bulk-chain 1.0.0__tar.gz → 1.2.1__tar.gz

bulk_chain-1.2.1/PKG-INFO

@@ -0,0 +1,134 @@
+Metadata-Version: 2.1
+Name: bulk_chain
+Version: 1.2.1
+Summary: A lightweight, no-strings-attached Chain-of-Thought framework for your LLM, ensuring reliable results for bulk input requests.
+Home-page: https://github.com/nicolay-r/bulk-chain
+Author: Nicolay Rusnachenko
+Author-email: rusnicolay@gmail.com
+License: MIT License
+Description: # bulk-chain 1.2.1
+        ![](https://img.shields.io/badge/Python-3.9-brightgreen.svg)
+        [![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nicolay-r/bulk-chain/blob/master/bulk_chain_tutorial.ipynb)
+        [![twitter](https://img.shields.io/twitter/url/https/shields.io.svg?style=social)](https://x.com/nicolayr_/status/1847969224636961033)
+        [![PyPI downloads](https://img.shields.io/pypi/dm/bulk-chain.svg)](https://pypistats.org/packages/bulk-chain)
+        
+        <p align="center">
+            <img src="logo.png"/>
+        </p>
+        
+        <p align="center">
+          <a href="https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm"><b>Third-party providers hosting</b>↗️</a>
+          <br>
+          <a href="https://github.com/nicolay-r/bulk-chain-shell">👉<b>demo</b>👈</a>
+        </p>
+        
+        A no-strings-attached **framework**  for your LLM that allows applying Chain-of-Thought-alike [prompt `schema`](#chain-of-thought-schema) towards a massive textual collections using custom **[third-party providers ↗️](https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm)**.
+        
+        ### Main Features
+        * ✅ **No-strings**: you're free to LLM dependencies and flexible `venv` customization.
+        * ✅ **Support schemas descriptions** for Chain-of-Thought concept.
+        * ✅ **Provides iterator over infinite amount of input contexts**
+        
+        # Installation
+        
+        From PyPI: 
+        
+        ```bash
+        pip install --no-deps bulk-chain
+        ```
+        
+        or latest version from here:
+        
+        ```bash
+        pip install git+https://github.com/nicolay-r/bulk-chain@master
+        ```
+        
+        ## Chain-of-Thought Schema
+        
+        To declare Chain-of-Though (CoT) schema we use `JSON` format. 
+        The field `schema` is a list of CoT instructions for the Large Language Model.
+        Each item of the list represent a dictionary with `prompt` and `out` keys that corresponds to the input prompt and output variable name respectively.
+        All the variable names should be mentioned in `{}`.
+        
+        **Example**:
+        ```python
+        [
+          {"prompt": "extract topic: {text}", "out": "topic"},
+          {"prompt": "extract subject: {text}", "out": "subject"},
+        ]
+        ```
+        
+        # Usage
+        
+        ## 🤖 Prepare 
+        
+        1. [schema](#chain-of-thought-schema)
+            * [Example for Sentiment Analysis](test/schema/thor_cot_schema.json)
