskResult` objects.
+
+## CLI
+
+`pip install "commoncompute[cli]"` installs the `cc` command.
+
+```bash
+cc login                              # stores the key locally
+cc quote vision_ocr --units 5         # price + ETA, no execution
+cc submit coreml_embed --payload '{"input":["hi"]}' --wait
+cc jobs list
+cc jobs get <id>
+cc balance
+cc receipts export --format csv --out receipts.csv
+```
+
+### Commands
+
+| Command | What it does |
+|---------|--------------|
+| `cc login` / `cc logout` | Store / remove the API key (browser approval, or `--api-key`) |
+| `cc whoami` | Show the account behind the current key |
+| `cc balance` | Current workspace balance |
+| `cc usage` | Spend + call-count rollups over a date range (`--start`, `--end`, `--group-by`) |
+| `cc spend` | Total spend over the last `--days` N, grouped by workload |
+| `cc tier` | Current volume tier and the next threshold |
+| `cc workloads` | List available workloads |
+| `cc models` | List models (`--workload` to filter) |
+| `cc quote` | Price + ETA for a workload without submitting (`--units`, `--priority`, `--model`) |
+| `cc submit` | Submit one job (`--payload/-f`, `--model`, `--priority`, `--wait`, `--timeout`) |
+| `cc submit-many` | Submit a JSONL file of payloads; stream one result per line as NDJSON (`--input/-i`, `--max-concurrent`, `--no-wait`) |
+| `cc chat` | One-shot chat message to a model (`--model`, `--stream/--no-stream`) |
+| `cc embed` | Embed a single string (prints the vector length) |
+| `cc playground` | Open the web playground |
+| `cc jobs list` | Recent submissions, newest first (`--limit/-n`) |
+| `cc jobs get <id>` | Fetch one job |
+| `cc jobs wait <id>` | Poll a job to a terminal state (`--timeout/-t`) |
+| `cc jobs events <id>` | Event timeline for a job |
+| `cc jobs download <id>` | Download a job's result (`--out/-o`, else stdout) |
+| `cc keys list` / `create` / `revoke` | Manage API keys |
+| `cc receipts list` | Receipts for completed jobs (`--limit/-n`) |
+| `cc receipts get <id>` | Signed receipt for a single job |
+| `cc receipts export` | Export receipts as CSV or JSON (`--format/-f`, `--out/-o`, `--limit/-n`) |
+| `cc config path` / `show` / `set` / `unset` | Inspect and edit local settings (see below) |
+
+`cc --version` (or `-V`) prints the version. Every read command that renders a
+table also accepts **`--json`** for plain, ANSI-free machine-readable output —
+`whoami`, `balance`, `usage`, `spend`, `tier`, `workloads`, `models`, `quote`,
+`submit`, `jobs list/get/wait/events`, `keys list`, and `receipts list`.
+
+### Shell completion
+
+Typer ships completion for bash, zsh, fish, and PowerShell:
+
+```bash
+cc --install-completion        # install for the current shell
+cc --show-completion           # print the script to inspect or customise
+```
+
+### Exit codes
+
+Scripts can branch on `cc`'s exit status:
+
+| Code | Meaning |
+|------|---------|
+| `0` | Success |
+| `1` | API or runtime error (network, server, bad request) |
+| `2` | Usage error — missing/invalid arguments, or no credentials found |
+| `3` | The job reached a **failed** terminal state (`failed` / `dead_letter` / `cancelled`) — `cc jobs wait` and `cc submit --wait` only |
+
+## Migrating from OpenAI (optional)
+
+Existing OpenAI-based pipelines (embeddings, chat, transcription) can point
+at Common Compute by swapping two env vars — or:
+
+```python
+from commoncompute.compat import openai   # sets OPENAI_BASE_URL / OPENAI_API_KEY
+client = openai.OpenAI()
+```
+
+This is a migration path, not the recommended interface: the native client
+returns locked prices, ETAs, and receipts that the OpenAI wire format can't
+express.
+
+## Errors
+
+Typed, always:
+
+```python
+try:
+    client.ocr.extract("scan.pdf", max_spend_usd=0.01)
+except cc.InsufficientFundsError:      # quote exceeded the cap / no card
+    ...
+except cc.PermissionDeniedError:       # key lacks scope for this workload
+    ...
+except cc.ConflictError:               # idempotency-key or state conflict (409)
+    ...
+except cc.UnsupportedFormatError:      # wrong file type for the workload
+    ...
+except cc.JobTimeoutError:             # wait() expired; job still running
+    ...
+except cc.NetworkError:                # no HTTP response after retries
+    ...
+except cc.CommonComputeError as e:     # everything raises from this
+    print(e.request_id)
+```
+
+The full hierarchy — `AuthenticationError`, `PermissionDeniedError`,
+`NotFoundError`, `ConflictError`, `RateLimitError`, `InsufficientFundsError`,
+`BadRequestError`, `ValidationError`, `UnsupportedFormatError`, `NetworkError`,
+`JobTimeoutError`, `APIError` — all subclass `CommonComputeError`.
+
+## Configuration
+
+Credentials and settings live under one canonical directory (override the whole
+directory with `$CC_CONFIG_DIR`):
+
+```
+~/.config/commoncompute/credentials   # the API key (single line)
+~/.config/commoncompute/config        # settings: base_url, org (key = value)
+```
+
+Two **legacy** locations are still read (never written) so older installs keep
+working: `~/.commoncompute/config` and `~/.commoncompute/credentials`.
+
+Environment variables take precedence over both files at runtime:
+
+| Setting  | Env var         | Resolution order (first match wins) |
+|----------|-----------------|-------------------------------------|
+| API key  | `CC_API_KEY`    | env → `~/.config/commoncompute/credentials` → `~/.commoncompute/config` → `~/.commoncompute/credentials` |
+| Base URL | `CC_BASE_URL`   | env → `config` file `base_url` → `https://api.commoncompute.ai` |
+| Org id   | `CC_ORG`        | env → `config` file `org` → default workspace |
+| Config dir | `CC_CONFIG_DIR` | overrides the `~/.config/commoncompute` location above |
+
+Inspect and edit the local config from the CLI:
+
+```bash
+cc config path                        # print the config directory
+cc config show                        # settings + active credential source (key masked)
+cc config set base_url https://api.commoncompute.ai
+cc config set org my-workspace
+cc config unset org
+```
+
+Env vars still win at runtime — `cc config set` writes the file, but
+`CC_BASE_URL` / `CC_ORG` override it for a given process.
+
+Python 3.9+. Core dependencies: `httpx`, `pydantic`. MIT license.

