podcast script generation component (#15)

* Add devcontainer and requirements

* Add pyproject.toml

* Add data_loaders and tests

* Add data_cleaners and tests

* Update demo

* Add `LOADERS` and `CLEANERS`

* Add markdown and docx

* Add API Reference

* Update tests

* Update install

* Add initial scripts

* More tests

* fix merge

* Add podcast writing to demo/app

* Add missing deps

* Add text_to_podcast module

* Expose model options and prompt tuning in the app

* pre-commit

* Strip system_prompt

* Rename to inference module. Add docstrings

* pre-commit

* Add CURATED_REPOS

* JSON prompt

* Update API docs

* Fix format

* Make text cutoff based on `model.n_ctx()`. Consider ~4 characters per token as a resonable default.

* Add inference tests

* Drop __init__ imports

* Fix outdated arg

* Drop redundant JSON output in prompt

* Update default stop

tests/integration/test_model_load_and_inference.py

@@ -12,12 +12,12 @@ def test_model_load_and_inference_text_to_text():
         "HuggingFaceTB/smollm-135M-instruct-v0.2-Q8_0-GGUF/smollm-135m-instruct-add-basics-q8_0.gguf"
     )
     result = text_to_text(
-        "Answer to: What is the capital of France?",
+        "What is the capital of France?",
         model=model,
         system_prompt="",
     )
     assert isinstance(result, str)
-    assert json.loads(result)
+    assert json.loads(result)["Capital"] == "Paris"
 
 
 def test_model_load_and_inference_text_to_text_no_json():
@@ -37,6 +37,19 @@ def test_model_load_and_inference_text_to_text_no_json():
     assert result.startswith("The capital of France is Paris")
 
 
+def test_model_load_and_inference_text_to_text_stream():
+    model = load_llama_cpp_model(
+        "HuggingFaceTB/smollm-135M-instruct-v0.2-Q8_0-GGUF/smollm-135m-instruct-add-basics-q8_0.gguf"
+    )
+    result = text_to_text_stream(
+        "What is the capital of France?",
+        model=model,
+        system_prompt="",
+    )
+    assert isinstance(result, Iterator)
+    assert json.loads("".join(result))["Capital"] == "Paris"
+
+
 def test_model_load_and_inference_text_to_text_stream_no_json():
     model = load_llama_cpp_model(
         "HuggingFaceTB/smollm-135M-instruct-v0.2-Q8_0-GGUF/smollm-135m-instruct-add-basics-q8_0.gguf"