+        2. **LLM model** from the [<b>Third-party providers hosting</b>↗️](https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm).
+        3. Data (iter of dictionaries)
+        
+        ## 🚀 Launch
+        
+        > **API**: For more details see the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+        
+        ```python
+        from bulk_chain.core.utils import dynamic_init
+        from bulk_chain.api import iter_content
+        
+        content_it = iter_content(
+            # 1. Your schema.              
+            schema=[
+              {"prompt": "extract topic: {text}", "out": "topic" },
+              {"prompt": "extract subject: {text}", "out": "subject"},
+            ],
+            # 2. Your third-party model implementation.
+            llm=dynamic_init(class_filepath="replicate_104.py")(
+               api_token="<API-KEY>",
+               model_name="meta/meta-llama-3-70b-instruct"),
+            # 3. Toggle streaming if needed
+            stream=False,
+            # 4. Toggle Async API mode usage.
+            async_mode=True,
+            # 5. Batch size.
+            batch_size=10,
+            # 6. Your iterator of dictionaries
+            input_dicts_it=[
+                # Example of data ...
+                { "text": "Rocks are hard" },
+                { "text": "Water is wet" },
+                { "text": "Fire is hot" }
+            ],
+        )
+            
+        for batch in content_it:
+           for entry in batch:
+              print(entry)
+        ```
+        
+        Outputs entries represent texts augmented with `topic` and `subject`:
+        ```jsonl
+        {'text': 'Rocks are hard', 'topic': 'The topic is: Geology/Rocks', 'subject': 'The subject is: "Rocks"'}
+        {'text': 'Water is wet', 'topic': 'The topic is: Properties of Water', 'subject': 'The subject is: Water'}
+        {'text': 'Fire is hot', 'topic': 'The topic is: Temperature/Properties of Fire', 'subject': 'The subject is: "Fire"'}
+        ```
+        
+        # API
+        
+        | Method               | Mode       | Description                                                         |
+        |----------------------|------------|---------------------------------------------------------------------|
+        | `ask(prompt)`        | Sync       | Infers the model with a single prompt.                              |
+        | `ask_stream(prompt)` | Sync       | Returns a generator that yields chunks of the inferred result.      |
+        | `ask_async(prompt)`  | Async      | Asynchronously infers the model with a single prompt.               |
+        | `ask_stream_async(prompt)` | Async | Asynchronously returns a generator of result chunks of the inferred result.          |
+        
+        See examples with models [at nlp-thirdgate 🌌](https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm).
+        
+Keywords: natural language processing,chain-of-thought,reasoning
+Platform: UNKNOWN
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.6
+Description-Content-Type: text/markdown

