bulk-chain 0.25.3__py3-none-any.whl → 1.0.0__py3-none-any.whl

bulk_chain/api.py

@@ -3,7 +3,7 @@ import os
 from itertools import chain
 
 from bulk_chain.core.llm_base import BaseLM
-from bulk_chain.core.service_batch import BatchIterator, BatchService
+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
@@ -20,51 +20,40 @@ INFER_MODES = {
 CWD = os.getcwd()
 
 
-def _handle_entry(entry, entry_info=None, **kwargs):
+def _iter_entry_content(entry, entry_info=None, **kwargs):
 
     if isinstance(entry, str):
         kwargs.get("callback_str_func", lambda *_: None)(entry, entry_info)
-        return entry
+        yield entry
     elif isinstance(entry, collections.abc.Iterable):
-        chunks = []
         h = kwargs.get("callback_stream_func", lambda *_: None)
-
         h(None, entry_info | {"action": "start"})
-
         for chunk in map(lambda item: str(item), entry):
-            chunks.append(chunk)
+            yield chunk
             h(chunk, entry_info)
-
         h(None, entry_info | {"action": "end"})
+    else:
+        raise Exception(f"Non supported type `{type(entry)}` for handling output from batch")
 
-        return "".join(chunks)
 
-    raise Exception(f"Non supported type `{type(entry)}` for handling output from batch")
+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 _update_batch_content(c, batch, schema, **kwargs):
-    assert (isinstance(batch, list))
-    assert (isinstance(c, str))
-
-    if c in schema.p2r:
-        for batch_item in batch:
-            batch_item[c] = DataService.get_prompt_text(
-                prompt=batch_item[c]["prompt"],
-                data_dict=batch_item,
-                handle_missed_func=kwargs["handle_missed_value_func"])
-    if c in schema.r2p:
-        p_column = schema.r2p[c]
-        # This instruction takes a lot of time in a non-batching mode.
-        BatchService.handle_param_as_batch(
-            batch=batch,
-            src_param=p_column,
-            tgt_param=c,
-            handle_batch_func=lambda b: kwargs["handle_batch_func"](b),
-            handle_entry_func=lambda entry, info: _handle_entry(entry=entry, entry_info=info, **kwargs)
-        )
-
-
-def _infer_batch(batch, schema, cols=None, **kwargs):
+def _iter_batch_responses(p_column, c, batch_content_it, **kwargs):
+    p_batch = [item[p_column] for item in batch_content_it]
+    # TODO. This part could be async.
+    # TODO. ind_in_batch might be a part of the async return.
+    for ind_in_batch, entry in enumerate(kwargs["handle_batch_func"](p_batch)):
+        yield ind_in_batch, _iter_entry_content(entry=entry, entry_info={"ind": ind_in_batch, "param": c}, **kwargs)
+
+
+def _infer_batch(batch, schema, return_mode, cols=None, **kwargs):
     assert (isinstance(batch, list))
 
     if len(batch) == 0:
@@ -75,16 +64,41 @@ def _infer_batch(batch, schema, cols=None, **kwargs):
         cols = list(first_item.keys()) if cols is None else cols
 
     for c in cols:
-        _update_batch_content(c=c, batch=batch, schema=schema, **kwargs)
 
-    return batch
+        # 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_batch_responses(c=c, p_column=schema.r2p[c], batch_content_it=iter(batch), **kwargs)
+            for ind_in_batch, chunk_it in content_it:
+
+                chunks = []
+                for chunk in chunk_it:
+                    chunks.append(chunk)
+
+                    if return_mode == "chunk":
+                        yield [ind_in_batch, c, chunk]
+
+                batch[ind_in_batch][c] = "".join(chunks)
+
+    if return_mode == "record":
+        for record in batch:
+            yield record
+
+    if return_mode == "batch":
+        yield batch
 
 
-def iter_content(input_dicts_it, llm, schema, batch_size=1, return_batch=True, limit_prompt=None, **kwargs):
+def iter_content(input_dicts_it, llm, schema, batch_size=1, limit_prompt=None, return_mode="batch", **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 (return_mode in ["batch", "chunk"])
     assert (isinstance(llm, BaseLM))
 
     # Quick initialization of the schema.
@@ -94,17 +108,18 @@ def iter_content(input_dicts_it, llm, schema, batch_size=1, return_batch=True, l
         schema = SchemaService(json_data=schema)
 
     prompts_it = map(
-        lambda data: DictionaryService.custom_update(src_dict=data, other_dict=schema.cot_args),
+        lambda data: DictionaryService.custom_update(src_dict=dict(data), other_dict=schema.cot_args),
         input_dicts_it
     )
 
     content_it = (_infer_batch(batch=batch,
                                handle_batch_func=lambda batch: INFER_MODES["batch"](llm, batch, limit_prompt),
+                               return_mode=return_mode,
                                schema=schema,
                                **kwargs)
                   for batch in BatchIterator(prompts_it, batch_size=batch_size))
 
