TalkPipe 0.12.2__tar.gz → 0.12.3a2__tar.gz

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/.github/copilot-instructions.md

@@ -1,6 +1,18 @@
 # TalkPipe AI Coding Instructions
 
-*Cursor users: See [AGENTS.md](../AGENTS.md) and `.cursor/skills/` for additional workflows (TDD, changelog, doc examples, entry points).*
+*Cursor users: See [AGENTS.md](../AGENTS.md) and `.cursor/skills/` for additional workflows.*
+
+## Quick Actions (Prompts)
+
+Use these slash commands in VS Code chat (type `/` to invoke):
+
+| Prompt | When to use |
+|--------|-------------|
+| `/tdd` | Implement a change with write-fail-fix-pass TDD order |
+| `/add-segment` | Add a new segment or source end-to-end (test → impl → entry-point → changelog) |
+| `/changelog` | Update CHANGELOG.md after a feature or fix |
+| `/update-entry-points` | Regenerate pyproject.toml entry points from decorators |
+| `/doc-examples` | Validate and fix documentation code examples |
 
 ## Project Overview
 

talkpipe-0.12.3a2/.github/prompts/add-segment.prompt.md

@@ -0,0 +1,57 @@
+---
+mode: agent
+description: Add a new segment or source to TalkPipe. Use when creating new pipe components. Covers decorator pattern, parameter annotations, entry-point registration, and TDD.
+---
+
+Add a new **$input** to TalkPipe following all project conventions:
+
+## Step 1 — Write a failing test
+
+In the appropriate file under `tests/talkpipe/`, write a test that fails without the new component. Run it to confirm failure:
+
+```bash
+source .venv/bin/activate && pytest <test-file> -v
+```
+
+## Step 2 — Implement the component
+
+Place it in the appropriate module under `src/talkpipe/`:
+
+```python
+from typing import Annotated, Iterator, Any
+from talkpipe.pipe.core import segment, field_segment
+from talkpipe import register_segment  # or register_source
+
+@register_segment("mySegment")          # camelCase name used in ChatterLang
+@segment()
+def my_segment(
+    items: Iterator[Any],
+    param: Annotated[str, "Description of this parameter"] = "default",
+) -> Iterator[Any]:
+    for item in items:
+        yield item  # process and yield
+```
+
+Rules:
+- Use `@segment()` for iterators; `@field_segment()` for per-field transforms
+- Use `Annotated[type, "description"]` for every parameter (shown in ChatterLang reference)
+- Do NOT add docstrings documenting parameters — use `Annotated` instead
+- For `@field_segment`, the first non-items argument is the `field` parameter by convention
+
+## Step 3 — Register entry point
+
+```bash
+.venv/bin/python .cursor/skills/update-entry-points/scripts/update_entry_points.py
+```
+
+Verify the new entry appears in `pyproject.toml` under `[project.entry-points."talkpipe.segments"]` or `"talkpipe.sources"`.
+
+## Step 4 — Verify test passes
+
+```bash
+pytest <test-file> -v
+```
+
+## Step 5 — Update CHANGELOG.md
+
+Add a bullet under `## Unreleased` describing the new component.

talkpipe-0.12.3a2/.github/prompts/changelog.prompt.md

@@ -0,0 +1,23 @@
+---
+mode: agent
+description: Update CHANGELOG.md after implementing a feature, fixing a bug, or making any user-facing change. Handles update-vs-add logic correctly.
+---
+
+Update [CHANGELOG.md](../../CHANGELOG.md) under the `## Unreleased` section.
+
+**Decision logic:**
+1. Is this a **minor change to an existing feature** already mentioned in Unreleased?
+   - Yes → Update that existing bullet; do not add a new one
+   - No → Add a new bullet at the top of the Unreleased list
+
+2. Is this **purely internal** (refactor, no user impact)?
+   - Yes → Changelog update optional
+   - No → Always update
+
+**Format rules:**
+- Present tense, sentence case
+- Use backticks for segment/command names (e.g. `mySegment`, `run_doc_examples`)
+- Link to docs with `[text](path)` when helpful
+- Multi-line bullets use 2-space indent for continuation lines
+
+The change to document: $input