commoncompute-0.2.0/README.md

@@ -0,0 +1,294 @@
+# Common Compute — Python SDK
+
+The official Python SDK + CLI for [Common Compute](https://commoncompute.ai) —
+batch AI compute without the AWS tax, on Apple Silicon hardware AWS can't offer.
+
+One SDK call replaces the IAM roles, compute environments, and job definitions.
+Every job returns its **price and ETA before it runs**, and you're only billed
+for **successful** jobs — each with a verifiable receipt.
+
+```bash
+pip install commoncompute          # core: httpx + pydantic only
+pip install "commoncompute[cli]"   # + the `cc` command line
+cc login                           # opens the browser — no key to copy-paste
+```
+
+`cc login` (or `commoncompute.connect()` from a script or notebook) opens an
+approval page in your browser; click **Approve** and a fresh API key is saved
+to `~/.config/commoncompute/credentials`, where the SDK finds it automatically.
+Prefer explicit config? `export CC_API_KEY=cc_live_...` works everywhere and
+takes precedence.
+
+## The 10-minute path
+
+```python
+import commoncompute as cc
+
+client = cc.Client()   # reads CC_API_KEY, or the saved credentials file
+
+job = client.transcription.create("s3://my-bucket/meeting.mp3", timestamps=True)
+print(job.job_id, job.locked_price_usd, job.eta_seconds)   # price known BEFORE it runs
+
+result = client.result(job)          # waits, downloads, attaches the receipt
+print(result.output)
+print(result.receipt)                # signed proof of what ran, where, for how much
+```
+
+## Examples
+
+### 1. OCR / document extraction — vs AWS Textract
+
+```python
+job = client.ocr.extract("https://example.com/contracts.pdf", structured=True)
+result = client.result(job)          # blocks + bounding boxes as JSON
+```
+
+### 2. Transcription in bulk
+
+```python
+jobs = client.transcription.create_many(
+    [f"s3://recordings/call-{i}.mp3" for i in range(200)],
+    language="en",
+    max_concurrent=16,
+)
+```
+
+### 3. Reranking — sharpen RAG retrieval
+
+```python
+job = client.rerank("what is the neural engine?", documents, top_n=5)
+top = client.result(job).output
+```
+
+### 4. Translation
+
+```python
+job = client.translate(catalog_descriptions, target_lang="de")
+```
+
+### 5. Background removal
+
+```python
+job = client.images.remove_background("product-shot.png")
+```
+
+Also available: `client.video.transcode(...)`, `client.build.ios_test(...)`,
+`client.images.generate(...)`, `client.embeddings.create(...)`, and the
+generic `client.submit(workload_id, payload)` for anything in
+[the catalog](https://commoncompute.ai/workloads).
+
+## Price before execution, hard caps, dry runs
+
+```python
+quote = client.ocr.extract("scan.pdf", dry_run=True)     # price + ETA, no job
+job = client.ocr.extract("scan.pdf", max_spend_usd=1.0)  # refused if it would exceed
+```
+
+## Batches that stream back
+
+```python
+for result in client.submit_many("vision_bgremove", images, max_concurrent=8):
+    save(result.output)              # results stream as they complete
+```
+
+## Receipts
+
+Every successful job carries a receipt (`job_id`, cost, provider id,
+timestamps, input/output hashes, signature):
+
+```python
+client.receipts.list()
+csv_blob = client.receipts.export(format="csv")
+```
+
+## Account
+
+```python
+client.account.balance()         # card-on-file billing state (cash only)
+client.account.spend(days=30)    # spend summary by workload
+client.account.tier()            # your volume tier + the next threshold
+```
+
+Per-task prices step down automatically as your monthly usage grows —
+your current rate is always the one a quote returns.
+
+## Async
+
+`AsyncClient` mirrors `Client` method-for-method — `submit`, `wait`, `result`,