-    yield from content_it if return_batch else chain.from_iterable(content_it)
+    yield from chain.from_iterable(content_it)
 
 
 def init_llm(adapter, **model_kwargs):

bulk_chain/core/llm_base.py

@@ -1,8 +1,6 @@
 import logging
 import time
 
-from bulk_chain.core.utils import format_model_name
-
 
 class BaseLM(object):
 
@@ -49,4 +47,4 @@ class BaseLM(object):
         raise NotImplemented()
 
     def name(self):
-        return format_model_name(self.__name)
+        return self.__name.replace("/", "_")

bulk_chain/core/service_batch.py

@@ -1,22 +1,3 @@
-class BatchService(object):
-
-    @staticmethod
-    def handle_param_as_batch(batch, src_param, tgt_param, handle_batch_func, handle_entry_func):
-        assert (isinstance(batch, list))
-        assert (isinstance(src_param, str))
-        assert (callable(handle_batch_func))
-
-        _batch = [item[src_param] for item in batch]
-
-        # Do handling for the batch.
-        _handled_batch = handle_batch_func(_batch)
-        assert (isinstance(_handled_batch, list))
-
-        # Apply changes.
-        for i, item in enumerate(batch):
-            item[tgt_param] = handle_entry_func(entry=_handled_batch[i], info={"ind": i, "param": tgt_param})
-
-
 class BatchIterator:
 
     def __init__(self, data_iter, batch_size, end_value=None, filter_func=None):

bulk_chain/core/utils.py

@@ -48,28 +48,6 @@ def iter_params(text):
         beg = pe+1
 
 
-def format_model_name(name):
-    return name.replace("/", "_")
-
-
-def parse_filepath(filepath, default_filepath=None, default_ext=None):
-    """ This is an auxiliary function for handling sources and targets from cmd string.
-    """
-    if filepath is None:
-        return default_filepath, default_ext, None
-    info = filepath.split(":")
-    filepath = info[0]
-    meta = info[1] if len(info) > 1 else None
-    ext = filepath.split('.')[-1] if default_ext is None else default_ext
-    return filepath, ext, meta
-
-
-def handle_table_name(name):
-    return name.\
-        replace('-', '_').\
-        replace('.', "_")
-
-
 def auto_import(name, is_class=False):
     """ Import from the external python packages.
     """

{bulk_chain-0.25.3.dist-info → bulk_chain-1.0.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bulk_chain
-Version: 0.25.3
+Version: 1.0.0
 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
@@ -16,9 +16,8 @@ Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: tqdm
-Requires-Dist: source-iter ==0.24.3
 
-# bulk-chain 0.25.3
+# bulk-chain 1.0.0
 ![](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)
@@ -31,7 +30,7 @@ Requires-Dist: source-iter ==0.24.3
 <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/blob/master/README.md#demo-mode">👉<b>demo</b>👈</a>
+  <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)**.
@@ -39,11 +38,7 @@ A no-strings-attached **framework**  for your LLM that allows applying Chain-of-
 ### 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** served in `CSV`/`JSONL`.
-
-### Extra Features
-* ✅ **Progress caching [for remote LLMs]**: withstanding exception during LLM calls by using `sqlite3` engine for caching LLM answers;
-
+* ✅ **Provides iterator over infinite amount of input contexts**
 
 # Installation
 
@@ -88,51 +83,8 @@ Preliminary steps:
 1. Define your [schema](#chain-of-thought-schema) ([Example for Sentiment Analysis](/ext/schema/thor_cot_schema.json)))
 2. Wrap or pick **LLM model** from the [<b>Third-party providers hosting</b>↗️](https://github.com/nicolay-r/nlp-thirdgate?tab=readme-ov-file#llm).
 
-## Shell
-
-### Demo Mode
-
-**demo mode** to interact with LLM via command line with LLM output streaming support. 
-The video below illustrates an example of application for sentiment analysis on author opinion extraction towards mentioned object in text.
-
-Quck start with launching demo:
-1. ⬇️ Download [replicate](https://replicate.com/) provider for `bulk-chain`:
-2. 📜 Setup your reasoning `thor_cot_schema.json` according to the [following example ↗️](test/schema/thor_cot_schema.json)
-3. 🚀 Launch `demo.py` as follows:
-```bash
-python3 -m bulk_chain.demo \
-    --schema "test/schema/thor_cot_schema.json" \
-    --adapter "dynamic:replicate_104.py:Replicate" \
-    %%m \
-    --model_name "meta/meta-llama-3-70b-instruct" \
-    --api_token "<REPLICATE-API-TOKEN>" \
-    --stream
-```
-
-📺 This video showcase application of the [↗️ Sentiment Analysis Schema](https://github.com/nicolay-r/bulk-chain/blob/master/test/schema/thor_cot_schema.json) towards [LLaMA-3-70B-Instruct](https://replicate.com/meta/meta-llama-3-70b-instruct) hosted by Replicate for reasoning over submitted texts
-![sa-bulk-chain-cot-final](https://github.com/user-attachments/assets/0cc8fdcb-6ddb-44a3-8f05-d76250ae6423)
 