talkpipe-0.12.3a2/.github/prompts/doc-examples.prompt.md

@@ -0,0 +1,29 @@
+---
+mode: agent
+description: Validate and fix documentation code examples. Use after editing docs, before committing doc changes, or when examples may be broken. Runs examples via pytest and fixes formatting issues.
+---
+
+Validate documentation code examples following TalkPipe conventions. See [docs/architecture/documentation-formatting.md](../../docs/architecture/documentation-formatting.md) for full formatting rules.
+
+## Run examples via pytest
+
+```bash
+source .venv/bin/activate
+pytest tests/test_doc_examples.py -v
+```
+
+Skip Ollama-dependent examples when Ollama is unavailable:
+```bash
+pytest tests/test_doc_examples.py -v -m "not requires_ollama"
+```
+
+## Formatting rules (fix any violations found)
+
+- Use **unindented** ` ```python ` fences (no leading spaces before the triple backtick)
+- Always include a language tag (` ```python ` or ` ```chatterlang `)
+- Standalone examples must include all imports and be runnable in isolation
+- Add `# skip-extract` as the first line of blocks that are intentionally non-runnable (fragments, setup code, external-service-only)
+
+## Scope
+
+$input

talkpipe-0.12.3a2/.github/prompts/tdd.prompt.md

@@ -0,0 +1,21 @@
+---
+mode: agent
+description: Follow TalkPipe TDD workflow. Use when implementing features, fixing bugs, or adding segments/sources. Enforces write-fail-fix-pass order.
+---
+
+Follow the TalkPipe TDD workflow for this change:
+
+1. **Write or update a test** in `tests/` that fails without the change. Prefer updating an existing test file over creating a new one.
+2. **Verify the test fails**: run `source .venv/bin/activate && pytest <test-file> -v`
+3. **Implement the change**
+4. **Verify the test passes**: re-run the same pytest command
+
+Constraints:
+- Tests mirror `src/` structure under `tests/talkpipe/`
+- Keep tests as short as possible while covering the functionality completely
+- Use `pytest.fixture` and `pytest-mock` for dependencies
+- Always use the `.venv` environment; abort and alert if it doesn't exist
+
+If a unit test is not reasonable (e.g., requires external LLM, is purely cosmetic), notify the user and explain why.
+
+The change to implement: $input

talkpipe-0.12.3a2/.github/prompts/update-entry-points.prompt.md

@@ -0,0 +1,26 @@
+---
+mode: agent
+description: Regenerate and apply talkpipe.sources and talkpipe.segments entry points from @register_source/@register_segment decorators. Use after adding new sources or segments, or when pyproject.toml entry points are out of sync.
+---
+
+Regenerate entry points from `@register_source` and `@register_segment` decorators and update `pyproject.toml`.
+
+Run from the project root:
+
+```bash
+source .venv/bin/activate
+python .cursor/skills/update-entry-points/scripts/update_entry_points.py
+```
+
+The script:
+1. Scans `src/talkpipe/` for `@register_source` and `@register_segment` decorators
+2. Generates updated entry-point TOML
+3. Replaces `[project.entry-points."talkpipe.sources"]` and `[project.entry-points."talkpipe.segments"]` in `pyproject.toml`
+4. Preserves all other `pyproject.toml` content
+
+**Dry run** (preview without writing):
+```bash
+python .cursor/skills/update-entry-points/scripts/update_entry_points.py --dry-run
+```
+
+After running, verify the expected entry appears in `pyproject.toml`.