bulk_chain-1.2.1/README.md

@@ -0,0 +1,116 @@
+# bulk-chain 1.2.1
+![](https://img.shields.io/badge/Python-3.9-brightgreen.svg)
+[![](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/nicolay-r/bulk-chain/blob/master/bulk_chain_tutorial.ipynb)
+[![twitter](https://img.shields.io/twitter/url/https/shields.io.svg?style=social)](https://x.com/nicolayr_/status/1847969224636961033)
+[![PyPI downloads](https://img.shields.io/pypi/dm/bulk-chain.svg)](https://pypistats.org/packages/bulk-chain)
+
+<p align="center">
+    <img src="logo.png"/>
+</p>
+
+<p align="center">
+  <a href="https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm"><b>Third-party providers hosting</b>↗️</a>
+  <br>
+  <a href="https://github.com/nicolay-r/bulk-chain-shell">👉<b>demo</b>👈</a>
+</p>
+
+A no-strings-attached **framework**  for your LLM that allows applying Chain-of-Thought-alike [prompt `schema`](#chain-of-thought-schema) towards a massive textual collections using custom **[third-party providers ↗️](https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm)**.
+
+### Main Features
+* ✅ **No-strings**: you're free to LLM dependencies and flexible `venv` customization.
+* ✅ **Support schemas descriptions** for Chain-of-Thought concept.
+* ✅ **Provides iterator over infinite amount of input contexts**
+
+# Installation
+
+From PyPI: 
+
+```bash
+pip install --no-deps bulk-chain
+```
+
+or latest version from here:
+
+```bash
+pip install git+https://github.com/nicolay-r/bulk-chain@master
+```
+
+## Chain-of-Thought Schema
+
+To declare Chain-of-Though (CoT) schema we use `JSON` format. 
+The field `schema` is a list of CoT instructions for the Large Language Model.
+Each item of the list represent a dictionary with `prompt` and `out` keys that corresponds to the input prompt and output variable name respectively.
+All the variable names should be mentioned in `{}`.
+
+**Example**:
+```python
+[
+  {"prompt": "extract topic: {text}", "out": "topic"},
+  {"prompt": "extract subject: {text}", "out": "subject"},
+]
+```
+
+# Usage
+
+## 🤖 Prepare 
+
+1. [schema](#chain-of-thought-schema)
+    * [Example for Sentiment Analysis](test/schema/thor_cot_schema.json)
+2. **LLM model** from the [<b>Third-party providers hosting</b>↗️](https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm).
+3. Data (iter of dictionaries)
+
+## 🚀 Launch
+
+> **API**: For more details see the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+
+```python
+from bulk_chain.core.utils import dynamic_init
+from bulk_chain.api import iter_content
+
+content_it = iter_content(
+    # 1. Your schema.              
+    schema=[
+      {"prompt": "extract topic: {text}", "out": "topic" },
+      {"prompt": "extract subject: {text}", "out": "subject"},
+    ],
+    # 2. Your third-party model implementation.
+    llm=dynamic_init(class_filepath="replicate_104.py")(
+       api_token="<API-KEY>",
+       model_name="meta/meta-llama-3-70b-instruct"),
+    # 3. Toggle streaming if needed
+    stream=False,
+    # 4. Toggle Async API mode usage.
+    async_mode=True,
+    # 5. Batch size.
+    batch_size=10,
+    # 6. Your iterator of dictionaries
+    input_dicts_it=[
+        # Example of data ...
+        { "text": "Rocks are hard" },
+        { "text": "Water is wet" },
+        { "text": "Fire is hot" }
+    ],
+)
+    
+for batch in content_it:
+   for entry in batch:
+      print(entry)
+```
+
+Outputs entries represent texts augmented with `topic` and `subject`:
+```jsonl
+{'text': 'Rocks are hard', 'topic': 'The topic is: Geology/Rocks', 'subject': 'The subject is: "Rocks"'}
+{'text': 'Water is wet', 'topic': 'The topic is: Properties of Water', 'subject': 'The subject is: Water'}
+{'text': 'Fire is hot', 'topic': 'The topic is: Temperature/Properties of Fire', 'subject': 'The subject is: "Fire"'}
+```
+
+# API
+
+| Method               | Mode       | Description                                                         |
+|----------------------|------------|---------------------------------------------------------------------|
+| `ask(prompt)`        | Sync       | Infers the model with a single prompt.                              |
+| `ask_stream(prompt)` | Sync       | Returns a generator that yields chunks of the inferred result.      |
+| `ask_async(prompt)`  | Async      | Asynchronously infers the model with a single prompt.               |
+| `ask_stream_async(prompt)` | Async | Asynchronously returns a generator of result chunks of the inferred result.          |
+
+See examples with models [at nlp-thirdgate 🌌](https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm).