 
-### Inference Mode
-
-> **NOTE:** You have to install `source-iter` and `tqdm` packages that actual [dependencies](dependencies.txt) of this project
-
-1. ⬇️ Download [replicate](https://replicate.com/) provider for `bulk-chain`:
-```bash
-wget https://raw.githubusercontent.com/nicolay-r/nlp-thirdgate/refs/heads/master/llm/replicate_104.py
-```
-2. 📜 Setup your reasoning `schema.json` according to the [following example ↗️](test/schema/default.json)
-3. 🚀 Launch inference using `DeepSeek-R1`:
-```bash
-python3 -m bulk_chain.infer \
-    --src "<PATH-TO-YOUR-CSV-or-JSONL>" \
-    --schema "test/schema/default.json" \
-    --adapter "replicate_104.py:Replicate" \
-    %%m \
-    --model_name "deepseek-ai/deepseek-r1" \
-    --api_token "<REPLICATE-API-TOKEN>"
-```
-
 ## API
 
 Please take a look at the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)

bulk_chain-1.0.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+bulk_chain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bulk_chain/api.py,sha256=d_c10Je8wUSnCdQjyWCHVx4FGW6M2_pBMMqKsI_YJaY,5119
+bulk_chain/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bulk_chain/core/llm_base.py,sha256=DZ9l4HpCs9uKTZp68miw_XCqmRAJBqQPuYSK889CeUk,1785
+bulk_chain/core/service_batch.py,sha256=LMxrZeQXV_AJAoCaMCHVx8TvjcmCaKUQhNE8K4D8pCo,1031
+bulk_chain/core/service_data.py,sha256=OWWHHnr_plwxYTxLuvMrhEc1PbSx-XC3rbFzV0hy3vk,1107
+bulk_chain/core/service_dict.py,sha256=lAghLU-3V3xYGv5BTA327Qcw8UJYmgQRMFdggzlrUgo,383
+bulk_chain/core/service_json.py,sha256=6o1xM_8c9QEjH9Q3qEmJylU9nahfRXhUd5sFF2dGJwo,182
+bulk_chain/core/service_schema.py,sha256=KIP4n0Tz2h1i7SIMGhgAhoiCgUFXOT1rzMt38yACS2U,1154
+bulk_chain/core/utils.py,sha256=Dx9Gy-jPpk-w_8WUekN0Ij4RBIWVAPg74vA3N0JgGqc,2471
+bulk_chain-1.0.0.dist-info/LICENSE,sha256=VF9SjNpwwSSFEY_eP_8A1ocDCrbwfjI1pZexXdCkOwo,1076
+bulk_chain-1.0.0.dist-info/METADATA,sha256=TR86CmhcHJ3Sep8TlHZ0Ede_PnH8G5iMILUvVvSskJY,3810
+bulk_chain-1.0.0.dist-info/WHEEL,sha256=pL8R0wFFS65tNSRnaOVrsw9EOkOqxLrlUPenUYnJKNo,91
+bulk_chain-1.0.0.dist-info/top_level.txt,sha256=Hxq_wyH-GDXKBaA63UfBIiMJO2eCHJG5EOrXDphpeB4,11
+bulk_chain-1.0.0.dist-info/RECORD,,