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/.github/workflows/ci-cd.yml

@@ -20,7 +20,7 @@ jobs:
         python-version: ['3.11', '3.12', '3.13']
     
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v7
       with:
         fetch-depth: 0
     
@@ -30,7 +30,7 @@ jobs:
         python-version: ${{ matrix.python-version }}
     
     - name: Cache pip dependencies
-      uses: actions/cache@v5
+      uses: actions/cache@v6
       with:
         path: ~/.cache/pip
         key: ${{ runner.os }}-pip-${{ hashFiles('pyproject.toml') }}
@@ -48,7 +48,7 @@ jobs:
     
     - name: Upload coverage to Codecov
       if: matrix.python-version == '3.11'
-      uses: codecov/codecov-action@v6
+      uses: codecov/codecov-action@v7
       with:
         files: ./coverage.xml
         flags: unittests
@@ -60,7 +60,7 @@ jobs:
       SAFETY_API_KEY: ${{ secrets.SAFETY_API_KEY }}
 
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v7
       with:
         fetch-depth: 0
     
@@ -104,7 +104,7 @@ jobs:
     
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v6
+      uses: actions/checkout@v7
     
     - name: Log in to Container Registry
       uses: docker/login-action@v4
@@ -177,7 +177,7 @@ jobs:
     
     steps:
     - name: Checkout repository
-      uses: actions/checkout@v6
+      uses: actions/checkout@v7
     
     - name: Initialize CodeQL
       uses: github/codeql-action/init@v4
@@ -196,7 +196,7 @@ jobs:
     if: github.event_name == 'release' && github.event.action == 'published'
     
     steps:
-    - uses: actions/checkout@v6
+    - uses: actions/checkout@v7
       with:
         fetch-depth: 0
     

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/CHANGELOG.md

@@ -2,6 +2,16 @@
 
 ## Unreleased
 
+- Added a local `eliza` prompt-adapter source for `llmPrompt` and guided-generation
+  segments. The adapter is deterministic (no external API keys), uses the configured
+  model name as ELIZA's self-reference, supports multi-turn memory/fact callbacks,
+  and provides generic structured outputs for score/binary/term extraction schemas.
+  Added a matching ChatterLang example to model/source configuration docs.
+- Fixed single-turn (`multi_turn=False`) prompt-adapter state handling so `_summary_message`
+  is cleared after each response and does not leak conversation memory between calls.
+- Fixed a CI import failure in `talkpipe.chatterlang.registry` by importing `List`
+  for the `available_names` return annotation, preventing `NameError` during module import.
+
 ## v0.12.2
 - Added batch embedding support: embedding adapters expose `execute_one` and `execute_batch`;
   `execute` remains as a deprecated alias for `execute_one` (removed in 1.0). `llmEmbed` extends

{talkpipe-0.12.2/src/talkpipe.egg-info → talkpipe-0.12.3a2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: talkpipe
-Version: 0.12.2
+Version: 0.12.3a2
 Summary: Python internal and external DSL for writing generative AI analytics
 Author-email: Travis Bauer <tlbauer@sandia.gov>
 Maintainer-email: Travis Bauer <tlbauer@sandia.gov>
@@ -36,6 +36,7 @@ Requires-Dist: pyyaml
 Requires-Dist: greenlet
 Requires-Dist: networkx
 Requires-Dist: starlette>=0.49.1
+Requires-Dist: build>=1.5.0
 Provides-Extra: dev
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-mock; extra == "dev"
@@ -79,7 +80,7 @@ This README is a high-level overview. Use the **[documentation map](#documentati
 
 ## What Can You Do With TalkPipe?
 
-- **Chat with LLMs** - Create multi-turn conversations with OpenAI, Ollama, or Anthropic models in just 2 lines of code
+- **Chat with LLMs** - Create multi-turn conversations with OpenAI, Ollama, or Anthropic models in just a few lines of code
 - **Process Documents** - Extract text from PDFs, analyze research papers, score content relevance
 - **Build RAG Pipelines** - Create end-to-end Retrieval-Augmented Generation workflows with vector databases
 - **Analyze Web Content** - Download web pages (respecting robots.txt), extract readable text, and summarize
@@ -128,7 +129,7 @@ These applications are entry points for different usage scenarios, from interact
 