+and `submit_many` all have `await`-able twins. Use it as an async context
+manager so the underlying HTTP pool is closed for you:
+
+```python
+import asyncio
+import commoncompute as cc
+
+async def main():
+    async with cc.AsyncClient() as client:          # closes the pool on exit
+        job = await client.submit("coreml_embed", {"input": ["hello world"]})
+        print(job.job_id, job.locked_price_usd, job.eta_seconds)  # price BEFORE it runs
+
+        await client.wait(job)                       # poll until terminal
+        result = await client.result(job)            # + download output & receipt
+        print(result.output)
+
+asyncio.run(main())
+```
+
+Batches stream back the same way — `submit_many` is an async generator:
+
+```python
+async with cc.AsyncClient() as client:
+    async for r in client.submit_many("coreml_embed", batches, max_concurrent=8):
+        save(r.output)                               # each result as it completes
+```
+
+The lower-level `client.jobs.*` namespace (`jobs.submit`, `jobs.wait`,
+`jobs.get`, `jobs.events`, `jobs.download`) is async here too when you want the
+raw request/response dicts instead of typed `Job`/`TaskResult` objects.
+
+## CLI
+
+`pip install "commoncompute[cli]"` installs the `cc` command.
+
+```bash
+cc login                              # stores the key locally
+cc quote vision_ocr --units 5         # price + ETA, no execution
+cc submit coreml_embed --payload '{"input":["hi"]}' --wait
+cc jobs list
+cc jobs get <id>
+cc balance
+cc receipts export --format csv --out receipts.csv
+```
+
+### Commands
+
+| Command | What it does |
+|---------|--------------|
+| `cc login` / `cc logout` | Store / remove the API key (browser approval, or `--api-key`) |
+| `cc whoami` | Show the account behind the current key |
+| `cc balance` | Current workspace balance |
+| `cc usage` | Spend + call-count rollups over a date range (`--start`, `--end`, `--group-by`) |
+| `cc spend` | Total spend over the last `--days` N, grouped by workload |
+| `cc tier` | Current volume tier and the next threshold |
+| `cc workloads` | List available workloads |
+| `cc models` | List models (`--workload` to filter) |
+| `cc quote` | Price + ETA for a workload without submitting (`--units`, `--priority`, `--model`) |
+| `cc submit` | Submit one job (`--payload/-f`, `--model`, `--priority`, `--wait`, `--timeout`) |
+| `cc submit-many` | Submit a JSONL file of payloads; stream one result per line as NDJSON (`--input/-i`, `--max-concurrent`, `--no-wait`) |
+| `cc chat` | One-shot chat message to a model (`--model`, `--stream/--no-stream`) |
+| `cc embed` | Embed a single string (prints the vector length) |
+| `cc playground` | Open the web playground |
+| `cc jobs list` | Recent submissions, newest first (`--limit/-n`) |
+| `cc jobs get <id>` | Fetch one job |
+| `cc jobs wait <id>` | Poll a job to a terminal state (`--timeout/-t`) |
+| `cc jobs events <id>` | Event timeline for a job |
+| `cc jobs download <id>` | Download a job's result (`--out/-o`, else stdout) |
+| `cc keys list` / `create` / `revoke` | Manage API keys |
+| `cc receipts list` | Receipts for completed jobs (`--limit/-n`) |
+| `cc receipts get <id>` | Signed receipt for a single job |
+| `cc receipts export` | Export receipts as CSV or JSON (`--format/-f`, `--out/-o`, `--limit/-n`) |
+| `cc config path` / `show` / `set` / `unset` | Inspect and edit local settings (see below) |
+
+`cc --version` (or `-V`) prints the version. Every read command that renders a
+table also accepts **`--json`** for plain, ANSI-free machine-readable output —
+`whoami`, `balance`, `usage`, `spend`, `tier`, `workloads`, `models`, `quote`,
+`submit`, `jobs list/get/wait/events`, `keys list`, and `receipts list`.
