Merge pull request #64 from SylphAI-Inc/li

Li

developer_notes/prompt_note.py

@@ -0,0 +1,84 @@
+def python_str_format_example(task_desc_str: str, input_str: str):
+
+    # percent(%) formatting
+    print("<SYS>%s</SYS> User: %s" % (task_desc_str, input_str))
+
+    # format() method with kwargs
+    print(
+        "<SYS>{task_desc_str}</SYS> User: {input_str}".format(
+            task_desc_str=task_desc_str, input_str=input_str
+        )
+    )
+
+    # f-string
+    print(f"<SYS>{task_desc_str}</SYS> User: {input_str}")
+
+    # Templates
+    from string import Template
+
+    t = Template("<SYS>$task_desc_str</SYS> User: $input_str")
+    print(t.substitute(task_desc_str=task_desc_str, input_str=input_str))
+
+
+def jinja2_template_example(template, **kwargs):
+    from jinja2 import Template
+
+    t = Template(template, trim_blocks=True, lstrip_blocks=True)
+    print(t.render(**kwargs))
+
+
+def lightrag_prompt(template, task_desc_str, input_str, tools=None):
+    from lightrag.core.prompt_builder import Prompt
+
+    prompt = Prompt(
+        template=template,
+        prompt_kwargs={
+            "task_desc_str": task_desc_str,
+            "tools": tools,
+        },
+    )
+    print(prompt)
+    print(prompt(input_str=input_str))
+
+    saved_prompt = prompt.to_dict()
+    restored_prompt = Prompt.from_dict(saved_prompt)
+    print(
+        restored_prompt == prompt
+    )  # False as the jinja2 template can not be serialized, but we recreated the template from the string at the time of restoration, so it works the same
+    print(restored_prompt)
+
+
+def lightrag_default_prompt():
+    from lightrag.core.prompt_builder import Prompt
+
+    prompt = Prompt()
+    input_str = "What is the capital of France?"
+    output = prompt(input_str=input_str)
+    print(output)
+
+
+if __name__ == "__main__":
+
+    task_desc_str = "You are a helpful assitant"
+    input_str = "What is the capital of France?"
+    tools = ["google", "wikipedia", "wikidata"]
+    template = r"""<SYS>{{ task_desc_str }}</SYS>
+{# tools #}
+{% if tools %}
+<TOOLS>
+{% for tool in tools %}
+{{loop.index}}. {{ tool }}
+{% endfor %}
+</TOOLS>
+{% endif %}
+User: {{ input_str }}"""
+    python_str_format_example(task_desc_str, input_str)
+    jinja2_template_example(template, task_desc_str=task_desc_str, input_str=input_str)
+    jinja2_template_example(
+        template, task_desc_str=task_desc_str, input_str=input_str, tools=tools
+    )
+    lightrag_prompt(
+        template, task_desc_str=task_desc_str, input_str=input_str, tools=tools
+    )
+
+    lightrag_default_prompt()

docs/source/apis/components/index.rst

@@ -1,3 +1,5 @@
+.. _apis-components:
+
 Components
 ==============
 
@@ -10,9 +12,9 @@ Overview
    components.agent
    components.model_client
    components.data_process
- 
+
    .. components.reasoning
-   
+
    components.retriever
    components.output_parsers
 
@@ -65,4 +67,3 @@ Retrievers
    :maxdepth: 1
 
    components.retriever
-

docs/source/apis/core/index.rst

@@ -1,3 +1,5 @@
+.. _apis-core:
+
 Core
 ===================
 
@@ -7,7 +9,7 @@ Overview
 ----------
 .. autosummary::
 