 ## Quick Start
 
-**Requirements:** Python 3.11 or newer.
+**Requirements:** Python 3.11 or newer. Check your version first with `python3 --version` — it must report 3.11 or higher before installing.
 
 ```bash
 pip install talkpipe
@@ -144,14 +145,32 @@ pip install talkpipe[model2vec] # In-process static embeddings (also in [all])
 # Or: pip install talkpipe[all]
 ```
 
-Configure API keys and provider URLs via environment variables (for example `TALKPIPE_openai_api_key`) or `~/.talkpipe.toml`. If TalkPipe runs on a different machine than your Ollama server, set `TALKPIPE_OLLAMA_SERVER_URL` to that host. See **[Configuration](docs/architecture/configuration.md)** for details and ChatterLang `$var` substitution.
+Configure API keys and provider URLs via environment variables (for example `OPENAI_API_KEY` and `ANTHROPIC_API_KEY`) or `~/.talkpipe.toml`. If TalkPipe runs on a different machine than your Ollama server, set `TALKPIPE_OLLAMA_SERVER_URL` to that host. See **[Configuration](docs/architecture/configuration.md)** for details and ChatterLang `$var` substitution.
+
+Quick local syntax check (no LLM server required):
+
+> **Note:** `source="eliza"` is **not** an LLM provider. It is a local, deterministic adapter intended for experimenting with TalkPipe/ChatterLang syntax and multi-turn flow when you do not yet have Ollama/OpenAI/Anthropic access.
+
+```python
+from talkpipe.chatterlang import compiler
+
+script = '| print | llmPrompt[model="Dr. Eliza", source="eliza", multi_turn=True] | print'
+chat = compiler.compile(script).as_function(single_in=True, single_out=True)
+
+chat("Hello, my name is Alice.")
+chat("What's my name?")
+```
 
 Multi-turn chat in a few lines:
 
+> **Prerequisite:** this example uses Ollama, which is a separate application, not just the `talkpipe[ollama]` Python package. Install and start it from https://ollama.com/download, then pull the model with `ollama pull llama3.2`. Cloud users can skip Ollama and substitute `source="openai"` or `source="anthropic"` (see the commented variants below).
+
 ```python
 from talkpipe.chatterlang import compiler
 
 script = '| print | llmPrompt[model="llama3.2", source="ollama", multi_turn=True] | print'
+# Using OpenAI:    model="gpt-4o-mini", source="openai"      (set OPENAI_API_KEY)
+# Using Anthropic: model="claude-haiku-4-5", source="anthropic" (set ANTHROPIC_API_KEY)
 chat = compiler.compile(script).as_function(single_in=True, single_out=True)
 
 response = chat("Hello! My name is Alice.")
@@ -581,7 +600,7 @@ smtp_port = 587
 Environment variables use the `TALKPIPE_` prefix:
 ```bash
 export TALKPIPE_email_password="your-password"
-export TALKPIPE_openai_api_key="sk-..."
+export OPENAI_API_KEY="sk-..."
 ```
 
 ### Performance Optimization
@@ -638,17 +657,17 @@ def multiplyBy(items, factor=2):
     for item in items:
         yield item * factor
 
-# Use it to double the Fibonacci numbers
+# Use it to multiply each value in the range by 3
 pipeline = arange(lower=5, upper=10) | multiplyBy(factor=3) | io.Print()
 result = pipeline.as_function(single_out=False)()
 
 # Output:
-# 0
-# 3
-# 3
-# 6
-# 9
-# Returns: [0, 3, 3, 6, 9]
+# 15
+# 18
+# 21
+# 24
+# 27
+# Returns: [15, 18, 21, 24, 27]
 ```
 