bulk_chain-1.2.1/bulk_chain/api.py

@@ -0,0 +1,229 @@
+import asyncio
+import collections
+import logging
+import os
+from itertools import chain
+from types import AsyncGeneratorType
+
+from bulk_chain.core.llm_base import BaseLM
+from bulk_chain.core.service_asyncio import AsyncioService
+from bulk_chain.core.service_batch import BatchIterator
+from bulk_chain.core.service_data import DataService
+from bulk_chain.core.service_dict import DictionaryService
+from bulk_chain.core.service_json import JsonService
+from bulk_chain.core.service_schema import SchemaService
+from bulk_chain.core.utils import attempt_wrapper
+
+
+INFER_MODES = {
+    "single": lambda llm, batch, **kwargs: [llm.ask(prompt) for prompt in batch],
+    "batch": lambda llm, batch, **kwargs: llm.ask_batch(batch),
+    "single_stream": lambda llm, batch, **kwargs: [llm.ask_stream(prompt) for prompt in batch],
+    "batch_async": lambda llm, batch, **kwargs: AsyncioService.run_tasks(
+        batch=batch, async_handler=llm.ask_async, event_loop=kwargs.get("event_loop")
+    ),
+    "batch_stream_async": lambda llm, batch, **kwargs: AsyncioService.run_tasks(
+        batch=batch, async_handler=llm.ask_stream_async, event_loop=kwargs.get("event_loop")
+    ),
+}
+
+
+CWD = os.getcwd()
+
+
+def _iter_batch_prompts(c, batch_content_it, **kwargs):
+    for ind_in_batch, entry in enumerate(batch_content_it):
+        content = DataService.get_prompt_text(
+            prompt=entry[c]["prompt"],
+            data_dict=entry,
+            handle_missed_func=kwargs["handle_missed_value_func"])
+        yield ind_in_batch, content
+
+
+def __handle_agen_to_gen(handle, batch, event_loop):
+    """ This handler provides conversion of the async generator to generator (sync).
+    """
+
+    def __wrap_with_index(async_gens):
+        async def wrapper(index, agen):
+            async for item in agen:
+                yield index, item
+        return [wrapper(i, agen) for i, agen in enumerate(async_gens)]
+
+    agen_list = handle(batch, event_loop=event_loop)
+
+    it = AsyncioService.async_gen_to_iter(
+        gen=AsyncioService.merge_generators(*__wrap_with_index(agen_list)),
+        loop=event_loop)
+
+    for ind_in_batch, chunk in it:
+        yield ind_in_batch, str(chunk)
+
+
+def __handle_gen(handle, batch, event_loop):
+    """ This handler deals with the iteration of each individual element of the batch.
+    """
+
+    def _iter_entry_content(entry):
+        if isinstance(entry, str):
+            yield entry
+        elif isinstance(entry, collections.abc.Iterable):
+            for chunk in map(lambda item: str(item), entry):
+                yield chunk
+        elif isinstance(entry, AsyncGeneratorType):
+            for chunk in AsyncioService.async_gen_to_iter(entry, loop=event_loop):
+                yield str(chunk)
+        else:
+            raise Exception(f"Non supported type `{type(entry)}` for handling output from batch")
+
+    for ind_in_batch, entry in enumerate(handle(batch, event_loop=event_loop)):
+        for chunk in _iter_entry_content(entry=entry):
+            yield ind_in_batch, chunk
+
+
+def _iter_chunks(p_column, batch_content_it, **kwargs):
+    handler = __handle_agen_to_gen if kwargs["infer_mode"] == "batch_stream_async" else __handle_gen
+    p_batch = [item[p_column] for item in batch_content_it]
+    it = handler(handle=kwargs["handle_batch_func"], batch=p_batch, event_loop=kwargs["event_loop"])
+    for ind_in_batch, chunk in it:
+        yield ind_in_batch, chunk
+
+
+def _column_ordered_chunks_iter(batch, schema, cols=None, keep_prompts=True, **kwargs):
+    """
+    NOTE: we populate `batch` content automatically
+    """
+    assert (isinstance(batch, list))
+
+    if len(batch) == 0:
+        return
+
+    if cols is None:
+        first_item = batch[0]
+        cols = list(first_item.keys()) if cols is None else cols
+
+    for c in cols:
+
+        # Handling prompt column.
+        if c in schema.p2r:
+            content_it = _iter_batch_prompts(c=c, batch_content_it=iter(batch), **kwargs)
+            for ind_in_batch, prompt in content_it:
+                batch[ind_in_batch][c] = prompt
+
+        # Handling column for inference.
+        if c in schema.r2p:
+            content_it = _iter_chunks(p_column=schema.r2p[c], batch_content_it=iter(batch), **kwargs)
+            # Register values.