bulk_chain/core/provider_sqlite.py

@@ -1,127 +0,0 @@
-import sqlite3
-
-
-class SQLite3Service(object):
-
-    @staticmethod
-    def __create_table(table_name, columns, id_column_name,
-                       id_column_type, cur, sqlite3_column_types=None):
-
-        # Setting up default column types.
-        if sqlite3_column_types is None:
-            types_count = len(columns) if id_column_name in columns else len(columns) - 1
-            sqlite3_column_types = ["TEXT"] * types_count
-
-        # Provide the ID column.
-        sqlite3_column_types = [id_column_type] + sqlite3_column_types
-
-        # Compose the whole columns list.
-        content = ", ".join([f"[{item[0]}] {item[1]}" for item in zip(columns, sqlite3_column_types)])
-        cur.execute(f"CREATE TABLE IF NOT EXISTS {table_name}({content})")
-        cur.execute(f"CREATE INDEX IF NOT EXISTS [{id_column_name}] ON {table_name}([{id_column_name}])")
-
-    @staticmethod
-    def __it_row_lists(cursor):
-        for row in cursor:
-            yield row
-
-    @staticmethod
-    def create_table_if_not_exist(**kwargs):
-        return SQLite3Service.__create_table(**kwargs)
-
-    @staticmethod
-    def entry_exist(table_name, target, id_column_name, id_value, **connect_kwargs) -> bool:
-        with sqlite3.connect(target, **connect_kwargs) as con:
-            cursor = con.cursor()
-
-            # Check table existance.
-            query = "SELECT name FROM sqlite_master WHERE type='table' AND name=?"
-            cursor.execute(query, (table_name,))
-            if cursor.fetchone() is None:
-                return False
-
-            # Check element.
-            r = cursor.execute(f"SELECT EXISTS(SELECT 1 FROM {table_name} WHERE [{id_column_name}]='{id_value}');")
-            ans = r.fetchone()[0]
-            return ans == 1
-
-    @staticmethod
-    def write(data_it, target, table_name, columns=None, id_column_name="id", data2col_func=None,
-              id_column_type="INTEGER", sqlite3_column_types=None, it_type='dict',
-              create_table_if_not_exist=True, skip_existed=True, **connect_kwargs):
-
-        need_set_column_id = True
-        need_initialize_columns = columns is None
-
-        # Setup default columns.
-        columns = [] if columns is None else columns
-
-        with sqlite3.connect(target, **connect_kwargs) as con:
-            cur = con.cursor()
-
-            for content in data_it:
-
-                if it_type == 'dict':
-                    # Extracting columns from data.
-                    data = content
-                    uid = data[id_column_name]
-                    row_columns = list(data.keys())
-                    row_params_func = lambda: [data2col_func(c, data) if data2col_func is not None else data[c]
-                                               for c in row_columns]
-                    # Append columns if needed.
-                    if need_initialize_columns:
-                        columns = list(row_columns)
-                elif it_type is None:
-                    # Setup row columns.
-                    uid, data = content
-                    row_columns = columns
-                    row_params_func = lambda: [uid] + data
-                else:
-                    raise Exception(f"it_type {it_type} does not supported!")
-
-                if need_set_column_id:
-                    # Register ID column.
-                    if id_column_name not in columns:
-                        columns.append(id_column_name)
-                    # Place ID column first.
-                    columns.insert(0, columns.pop(columns.index(id_column_name)))
-                    need_set_column_id = False
-
-                if create_table_if_not_exist:
-                    SQLite3Service.__create_table(
-                        columns=columns, table_name=table_name, cur=cur,
-                        id_column_name=id_column_name, id_column_type=id_column_type,
-                        sqlite3_column_types=sqlite3_column_types)
-
-                # Check that each rows satisfies criteria of the first row.
-                [Exception(f"{column} is expected to be in row!") for column in row_columns if column not in columns]
-
-                if skip_existed:
-                    r = cur.execute(f"SELECT EXISTS(SELECT 1 FROM {table_name} WHERE [{id_column_name}]='{uid}');")
-                    ans = r.fetchone()[0]
-
-                    if ans == 1:
-                        continue
-
-                params = ", ".join(tuple(['?'] * (len(columns))))
-                row_columns_str = ", ".join([f"[{col}]" for col in row_columns])
-                content_list = row_params_func()
-                cur.execute(f"INSERT INTO {table_name}({row_columns_str}) VALUES ({params})", content_list)
-                con.commit()
-
-            cur.close()
-
-    @staticmethod
-    def read(src, table="content", **connect_kwargs):
-        with sqlite3.connect(src, **connect_kwargs) as conn:
-            cursor = conn.cursor()
-            cursor.execute(f"SELECT * FROM {table}")
-            for record_list in SQLite3Service.__it_row_lists(cursor):
-                yield record_list
-
-    @staticmethod
-    def read_columns(target, table="content", **connect_kwargs):
-        with sqlite3.connect(target, **connect_kwargs) as conn:
-            cursor = conn.cursor()
-            cursor.execute(f"PRAGMA table_info({table})")
-            return [row[1] for row in cursor.fetchall()]

bulk_chain/core/service_args.py

@@ -1,72 +0,0 @@
-class CmdArgsService:
-
-    @staticmethod
-    def autocast(v):
-        for t in [int, float, str]:
-            try:
-                return t(v)
-            except:
-                pass
-
-    @staticmethod
-    def iter_arguments(lst):
-
-        def __release():
-
-            # We use the True value by default to treat the related parameter as flag.
-            if len(buf) == 0:
-                buf.append(True)
-
-            return key, buf if len(buf) > 1 else buf[0]
-
-        key = None
-        buf = []
-        for a in lst:
-            if a.startswith('--'):
-                # release
-                if key is not None:
-                    yield __release()
-                # set new key and empty buf
-                key = a[2:]
-                buf = []
-            else:
-                # append argument into buffer.
-                buf.append(a)
-
-        # Sharing the remaining params.
-        if key is not None:
-            yield __release()
-
-    @staticmethod
-    def __find_suffix_ind(lst, idx_from, end_prefix):
-        for i in range(idx_from, len(lst)):
-            if lst[i].startswith(end_prefix):
-                return i
-        return len(lst)
-
-    @staticmethod
-    def extract_native_args(lst, end_prefix):
-        return lst[:CmdArgsService.__find_suffix_ind(lst, idx_from=0, end_prefix=end_prefix)]
-
-    @staticmethod
-    def find_grouped_args(lst, starts_with, end_prefix):
-        """Slices a list in two, cutting on index matching "sep"
-        """
-
-        # Checking the presence of starts_with.
-        # We have to return empty content in the case of absence starts_with in the lst.
-        if starts_with not in lst:
-            return []
-
-        # Assigning start index.
-        idx_from = lst.index(starts_with) + 1
-
-        # Assigning end index.
-        idx_to = CmdArgsService.__find_suffix_ind(lst, idx_from=idx_from, end_prefix=end_prefix)
-
-        return lst[idx_from:idx_to]
-
-    @staticmethod
-    def args_to_dict(args):
-        return {k: CmdArgsService.autocast(v) if not isinstance(v, list) else v
-                for k, v in CmdArgsService.iter_arguments(args)} if args is not None else {}