 **Field Segments** provide a convenient way to create 1:1 segments:

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/README.md

@@ -20,7 +20,7 @@ This README is a high-level overview. Use the **[documentation map](#documentati
 
 ## What Can You Do With TalkPipe?
 
-- **Chat with LLMs** - Create multi-turn conversations with OpenAI, Ollama, or Anthropic models in just 2 lines of code
+- **Chat with LLMs** - Create multi-turn conversations with OpenAI, Ollama, or Anthropic models in just a few lines of code
 - **Process Documents** - Extract text from PDFs, analyze research papers, score content relevance
 - **Build RAG Pipelines** - Create end-to-end Retrieval-Augmented Generation workflows with vector databases
 - **Analyze Web Content** - Download web pages (respecting robots.txt), extract readable text, and summarize
@@ -69,7 +69,7 @@ These applications are entry points for different usage scenarios, from interact
 
 ## Quick Start
 
-**Requirements:** Python 3.11 or newer.
+**Requirements:** Python 3.11 or newer. Check your version first with `python3 --version` — it must report 3.11 or higher before installing.
 
 ```bash
 pip install talkpipe
@@ -85,14 +85,32 @@ pip install talkpipe[model2vec] # In-process static embeddings (also in [all])
 # Or: pip install talkpipe[all]
 ```
 
-Configure API keys and provider URLs via environment variables (for example `TALKPIPE_openai_api_key`) or `~/.talkpipe.toml`. If TalkPipe runs on a different machine than your Ollama server, set `TALKPIPE_OLLAMA_SERVER_URL` to that host. See **[Configuration](docs/architecture/configuration.md)** for details and ChatterLang `$var` substitution.
+Configure API keys and provider URLs via environment variables (for example `OPENAI_API_KEY` and `ANTHROPIC_API_KEY`) or `~/.talkpipe.toml`. If TalkPipe runs on a different machine than your Ollama server, set `TALKPIPE_OLLAMA_SERVER_URL` to that host. See **[Configuration](docs/architecture/configuration.md)** for details and ChatterLang `$var` substitution.
+
+Quick local syntax check (no LLM server required):
+
+> **Note:** `source="eliza"` is **not** an LLM provider. It is a local, deterministic adapter intended for experimenting with TalkPipe/ChatterLang syntax and multi-turn flow when you do not yet have Ollama/OpenAI/Anthropic access.
+
+```python
+from talkpipe.chatterlang import compiler
+
+script = '| print | llmPrompt[model="Dr. Eliza", source="eliza", multi_turn=True] | print'
+chat = compiler.compile(script).as_function(single_in=True, single_out=True)
+
+chat("Hello, my name is Alice.")
+chat("What's my name?")
+```
 
 Multi-turn chat in a few lines:
 
+> **Prerequisite:** this example uses Ollama, which is a separate application, not just the `talkpipe[ollama]` Python package. Install and start it from https://ollama.com/download, then pull the model with `ollama pull llama3.2`. Cloud users can skip Ollama and substitute `source="openai"` or `source="anthropic"` (see the commented variants below).
+
 ```python
 from talkpipe.chatterlang import compiler
 
 script = '| print | llmPrompt[model="llama3.2", source="ollama", multi_turn=True] | print'
+# Using OpenAI:    model="gpt-4o-mini", source="openai"      (set OPENAI_API_KEY)
+# Using Anthropic: model="claude-haiku-4-5", source="anthropic" (set ANTHROPIC_API_KEY)
 chat = compiler.compile(script).as_function(single_in=True, single_out=True)
 
 response = chat("Hello! My name is Alice.")
@@ -522,7 +540,7 @@ smtp_port = 587
 Environment variables use the `TALKPIPE_` prefix:
 ```bash
 export TALKPIPE_email_password="your-password"
-export TALKPIPE_openai_api_key="sk-..."
+export OPENAI_API_KEY="sk-..."
 ```
 
 ### Performance Optimization
@@ -579,17 +597,17 @@ def multiplyBy(items, factor=2):
     for item in items:
         yield item * factor
 
-# Use it to double the Fibonacci numbers
+# Use it to multiply each value in the range by 3
 pipeline = arange(lower=5, upper=10) | multiplyBy(factor=3) | io.Print()
 result = pipeline.as_function(single_out=False)()
 
 # Output:
-# 0
-# 3
-# 3
-# 6
-# 9
-# Returns: [0, 3, 3, 6, 9]
+# 15
+# 18
+# 21
+# 24
+# 27
+# Returns: [15, 18, 21, 24, 27]
 ```
 