+            for item in batch:
+                item[c] = []
+            for ind_in_batch, chunk in content_it:
+                # Append batch.
+                batch[ind_in_batch][c].append(chunk)
+                yield [ind_in_batch, c, chunk]
+
+            # Convert content to string.
+            for item in batch:
+                item[c] = "".join(item[c])
+
+    if not keep_prompts:
+        for batch_item in batch:
+            for key in list(batch_item.keys()):
+                prompt_col = SchemaService.col_to_prompt(col_name=key, prompt_data=batch_item)
+                if prompt_col in batch_item:
+                    del batch_item[prompt_col]
+
+
+def _infer_batch(return_type, batch, batch_ind, **kwargs):
+    assert (return_type in ["batch", "chunk", "record"])
+
+    # Filling batch with inference content.
+    for ind_in_batch, column, chunk in _column_ordered_chunks_iter(batch=batch, **kwargs):
+        if return_type == "chunk":
+            global_ind = batch_ind * len(batch) + ind_in_batch
+            yield [global_ind, column, chunk]
+
+    if return_type == "record":
+        for record in batch:
+            yield record
+
+    if return_type == "batch":
+        yield batch
+
+
+def get_infer_mode(stream, batch_size, async_mode):
+    if not stream and batch_size == 1:
+        return 'single', 'record'
+    elif not stream and batch_size > 1:
+        if async_mode:
+            return 'batch_async', 'batch'
+        else:
+            return 'batch', 'batch'
+    elif stream and batch_size == 1:
+        return 'single_stream', 'chunk'
+    elif stream and batch_size > 1:
+        return 'batch_stream_async', 'chunk'
+
+    raise ValueError(f"Invalid combination of stream and batch_size: {stream}, {batch_size}")
+
+
+def iter_content(input_dicts_it, llm, schema, batch_size=1, limit_prompt=None,
+                 stream=False, async_mode=False, attempts=1, event_loop=None,
+                 handle_missed_value_func=lambda *_: None, **kwargs):
+    """ This method represent Python API aimed at application of `llm` towards
+        iterator of input_dicts via cache_target that refers to the SQLite using
+        the given `schema`
+    """
+    assert (isinstance(llm, BaseLM))
+    assert (isinstance(batch_size, int) and batch_size > 0)
+    assert (isinstance(async_mode, bool)) 
+
+    infer_type, return_type = get_infer_mode(stream=stream, batch_size=batch_size, async_mode=async_mode)
+    infer_mode = INFER_MODES[infer_type]
+
+    # Setup event loop.
+    event_loop = asyncio.get_event_loop_policy().get_event_loop() \
+        if event_loop is None else event_loop
+
+    # Quick initialization of the schema.
+    if isinstance(schema, str):
+        schema = JsonService.read(schema)
+    if isinstance(schema, dict):
+        schema = SchemaService(json_data=schema)
+    if isinstance(schema, list):
+        schema = SchemaService(json_data={"schema": schema})
+
+    prompts_it = map(
+        lambda data: DictionaryService.custom_update(src_dict=dict(data), other_dict=schema.cot_args),
+        input_dicts_it
+    )
+
+    handle_batch_func = lambda batch, **handle_kwargs: infer_mode(
+        llm,
+        DataService.limit_prompts(batch, limit=limit_prompt),
+        **handle_kwargs
+    )
+
+    # Optional wrapping into attempts.
+    if attempts > 1:
+        # Optional setup of the logger.
+        logger = logging.getLogger(__name__)
+        logging.basicConfig(level=logging.INFO)
+
+        attempt_dec = attempt_wrapper(attempts=attempts,
+                                      delay_sec=kwargs.get("attempt_delay_sec", 1),
+                                      logger=logger)
+        handle_batch_func = attempt_dec(handle_batch_func)
+
+    kwargs["handle_missed_value_func"] = handle_missed_value_func
+
+    content_it = (_infer_batch(return_type=return_type,
+                               batch=batch,
+                               batch_ind=batch_ind,
+                               infer_mode=infer_mode,
+                               handle_batch_func=handle_batch_func,
+                               schema=schema,
+                               event_loop=event_loop,
+                               **kwargs)
+                  for batch_ind, batch in enumerate(BatchIterator(prompts_it, batch_size=batch_size)))
+
+    yield from chain.from_iterable(content_it)