+
+### Shell completion
+
+Typer ships completion for bash, zsh, fish, and PowerShell:
+
+```bash
+cc --install-completion        # install for the current shell
+cc --show-completion           # print the script to inspect or customise
+```
+
+### Exit codes
+
+Scripts can branch on `cc`'s exit status:
+
+| Code | Meaning |
+|------|---------|
+| `0` | Success |
+| `1` | API or runtime error (network, server, bad request) |
+| `2` | Usage error — missing/invalid arguments, or no credentials found |
+| `3` | The job reached a **failed** terminal state (`failed` / `dead_letter` / `cancelled`) — `cc jobs wait` and `cc submit --wait` only |
+
+## Migrating from OpenAI (optional)
+
+Existing OpenAI-based pipelines (embeddings, chat, transcription) can point
+at Common Compute by swapping two env vars — or:
+
+```python
+from commoncompute.compat import openai   # sets OPENAI_BASE_URL / OPENAI_API_KEY
+client = openai.OpenAI()
+```
+
+This is a migration path, not the recommended interface: the native client
+returns locked prices, ETAs, and receipts that the OpenAI wire format can't
+express.
+
+## Errors
+
+Typed, always:
+
+```python
+try:
+    client.ocr.extract("scan.pdf", max_spend_usd=0.01)
+except cc.InsufficientFundsError:      # quote exceeded the cap / no card
+    ...
+except cc.PermissionDeniedError:       # key lacks scope for this workload
+    ...
+except cc.ConflictError:               # idempotency-key or state conflict (409)
+    ...
+except cc.UnsupportedFormatError:      # wrong file type for the workload
+    ...
+except cc.JobTimeoutError:             # wait() expired; job still running
+    ...
+except cc.NetworkError:                # no HTTP response after retries
+    ...
+except cc.CommonComputeError as e:     # everything raises from this
+    print(e.request_id)
+```
+
+The full hierarchy — `AuthenticationError`, `PermissionDeniedError`,
+`NotFoundError`, `ConflictError`, `RateLimitError`, `InsufficientFundsError`,
+`BadRequestError`, `ValidationError`, `UnsupportedFormatError`, `NetworkError`,
+`JobTimeoutError`, `APIError` — all subclass `CommonComputeError`.
+
+## Configuration
+
+Credentials and settings live under one canonical directory (override the whole
+directory with `$CC_CONFIG_DIR`):
+
+```
+~/.config/commoncompute/credentials   # the API key (single line)
+~/.config/commoncompute/config        # settings: base_url, org (key = value)
+```
+
+Two **legacy** locations are still read (never written) so older installs keep
+working: `~/.commoncompute/config` and `~/.commoncompute/credentials`.
+
+Environment variables take precedence over both files at runtime:
+
+| Setting  | Env var         | Resolution order (first match wins) |
+|----------|-----------------|-------------------------------------|
+| API key  | `CC_API_KEY`    | env → `~/.config/commoncompute/credentials` → `~/.commoncompute/config` → `~/.commoncompute/credentials` |
+| Base URL | `CC_BASE_URL`   | env → `config` file `base_url` → `https://api.commoncompute.ai` |
+| Org id   | `CC_ORG`        | env → `config` file `org` → default workspace |
+| Config dir | `CC_CONFIG_DIR` | overrides the `~/.config/commoncompute` location above |
+
+Inspect and edit the local config from the CLI:
+
+```bash
+cc config path                        # print the config directory
+cc config show                        # settings + active credential source (key masked)
+cc config set base_url https://api.commoncompute.ai
+cc config set org my-workspace
+cc config unset org
+```
+
+Env vars still win at runtime — `cc config set` writes the file, but
+`CC_BASE_URL` / `CC_ORG` override it for a given process.
+
+Python 3.9+. Core dependencies: `httpx`, `pydantic`. MIT license.