 **Field Segments** provide a convenient way to create 1:1 segments:

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/docs/architecture/configuration.md

@@ -27,7 +27,8 @@ logger_levels = "root:INFO,talkpipe:DEBUG"
 logger_files = "talkpipe:/tmp/talkpipe.log,root:/tmp/app.log"
 
 # LLM Configuration
-openai_api_key = "your-api-key-here"
+default_model_name = "llama3.2"
+default_model_source = "ollama"
 ollama_base_url = "http://localhost:11434"
 
 # Server Configuration
@@ -58,6 +59,10 @@ The configuration system loads a single TOML file from:
 
 All TalkPipe environment variables use the prefix `TALKPIPE_` followed by the configuration key name in uppercase.
 
+Provider SDK credentials are separate from TalkPipe config keys:
+- OpenAI SDK reads `OPENAI_API_KEY`
+- Anthropic SDK reads `ANTHROPIC_API_KEY`
+
 #### Environment Variable Examples
 
 ```bash
@@ -211,7 +216,8 @@ In the script:
 **Best Practices:**
 ```bash
 # ✅ Use environment variables for secrets
-export TALKPIPE_OPENAI_API_KEY="sk-your-secret-key"
+export OPENAI_API_KEY="sk-your-secret-key"
+export ANTHROPIC_API_KEY="your-anthropic-key"
 
 # ❌ Avoid putting secrets in config files
 # ~/.talkpipe.toml
@@ -281,7 +287,7 @@ config = get_config(reload=True)  # Re-reads from sources
 ```bash
 # Use environment variables for local development
 export TALKPIPE_LOGGER_LEVELS="root:DEBUG,talkpipe:DEBUG"
-export TALKPIPE_OPENAI_API_KEY="sk-dev-key"
+export OPENAI_API_KEY="sk-dev-key"
 export TALKPIPE_DEFAULT_PORT="8080"
 
 # Use local configuration file for persistent settings

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/docs/architecture/extending-talkpipe.md

@@ -6,6 +6,8 @@ This guide explains how to add custom **sources** (pipeline starters) and **segm
 
 You usually implement a segment as a small function and attach two decorators: `@segment()` turns the function into a segment class factory, and `@register_segment("nameInChatterLang")` adds that class to the global registry under one or more ChatterLang names.
 
+> **Import note:** `talkpipe` re-exports `segment`, `register_segment`, `compile`, and friends at the top level as convenience shortcuts. `from talkpipe import segment, register_segment` and `from talkpipe.chatterlang import registry, compiler` (used in the README) are equivalent — pick one style and use it consistently. This guide uses the top-level shortcuts.
+
 ```python
 from typing import Iterator, Any
 
@@ -285,14 +287,20 @@ INPUT FROM apiData(url="https://api.example.com/data")
 
 ### Entry points for distributable components
 
-For code in **this** repository, after adding or renaming `@register_segment` / `@register_source` classes, regenerate `pyproject.toml` entry points with:
+Segments and sources are discovered through the **`talkpipe.segments`** and **`talkpipe.sources`** entry point groups. How you keep those aligned with your decorators depends on whether you are writing a third-party package or contributing to the TalkPipe repository itself.
+
+#### For third-party plugin authors
+
+In your **own** package, declare the same groups in your `pyproject.toml`, pointing each name at `module:ClassName` (the class your decorators attach to). This is all a distributable plugin needs — you do **not** need any TalkPipe repo tooling.
+
+#### For TalkPipe repo contributors (this repository only)
+
+When working inside the TalkPipe source checkout, after adding or renaming `@register_segment` / `@register_source` classes, regenerate `pyproject.toml` entry points with the repo-internal script (not shipped with the installed package):
 