bulk_chain/core/service_llm.py

@@ -1,68 +0,0 @@
-from bulk_chain.api import iter_content
-from bulk_chain.core.llm_base import BaseLM
-from bulk_chain.core.utils_logger import StreamedLogger
-
-
-def pad_str(text, pad):
-    return text.rjust(len(text) + pad, ' ')
-
-
-def nice_output(text, remove_new_line=False):
-    short_text = text.replace("\n", "") if remove_new_line else text
-    return short_text
-
-
-def chat_with_lm(lm, preset_dict=None, schema=None, model_name=None, pad=0):
-    assert (isinstance(lm, BaseLM))
-    assert (isinstance(model_name, str) or model_name is None)
-
-    preset_dict = {} if preset_dict is None else preset_dict
-
-    streamed_logger = StreamedLogger(__name__)
-    do_exit = False
-    model_name = model_name if model_name is not None else "agent"
-
-    while not do_exit:
-
-        # Launching the CoT engine loop.
-        data_dict = {} | preset_dict
-
-        def callback_str_func(entry, info):
-            streamed_logger.info(pad_str(f"{model_name} ({info['param']})->\n", pad=pad))
-            streamed_logger.info(nice_output(entry, remove_new_line=False))
-            streamed_logger.info("\n\n")
-
-        def handle_missed_value(col_name):
-            user_input = input(f"Enter your prompt for `{col_name}`"
-                               f"(or 'exit' to quit): ")
-
-            if user_input.lower() == 'exit':
-                exit(0)
-
-            return user_input
-
-        def callback_stream_func(entry, info):
-            if entry is None and info["action"] == "start":
-                streamed_logger.info(pad_str(f"{model_name} ({info['param']})->\n", pad=pad))
-                return
-            if entry is None and info["action"] == "end":
-                streamed_logger.info("\n\n")
-                return
-
-            streamed_logger.info(entry)
-
-        content_it = iter_content(
-            input_dicts_it=[data_dict],
-            llm=lm,
-            schema=schema,
-            batch_size=1,
-            return_batch=True,
-            handle_missed_value_func=handle_missed_value,
-            callback_str_func=callback_str_func,
-            callback_stream_func=callback_stream_func,
-        )
-
-        for _ in content_it:
-            user_input = input(f"Enter to continue (or 'exit' to quit) ...\n")
-            if user_input.lower() == 'exit':
-                do_exit = True

bulk_chain/core/utils_logger.py

@@ -1,41 +0,0 @@
-import logging
-
-
-def StreamedLogger(name: str) -> logging.Logger:
-    """ https://medium.com/@r.das699/optimizing-logging-practices-for-streaming-data-in-python-521798e1ed82
-    """
-    root_handlers = logging.getLogger().handlers
-    current_logger = logging.getLogger(name)
-    if not root_handlers:
-        new_handler = logging.StreamHandler()
-        new_handler.terminator = ""
-        new_handler.setFormatter(logging.Formatter("%(message)s"))
-        current_logger.addHandler(new_handler)
-        current_logger.propagate = False
-        current_logger.setLevel(logging.INFO)
-        return current_logger
-
-    for handler in current_logger.handlers[:]:
-        current_logger.removeHandler(handler)
-
-    for handler_r in root_handlers:
-        if type(handler_r) is logging.StreamHandler:
-            new_handler = logging.StreamHandler()
-            new_handler.terminator = ""
-            new_handler.setFormatter(logging.Formatter("%(message)s"))
-            current_logger.addHandler(new_handler)
-        elif type(handler_r) is logging.FileHandler:
-            new_handler = logging.FileHandler(
-                handler_r.baseFilename,
-                handler_r.mode,
-                handler_r.encoding,
-                handler_r.delay,
-                handler_r.errors,
-            )
-            new_handler.terminator = ""  # This will stop the printing in new line
-            new_handler.setFormatter(logging.Formatter("%(message)s"))
-            current_logger.addHandler(new_handler)
-        else:
-            continue
-    current_logger.propagate = False  # Don't propagate to root logger
-    return current_logger