bulk_chain-1.2.1/bulk_chain/core/llm_base.py

@@ -0,0 +1,29 @@
+class BaseLM(object):
+
+    def __init__(self, **kwargs):
+        pass
+
+    def ask(self, prompt):
+        """ Assumes to return str.
+        """
+        raise NotImplemented()
+
+    def ask_batch(self, batch):
+        """ Assumes to return generator.
+        """
+        raise NotImplemented()
+
+    def ask_stream(self, prompt):
+        """ Assumes to return generator.
+        """
+        raise NotImplemented()
+
+    async def ask_async(self, prompt):
+        """ Assumes to return co-routine.
+        """
+        raise NotImplemented()
+
+    async def ask_stream_async(self, prompt):
+        """ Assumes to return AsyncGenerator.
+        """
+        raise NotImplemented()

bulk_chain-1.2.1/bulk_chain/core/service_asyncio.py

@@ -0,0 +1,65 @@
+import asyncio
+from typing import AsyncGenerator, Any
+
+
+class AsyncioService:
+
+    @staticmethod
+    async def _run_tasks_async(batch, async_handler):
+        tasks = [async_handler(prompt) for prompt in batch]
+        return await asyncio.gather(*tasks)
+
+    @staticmethod
+    async def _run_generator(gen, output_queue, idx):
+        try:
+            async for item in gen:
+                await output_queue.put((idx, item))
+        finally:
+            await output_queue.put((idx, StopAsyncIteration))
+
+
+    @staticmethod
+    def run_tasks(event_loop, **tasks_kwargs):
+        return event_loop.run_until_complete(AsyncioService._run_tasks_async(**tasks_kwargs))
+
+    @staticmethod
+    async def merge_generators(*gens: AsyncGenerator[Any, None]) -> AsyncGenerator[Any, None]:
+
+        output_queue = asyncio.Queue()
+        tasks = [
+            asyncio.create_task(AsyncioService._run_generator(gen, output_queue, idx))
+            for idx, gen in enumerate(gens)
+        ]
+
+        finished = set()
+        while len(finished) < len(tasks):
+            idx, item = await output_queue.get()
+            if item is StopAsyncIteration:
+                finished.add(idx)
+            else:
+                yield item
+
+        for task in tasks:
+            task.cancel()
+
+    @staticmethod
+    def async_gen_to_iter(gen, loop=None):
+        """ This approach is limited. Could be considered as legacy.
+            https://stackoverflow.com/questions/71580727/translating-async-generator-into-sync-one/78573267#78573267
+        """
+
+        loop_created = False
+        if loop is None:
+            loop_created = True
+            loop = asyncio.new_event_loop()
+
+        asyncio.set_event_loop(loop)
+        try:
+            while True:
+                try:
+                    yield loop.run_until_complete(gen.__anext__())
+                except StopAsyncIteration:
+                    break
+        finally:
+            if loop_created:
+                loop.close()

{bulk_chain-1.0.0 → bulk_chain-1.2.1}/bulk_chain/core/service_batch.py

@@ -1,8 +1,8 @@
 class BatchIterator:
 
     def __init__(self, data_iter, batch_size, end_value=None, filter_func=None):
-        assert(isinstance(batch_size, int) and batch_size > 0)
-        assert(callable(end_value) or end_value is None)
+        assert (isinstance(batch_size, int) and batch_size > 0)
+        assert (callable(end_value) or end_value is None)
         self.__data_iter = data_iter
         self.__index = 0
         self.__batch_size = batch_size

{bulk_chain-1.0.0 → bulk_chain-1.2.1}/bulk_chain/core/service_schema.py

@@ -9,6 +9,10 @@ class SchemaService(object):
         prompt_schema = {"schema": [{"prompt": prompt, "out": "response", "in": "prompt"}]}
         return cls(prompt_schema)
 
+    @staticmethod
+    def col_to_prompt(col_name, prompt_data):
+        return col_name + "_prompt" if "in" not in prompt_data else prompt_data["in"]
+
     @staticmethod
     def __init_schema(prompts):
 
@@ -19,7 +23,7 @@ class SchemaService(object):
 
         for prompt in prompts:
             r_col_name = prompt["out"]
-            p_col_name = r_col_name + "_prompt" if "in" not in prompt else prompt["in"]
+            p_col_name = SchemaService.col_to_prompt(col_name=r_col_name, prompt_data=prompt)
 
             assert r_col_name not in schema_r2p, f"`{r_col_name}` has been already declared!"
             assert p_col_name not in schema_p2r, f"`{p_col_name}` has been already declared!"