 `python .cursor/skills/update-entry-points/scripts/update_entry_points.py`
 
 (from the project root; see [protocol.md](protocol.md)). That keeps **`talkpipe.segments`** and **`talkpipe.sources`** aligned with decorators so installs and lazy loading resolve the right modules.
 
-In a **separate** package, declare the same groups in your own `pyproject.toml`, pointing each name at `module:ClassName` (the class your decorators attach to).
-
 ### `talkpipe.plugins` (optional)
 
 The `talkpipe.plugins` entry point group is separate from per-segment registration. Importing `talkpipe` runs `load_plugins()`, which loads each plugin entry point. Prefer pointing the entry point at a **module** so importing it runs your `@register_*` decorators; optionally define a module-level `initialize_plugin()` for extra setup. See [TalkPipe Plugin Manager](../api-reference/talkpipe-plugin-manager.md) for CLI (`talkpipe_plugins`) and configuration details.

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/docs/guides/model-and-source-configuration.md

@@ -117,7 +117,7 @@ The first piece of the pattern above is the `source` value itself. Sources are r
 
 | Segment | Registered sources |
 |---------|-------------------|
-| **`llmPrompt`** (chat) | `ollama`, `openai`, `anthropic` |
+| **`llmPrompt`** (chat) | `ollama`, `openai`, `anthropic`, `eliza` |
 | **`llmVisionPrompt`** (multimodal chat) | `ollama`, `openai`, `anthropic` |
 | **`llmEmbed`** (embeddings) | `ollama`, `openai`, `model2vec` |
 
@@ -344,7 +344,17 @@ INPUT FROM prompt[data="Hello"]
 | print
 ```
 
-### 2. Global defaults in TOML
+### 2. Local Eliza source (no provider API key)
+
+`eliza` is a local adapter. Set `model` to the name Eliza should use when referring to itself.
+
+```chatterlang
+INPUT FROM prompt[data="I'm feeling stuck on a bug."]
+| llmPrompt[model="Dr. Eliza", source="eliza", multi_turn=True]
+| print
+```
+
+### 3. Global defaults in TOML
 
 With `default_model_name` and `default_model_source` set in `~/.talkpipe.toml`:
 
@@ -354,7 +364,7 @@ INPUT FROM prompt[data="Hello"]
 | print
 ```
 
-### 3. Environment-only defaults (containers / CI)
+### 4. Environment-only defaults (containers / CI)
 
 ```bash
 export TALKPIPE_default_model_name=llama3.2
@@ -385,7 +395,7 @@ ENV TALKPIPE_default_model_name=gpt-4o \
 
 `OPENAI_API_KEY` is intentionally left to the runtime (a Docker secret, Kubernetes secret, or `--env` flag) rather than baked into the image.
 
-### 4. ChatterLang `$key` and CLI overrides
+### 5. ChatterLang `$key` and CLI overrides
 
 ```bash
 chatterlang_script --script 'INPUT FROM prompt[data="Hi"] | llmPrompt[model=$default_model_name, source=$default_model_source] | print' \
@@ -393,7 +403,7 @@ chatterlang_script --script 'INPUT FROM prompt[data="Hi"] | llmPrompt[model=$def
   --default_model_source ollama
 ```
 
-### 5. Pipe API with config fallback
+### 6. Pipe API with config fallback
 