bulk_chain/demo.py

@@ -1,84 +0,0 @@
-import json
-
-import argparse
-import logging
-import sys
-
-from source_iter.service_jsonl import JsonlService
-
-from bulk_chain.api import init_llm
-from bulk_chain.core.service_args import CmdArgsService
-from bulk_chain.core.service_json import JsonService
-from bulk_chain.core.service_llm import chat_with_lm
-from bulk_chain.core.service_schema import SchemaService
-from bulk_chain.core.utils import parse_filepath
-
-logger = logging.getLogger(__name__)
-logging.basicConfig(level=logging.INFO)
-
-
-def iter_from_json(filepath):
-    with open(filepath, "r") as f:
-        content = json.load(f)
-        for key, value in content.items():
-            yield key, value
-
-
-def iter_from_text_file(filepath):
-    with open(filepath, "r") as f:
-        yield filepath.split('.')[0], f.read()
-
-
-if __name__ == '__main__':
-
-    parser = argparse.ArgumentParser(description="LLM demo usage based on CoT schema")
-    parser.add_argument('--adapter', dest='adapter', type=str, default=None)
-    parser.add_argument('--attempts', dest='attempts', type=int, default=None)
-    parser.add_argument('--src', dest='src', type=str, nargs="*", default=None)
-    parser.add_argument('--schema', dest='schema', type=str, default=None,
-                        help="Path to the JSON file that describes schema")
-    parser.add_argument('--limit-prompt', dest="limit_prompt", type=int, default=None,
-                        help="Optional trimming prompt by the specified amount of characters.")
-
-    # Extract native arguments.
-    native_args = CmdArgsService.extract_native_args(sys.argv, end_prefix="%%")
-    args = parser.parse_args(args=native_args[1:])
-
-    # Extract model-related arguments and Initialize Large Language Model.
-    model_args = CmdArgsService.find_grouped_args(lst=sys.argv, starts_with="%%m", end_prefix="%%")
-    model_args_dict = CmdArgsService.args_to_dict(model_args) | {"attempts": args.attempts}
-    llm, llm_model_name = init_llm(adapter=args.adapter, **model_args_dict)
-
-    # Setup schema.
-    schema = SchemaService(json_data=JsonService.read(args.schema))
-    schema_name = schema.src.get("name", None)
-    if schema is not None:
-        logger.info(f"Using schema: {schema_name}")
-
-    output_providers = {
-        "jsonl": lambda filepath, data_it, header:
-            JsonlService.write(target=filepath,
-                               data_it=map(lambda item: {key: item[i] for i, key in enumerate(header)}, data_it))
-    }
-
-    input_file_handlers = {
-        "json": lambda filepath: iter_from_json(filepath),
-        "txt": lambda filepath: iter_from_text_file(filepath)
-    }
-
-    # Input extension type defines the provider.
-    if args.src is None:
-        args.src = []
-    if isinstance(args.src, str):
-        args.src = [args.src]
-    sources = [parse_filepath(s) for s in args.src]
-
-    preset_dict = {}
-    for fp, ext, _ in sources:
-        for key, value in input_file_handlers[ext](fp):
-            if key in preset_dict:
-                raise Exception(f"While at handling {fp}: Key {key} is already registered!")
-            preset_dict[key] = value
-
-    # Launch Demo.
-    chat_with_lm(llm, preset_dict=preset_dict, schema=schema, model_name=llm_model_name)