-   core.base_data_class  
+   core.base_data_class
    core.component
    core.db
    core.default_prompt_template

docs/source/apis/eval/index.rst

@@ -1,3 +1,5 @@
+.. _apis-eval:
+
 Evaluation
 ==============
 

docs/source/apis/optim/index.rst

@@ -1,3 +1,5 @@
+.. _apis-optim:
+
 .. Optimizer
 .. ==============
 
@@ -22,4 +24,4 @@ Optimizer
    optim.sampler
    optim.few_shot_optimizer
    optim.llm_augment
-   optim.llm_optimizer
+   optim.llm_optimizer

docs/source/apis/tracing/index.rst

@@ -1,3 +1,5 @@
+.. _apis-tracing:
+
 Tracing
 ==============
 
@@ -22,4 +24,4 @@ Loggers
    :maxdepth: 1
 
    tracing.generator_state_logger
-   tracing.generator_call_logger
+   tracing.generator_call_logger

docs/source/apis/utils/index.rst

@@ -1,3 +1,5 @@
+.. _apis-utils:
+
 Utils
 =============================
 
@@ -31,4 +33,3 @@ Setup_env
    :maxdepth: 1
 
    utils.setup_env
-

docs/source/developer_notes/index.rst

@@ -4,7 +4,7 @@
 Tutorials
 =============================
 
-*Why and How Each Part works*
+.. *Why and How Each Part works*
 
 Learn the `why` and `how-to` (customize and integrate) behind each core part within the `LightRAG` library.
 These are our most important tutorials before you move ahead to build use cases  (LLM applications) end to end.
@@ -47,7 +47,8 @@ Building
 -------------------
 Base classes
 ~~~~~~~~~~~~~~~~~~~~~~
-Code path: ``lightrag.core``.
+Code path: :ref:`lightrag.core <apis-core>`.
+
 
 .. list-table::
    :widths: 20 80
@@ -56,9 +57,9 @@ Code path: ``lightrag.core``.
    * - Base Class
      - Description
    * - :doc:`component`
-     - Similar to ``Module`` in `PyTorch`, it standardizes the interface of all components with `call`, `acall`, and `__call__` methods, handles states, and serialization. Components can be easily chained togehter via `Sequential` for now.
+     - The building block for task pipeline. It standardizes the interface of all components with `call`, `acall`, and `__call__` methods, handles state serialization, nested components, and parameters for optimization. Components can be easily chained together via ``Sequential``.
    * - :doc:`base_data_class`
-     - Leverages the ``dataclasses`` module in Python to ease the data interaction with prompt and serialization.
+     - The base class for data. It eases the data interaction with LLMs for both prompt formatting and output parsing.
 
 
 
@@ -79,10 +80,10 @@ RAG components
 ^^^^^^^^^^^^^^^^^^^
 
 
-Code path: ``lightrag.core``. For abstract classes:
+Code path: :ref:`lightrag.core<apis-core>`. For abstract classes:
 
-- ``ModelClient``: the functional subclass is in ``lightrag.components.model_client``.
-- ``Retriever``: the functional subclass is in ``lightrag.components.retriever``. It works hand-in-hand with the ``LocalDB`` and Cloud DB in ``lightrag.database``.
+- ``ModelClient``: the functional subclass is in :ref:`lightrag.components.model_client<components-model_client>`.
+- ``Retriever``: the functional subclass is in :ref:`lightrag.components.retriever<components-retriever>`.
 
 
 .. list-table::
@@ -92,11 +93,13 @@ Code path: ``lightrag.core``. For abstract classes:
    * - Part
      - Description
    * - :doc:`prompt`
-     - Built on ``jinja2``, it programmablly and flexibly format prompt(text) as **input to the generator**.
+     - Built on `jinja2`, it programmatically and flexibly formats prompts as input to the generator.
    * - :doc:`model_client`
      - ``ModelClient`` is the protocol and base class for LightRAG to **integrate all models**, either APIs or local, LLMs or Embedding models or any others.
    * - :doc:`generator`
      - The **center component** that orchestrates the model client(LLMs in particular), prompt, and output processors for format parsing or any post processing.
+   * - :doc:`output_parsers`
+     - The component that parses the output string to structured data.
    * - :doc:`embedder`
      - The component that orchestrates model client (Embedding models in particular) and output processors.
    * - :doc:`retriever`
@@ -133,6 +136,7 @@ Components work on a sequence of ``Document`` and return a sequence of ``Documen
    prompt
    model_client
    generator
+   output_parsers
    embedder
    retriever
    text_splitter

docs/source/developer_notes/output_parsers.rst

@@ -0,0 +1,2 @@
+OutputParser
+=============