 ```python
 from talkpipe.llm.chat import LLMPrompt
@@ -409,7 +419,7 @@ segment = LLMPrompt(system_prompt="You are helpful.")
 | Symptom | What to check |
 |---------|----------------|
 | `Model name and source must be provided` | Set `model` and `source` on the segment, or add `default_model_name` and `default_model_source` (or embedding equivalents for `llmEmbed`). |
-| `Unknown source` | Chat / vision: use `ollama`, `openai`, or `anthropic`. Embeddings: use `ollama` or `openai` (or register additional adapters). |
+| `Unknown source` | Chat / vision: use `ollama`, `openai`, `anthropic`, or `eliza` (chat only). Embeddings: use `ollama`, `openai`, or `model2vec` (or register additional adapters). |
 | `llmVisionPrompt` errors at the provider with model-not-found / unsupported-input | `llmVisionPrompt` reads `default_model_name` / `default_model_source` (the chat defaults). Set `model` and `source` explicitly on the segment, or change the chat defaults to a vision-capable model. |
 | Ollama connection refused | Run `ollama serve` or set `OLLAMA_SERVER_URL` / `TALKPIPE_OLLAMA_SERVER_URL`. |
 | OpenAI / Anthropic auth errors | Set `OPENAI_API_KEY` or `ANTHROPIC_API_KEY`; these are not read from `TALKPIPE_*` model keys. |

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/docs/quickstart.md

@@ -81,6 +81,26 @@ pipeline = compiler.compile(script).as_function(single_out=False)
 pipeline()  # Skips "hello", prints 1, 2, 3, 4
 ```
 
+## Local Syntax Sandbox (No LLM Backend Needed)
+
+If you do not have Ollama/OpenAI/Anthropic access yet, you can still practice
+TalkPipe and ChatterLang syntax with `source="eliza"`.
+
+`eliza` is **not** an LLM provider. It is a local deterministic adapter meant for
+testing pipeline shape, parameter wiring, and multi-turn flow.
+
+### ChatterLang
+
+```python
+from talkpipe.chatterlang import compiler
+
+script = '| llmPrompt[model="Dr. Eliza", source="eliza", multi_turn=True] | print'
+chat = compiler.compile(script).as_function(single_in=True, single_out=True)
+
+chat("Hello, my name is Alice.")
+chat("What's my name?")
+```
+
 ## Your First Pipeline (With LLM)
 
 Requires `talkpipe[ollama]` and Ollama running with a model (e.g. `ollama pull llama3.2`).
@@ -137,11 +157,11 @@ Open http://localhost:2025/stream to chat with the LLM.
 For a minimal document Q&A workflow without writing scripts:
 
 ```bash
-makevectordatabase "docs/*.md" --path ./mydb
+makevectordatabase "docs/*.md" --path ./mydb --embedding_source ollama --embedding_model nomic-embed-text
 serverag --path ./mydb
 ```
 
-Then open http://localhost:2026/stream. See [makevectordatabase and serverag](guides/makevectordatabase-and-serverag.md) for full options.
+`--embedding_source` and `--embedding_model` are required unless you set defaults in `~/.talkpipe.toml`; the example above needs Ollama running with the embedding model pulled (`ollama pull nomic-embed-text`). Then open http://localhost:2026/stream. See [makevectordatabase and serverag](guides/makevectordatabase-and-serverag.md) for full options.
 
 ## Next Steps
 

{talkpipe-0.12.2 → talkpipe-0.12.3a2}/pyproject.toml

@@ -43,11 +43,11 @@ dependencies = [
     'pyyaml',
     'greenlet',
     'networkx',
-
     # Security override: starlette is a transitive dependency, pinned here
-    # to fix CVE-2025-62727 (DoS vulnerability). Remove once parent 
+    # to fix CVE-2025-62727 (DoS vulnerability). Remove once parent
     # dependency (e.g., FastAPI) requires starlette>=0.49.1
-    "starlette>=0.49.1"
+    "starlette>=0.49.1",
+    "build>=1.5.0",
 ]
 dynamic = ["version"]