{commoncompute-0.1.2 → commoncompute-0.2.0}/commoncompute/__init__.py

@@ -11,32 +11,41 @@ Quickstart::
     client = cc.Client(api_key="cc_live_...")
     print(client.balance())
 
-    # Native job submission (embeddings — live today)
+    # OpenAI-compatible chat
+    reply = client.chat.create(
+        model="qwen-2.5-7b",
+        messages=[{"role": "user", "content": "hi"}],
+    )
+    print(reply["choices"][0]["message"]["content"])
+
+    # Native job submission
     job = client.jobs.submit(
         workload_id="coreml_embed",
         payload={"input": ["hello world"]},
     )
     result = client.jobs.wait(job["id"])
 
-    # OpenAI-compatible embeddings
-    vectors = client.embeddings.create(input=["hello world"], model="bge-base")
+Streaming chat::
 
-`client.chat.*` targets LLM workloads that are still marked *coming soon*
-in the catalog — the API declines them with `workload_not_available`
-(HTTP 409) until they go live. See https://commoncompute.ai/workloads.
+    for chunk in client.chat.stream(model="qwen-2.5-7b",
+                                    messages=[{"role": "user", "content": "hi"}]):
+        delta = chunk["choices"][0].get("delta", {}).get("content", "")
+        print(delta, end="", flush=True)
 """
 
 # MUST come before any submodule imports — _transport.py reads
 # `commoncompute.__version__` at import time for the User-Agent header,
 # and the previous ordering (`__version__` defined at the bottom) made
 # every clean install of the SDK fail with a circular ImportError.
-__version__ = "0.1.2"
+__version__ = "0.2.0"
 
 from .client import Client, AsyncClient
 from .errors import (
     CommonComputeError,
     AuthenticationError,
+    PermissionDeniedError,
     NotFoundError,
+    ConflictError,
     RateLimitError,
     InsufficientFundsError,
     InsufficientCreditsError,  # legacy alias of InsufficientFundsError
@@ -58,7 +67,9 @@ __all__ = [
     "login",
     "CommonComputeError",
     "AuthenticationError",
+    "PermissionDeniedError",
     "NotFoundError",
+    "ConflictError",
     "RateLimitError",
     "InsufficientFundsError",
     "InsufficientCreditsError",