bulk_chain/infer.py

@@ -1,193 +0,0 @@
-from itertools import chain
-from os.path import join, basename
-
-import argparse
-import logging
-import sys
-
-from source_iter.service_csv import CsvService
-from source_iter.service_jsonl import JsonlService
-from tqdm import tqdm
-
-from bulk_chain.api import INFER_MODES, _infer_batch, CWD, init_llm
-from bulk_chain.core.llm_base import BaseLM
-from bulk_chain.core.provider_sqlite import SQLite3Service
-from bulk_chain.core.service_args import CmdArgsService
-from bulk_chain.core.service_batch import BatchIterator
-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 handle_table_name, optional_limit_iter, parse_filepath
-
-logger = logging.getLogger(__name__)
-logging.basicConfig(level=logging.INFO)
-
-WRITER_PROVIDERS = {
-    "sqlite": lambda filepath, table_name, data_it, **kwargs: SQLite3Service.write(
-        data_it=data_it, target=filepath, table_name=table_name, skip_existed=True, **kwargs)
-}
-
-READER_PROVIDERS = {
-    "sqlite": lambda filepath, table_name: SQLite3Service.read(filepath, table=table_name)
-}
-
-
-def infer_batch(batch, columns=None, **kwargs):
-    assert (len(batch) > 0)
-    # TODO. Support proper selection of columns.
-    cols = batch[0].keys() if columns is None else columns
-    return _infer_batch(batch=batch, cols=cols, **kwargs)
-
-
-def raise_(ex):
-    raise ex
-
-
-def iter_content_cached(input_dicts_it, llm, schema, cache_target, batch_size, id_column_name, limit_prompt=None,
-                        **cache_kwargs):
-    assert (isinstance(llm, BaseLM))
-    assert (isinstance(cache_target, str))
-
-    # Quick initialization of the schema.
-    if isinstance(schema, str):
-        schema = JsonService.read(schema)
-    if isinstance(schema, dict):
-        schema = SchemaService(json_data=schema)
-
-    # Parse target.
-    cache_filepath, _, cache_table = parse_filepath(filepath=cache_target)
-
-    # Iterator of the queries.
-    prompts_it = map(
-        lambda data: DictionaryService.custom_update(src_dict=data, other_dict=schema.cot_args),
-        input_dicts_it
-    )
-
-    prompts_batched_it = BatchIterator(
-        data_iter=iter(tqdm(prompts_it, desc="Iter Content")),
-        batch_size=batch_size,
-        filter_func=lambda data: not SQLite3Service.entry_exist(
-            id_column_name=id_column_name, table_name=cache_table, target=cache_filepath,
-            id_value=data[id_column_name], **cache_kwargs)
-    )
-
-    results_it = map(
-        lambda batch: infer_batch(
-            batch=batch, schema=schema,
-            handle_batch_func=lambda batch: INFER_MODES["batch"](llm, batch, limit_prompt),
-            handle_missed_value_func=lambda col_name: raise_(
-                Exception(f"Value for {col_name} is undefined. Filling undefined values is not supported")
-            )
-        ),
-        prompts_batched_it
-    )
-
-    # Perform caching first.
-    WRITER_PROVIDERS["sqlite"](
-        filepath=cache_filepath,
-        table_name=cache_table,
-        data_it=chain.from_iterable(results_it),
-        id_column_name=id_column_name,
-        **cache_kwargs)
-
-    # Then retrieve data.
-    return READER_PROVIDERS["sqlite"](filepath=cache_filepath, table_name=cache_table)
-
-
-if __name__ == '__main__':
-
-    parser = argparse.ArgumentParser(description="Infer Instruct LLM inference based on CoT schema")
-    parser.add_argument('--adapter', dest='adapter', type=str, default=None)
-    parser.add_argument('--id-col', dest='id_col', type=str, default="uid")
-    parser.add_argument('--src', dest='src', type=str, nargs="?", default=None)
-    parser.add_argument('--schema', dest='schema', type=str, default=None,
-                        help="Path to the JSON file that describes schema")
-    parser.add_argument('--to', dest='to', type=str, default=None, choices=["csv", "sqlite"])
-    parser.add_argument('--output', dest='output', type=str, default=None)
-    parser.add_argument('--limit', dest='limit', type=int, default=None,
-                        help="Limit amount of source texts for prompting.")
-    parser.add_argument('--batch-size', dest='batch_size', type=int, default=1)
-    parser.add_argument('--limit-prompt', dest="limit_prompt", type=int, default=None,
-                        help="Optional trimming prompt by the specified amount of characters.")
-
-    # Extract native arguments.
-    native_args = CmdArgsService.extract_native_args(sys.argv, end_prefix="%%")
-    args = parser.parse_args(args=native_args[1:])
-
-    # Extract csv-related arguments.
-    csv_args = CmdArgsService.find_grouped_args(lst=sys.argv, starts_with="%%csv", end_prefix="%%")
-    csv_args_dict = CmdArgsService.args_to_dict(csv_args)
-
-    # Extract model-related arguments and Initialize Large Language Model.
-    model_args = CmdArgsService.find_grouped_args(lst=sys.argv, starts_with="%%m", end_prefix="%%")
-    model_args_dict = CmdArgsService.args_to_dict(model_args) | {"attempts": 1}
-    llm, llm_model_name = init_llm(adapter=args.adapter, **model_args_dict)
-
-    # Setup schema.
-    schema = SchemaService(json_data=JsonService.read(args.schema))
-    schema_name = schema.src.get("name", None)
-    if schema is not None:
-        logger.info(f"Using schema: {schema_name}")
-
-    input_providers = {
-        "csv": lambda filepath: CsvService.read(src=filepath, row_id_key=args.id_col,
-                                                as_dict=True, skip_header=True,
-                                                delimiter=csv_args_dict.get("delimiter", ","),
-                                                escapechar=csv_args_dict.get("escapechar", None)),
-        "tsv": lambda filepath: CsvService.read(src=filepath, row_id_key=args.id_col,
-                                                as_dict=True, skip_header=True,
-                                                delimiter=csv_args_dict.get("delimiter", "\t"),
-                                                escapechar=csv_args_dict.get("escapechar", None)),
-        "jsonl": lambda filepath: JsonlService.read(src=filepath, row_id_key=args.id_col)
-    }
-
-    output_providers = {
-        "csv": lambda filepath, data_it, header: CsvService.write(target=filepath,
-                                                                  data_it=data_it, header=header,
-                                                                  delimiter=csv_args_dict.get("delimiter", ","),
-                                                                  escapechar=csv_args_dict.get("escapechar", None),
-                                                                  it_type=None),
-        "tsv": lambda filepath, data_it, header: CsvService.write(target=filepath,
-                                                                  data_it=data_it, header=header,
-                                                                  delimiter=csv_args_dict.get("delimiter", "\t"),
-                                                                  escapechar=csv_args_dict.get("escapechar", None),
-                                                                  it_type=None),
-        "jsonl": lambda filepath, data_it, header:
-        JsonlService.write(target=filepath,
-                           data_it=map(lambda item: {key: item[i] for i, key in enumerate(header)}, data_it))
-    }
-
-    # Setup output.
-    args.output = args.output.format(model=llm.name()) if args.output is not None else args.output
-    tgt_filepath, tgt_ext, tgt_meta = parse_filepath(args.output, default_ext=args.to)
-
-    # We do not support multiple files for other modes.
-    src_filepath, src_ext, src_meta = parse_filepath(args.src)
-
-    def default_output_file_template(ext):
-        # This is a default template for output files to be generated.
-        return "".join(["_".join([join(CWD, basename(src_filepath)), llm.name(), schema_name]), ext])
-
-    # Setup cache target as well as the related table.
-    cache_filepath = default_output_file_template(".sqlite") if tgt_filepath is None else tgt_filepath
-    cache_table = handle_table_name(tgt_meta if tgt_meta is not None else "contents")
-
-    # This is a content that we extracted via input provider.
-    it_data = input_providers[src_ext](src_filepath)
-
-    data_it = iter_content_cached(input_dicts_it=optional_limit_iter(it_data=it_data, limit=args.limit),
-                                  limit_prompt=args.limit_prompt,
-                                  schema=schema,
-                                  llm=llm,
-                                  batch_size=args.batch_size,
-                                  id_column_name=args.id_col,
-                                  cache_target=":".join([cache_filepath, cache_table]))
-
-    # Setup output target
-    tgt_ext = src_ext if tgt_ext is None else tgt_ext
-    output_target = default_output_file_template(f".{tgt_ext}") if tgt_filepath is None else tgt_filepath
-
-    # Perform output writing process.
-    output_providers[tgt_ext](filepath=output_target,
-                              data_it=data_it,
-                              header=SQLite3Service.read_columns(target=cache_filepath, table=cache_table))

bulk_chain-0.25.3.dist-info/RECORD

@@ -1,21 +0,0 @@
-bulk_chain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bulk_chain/api.py,sha256=8hXJb66bEOf1izgeBmjrB9LexSMJD7GquUhIm76lfmY,4351
-bulk_chain/demo.py,sha256=20r_-ioR3fu3eqHJnCRK4aQmBKTMgjFAHzZPJcXaEz8,3186
-bulk_chain/infer.py,sha256=Qb7ZV3_DXIh1jQoEjER_H2rO4ntREj_iIwGpEpAXJCE,9157
-bulk_chain/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bulk_chain/core/llm_base.py,sha256=fuWxfEOSRYvnoZMOcfnq1E2LIJKnrpsnxQ1z6SmY1nM,1839
-bulk_chain/core/provider_sqlite.py,sha256=sW4Yefp_zYuL8xVys8la5hG0Ng94jSqiXelPgGGB5B0,5327
-bulk_chain/core/service_args.py,sha256=lq4Veuh4QNu8mlCv8MT9S1rMxTn4FKalyp-3boYonVk,2136
-bulk_chain/core/service_batch.py,sha256=z1OND6x40QBvK2H_Wt8sRS8MadUvYTCHmbS_dCm9t7M,1678
-bulk_chain/core/service_data.py,sha256=OWWHHnr_plwxYTxLuvMrhEc1PbSx-XC3rbFzV0hy3vk,1107
-bulk_chain/core/service_dict.py,sha256=lAghLU-3V3xYGv5BTA327Qcw8UJYmgQRMFdggzlrUgo,383
-bulk_chain/core/service_json.py,sha256=6o1xM_8c9QEjH9Q3qEmJylU9nahfRXhUd5sFF2dGJwo,182
-bulk_chain/core/service_llm.py,sha256=3WYoBgaiqoRwsoKq6VUUNMasbLj5rMCjGkU3OQVxGf8,2278
-bulk_chain/core/service_schema.py,sha256=KIP4n0Tz2h1i7SIMGhgAhoiCgUFXOT1rzMt38yACS2U,1154
-bulk_chain/core/utils.py,sha256=1irk3RGLzJxeLZ-Tv0oOceOKG0ADtpEWniG2UGbYA_U,3089
-bulk_chain/core/utils_logger.py,sha256=BD-ADxaeeuHztaYjqtIY_cIzc5r2Svq9XwRtrgIEqyI,1636
-bulk_chain-0.25.3.dist-info/LICENSE,sha256=VF9SjNpwwSSFEY_eP_8A1ocDCrbwfjI1pZexXdCkOwo,1076
-bulk_chain-0.25.3.dist-info/METADATA,sha256=-yt6rNoJSGqHRe-6z-mdf51wtwpVLYvcr8Yv_1qkdxQ,6037
-bulk_chain-0.25.3.dist-info/WHEEL,sha256=pL8R0wFFS65tNSRnaOVrsw9EOkOqxLrlUPenUYnJKNo,91
-bulk_chain-0.25.3.dist-info/top_level.txt,sha256=Hxq_wyH-GDXKBaA63UfBIiMJO2eCHJG5EOrXDphpeB4,11
-bulk_chain-0.25.3.dist-info/RECORD,,