bulk-chain 0.24.1__py3-none-any.whl → 0.25.0__py3-none-any.whl

bulk_chain/api.py

@@ -0,0 +1,79 @@
+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_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
+
+
+INFER_MODES = {
+    "default": lambda llm, prompt, limit_prompt=None: llm.ask_core(
+        prompt[:limit_prompt] if limit_prompt is not None else prompt),
+    "batch": lambda llm, batch, limit_prompt=None: llm.ask_core(
+        DataService.limit_prompts(batch, limit=limit_prompt))
+}
+
+
+CWD = os.getcwd()
+
+
+def _update_batch_content(c, batch, schema, infer_func):
+    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)
+    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_func=lambda b: infer_func(b))
+
+
+def _infer_batch(batch, schema, infer_func, cols=None):
+    assert (isinstance(batch, list))
+    assert (callable(infer_func))
+
+    if len(batch) == 0:
+        return batch
+
+    if cols is None:
+        first_item = batch[0]
+        cols = first_item.keys() if cols is None else cols
+
+    for c in cols:
+        _update_batch_content(c=c, batch=batch, schema=schema, infer_func=infer_func)
+
+    return batch
+
+
+def iter_content(input_dicts_it, llm, schema, batch_size=1, return_batch=True, limit_prompt=None):
+    """ 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))
+
+    # Quick initialization of the schema.
+    if isinstance(schema, str):
+        schema = JsonService.read(schema)
+    if isinstance(schema, dict):
+        schema = SchemaService(json_data=schema)
+
+    prompts_it = map(
+        lambda data: DictionaryService.custom_update(src_dict=data, other_dict=schema.cot_args),
+        input_dicts_it
+    )
+
+    content_it = (_infer_batch(batch=batch,
+                               infer_func=lambda batch: INFER_MODES["batch"](llm, batch, limit_prompt),
+                               schema=schema)
+                  for batch in BatchIterator(prompts_it, batch_size=batch_size))
+
+    yield from content_it if return_batch else chain.from_iterable(content_it)

bulk_chain/core/llm_base.py

@@ -1,13 +1,52 @@
+import logging
+import time
+
 from bulk_chain.core.utils import format_model_name
 
 
 class BaseLM(object):
 
-    def __init__(self, name):
+    def __init__(self, name=None, attempts=None, delay_sec=1, enable_log=True,
+                 support_batching=False, **kwargs):
+
         self.__name = name
+        self.__attempts = 1 if attempts is None else attempts
+        self.__delay_sec = delay_sec
+        self.__support_batching = support_batching
+
+        if enable_log:
+            self.__logger = logging.getLogger(__name__)
+            logging.basicConfig(level=logging.INFO)
+
+    def ask_core(self, batch):
+
+        for i in range(self.__attempts):
+            try:
+                if self.__support_batching:
+                    # Launch in batch mode.
+                    content = self.ask(batch)
+                else:
+                    # Launch in non-batch mode.
+                    assert len(batch) == 1, "The LM does not support batching," \
+                                            f" while size of the content is {len(batch)} which is not equal 1. " \
+                                            f"Please enable batch-supporting or set required inference settings."
+                    content = batch[0]
+
+                response = self.ask(content)
+
+                # Wrapping into batch the response in the case of non-batching mode.
+                return response if self.__support_batching else [response]
+
+            except Exception as e:
+                if self.__logger is not None:
+                    self.__logger.info("Unable to infer the result. Try {} out of {}.".format(i, self.__attempts))
+                    self.__logger.info(e)
+                time.sleep(self.__delay_sec)
+
+        raise Exception("Can't infer")
 
-    def ask(self, prompt):
+    def ask(self, content):
         raise NotImplemented()
 
     def name(self):
-        return format_model_name(self.__name)
+        return format_model_name(self.__name)

bulk_chain/core/service_args.py

@@ -33,14 +33,33 @@ class CmdArgsService:
             yield __release()
 
     @staticmethod
-    def partition_list(lst, sep):
+    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"
         """
-        if sep in lst:
-            idx = lst.index(sep)
-            return (lst[:idx], lst[idx+1:])
-        else:
-            return (lst[:], None)
+
+        # 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):

bulk_chain/core/service_batch.py

@@ -0,0 +1,51 @@
+class BatchService(object):
+
+    @staticmethod
+    def handle_param_as_batch(batch, src_param, tgt_param, handle_func):
+        assert (isinstance(batch, list))
+        assert (isinstance(src_param, str))
+        assert (callable(handle_func))
+
+        _batch = [item[src_param] for item in batch]
+
+        # Do handling for the batch.
+        _handled_batch = handle_func(_batch)
+        assert (isinstance(_handled_batch, list))
+
+        # Apply changes.
+        for i, item in enumerate(batch):
+            item[tgt_param] = _handled_batch[i]
+
+
+class BatchIterator:
+
+    def __init__(self, data_iter, batch_size, end_value=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
+        self.__end_value = end_value
+
+    def __iter__(self):
+        return self
+
+    def __next__(self):
+        buffer = []
+        while True:
+            try:
+                data = next(self.__data_iter)
+            except StopIteration:
+                break
+            buffer.append(data)
+            if len(buffer) == self.__batch_size:
+                break
+
+        if len(buffer) > 0:
+            self.__index += 1
+            return buffer
+
+        if self.__end_value is None:
+            raise StopIteration
+        else:
+            return self.__end_value()

bulk_chain/core/service_data.py

@@ -20,3 +20,7 @@ class DataService(object):
         field_names = list(parse_fields_func(prompt))
         return DataService.compose_prompt_text(
             prompt=prompt, data_dict=data_dict, field_names=field_names)
+
+    @staticmethod
+    def limit_prompts(prompts_list, limit=None):
+        return [p[:limit] if limit is not None else p for p in prompts_list]

bulk_chain/core/service_dict.py

@@ -0,0 +1,10 @@
+class DictionaryService:
+
+    @staticmethod
+    def custom_update(src_dict, other_dict):
+        for k, v in other_dict.items():
+            if k in src_dict:
+                raise Exception(f"The key `{k}` is already defined in both dicts with values: "
+                                f"`{src_dict[k]}` (src) and `{v}` (other)")
+            src_dict[k] = v
+        return src_dict

bulk_chain/core/service_json.py

@@ -4,23 +4,7 @@ import json
 class JsonService(object):
 
     @staticmethod
-    def read_data(src):
+    def read(src):
         assert (isinstance(src, str))
         with open(src, "r") as f:
-            return json.load(f)
-
-    @staticmethod
-    def read_lines(src, row_id_key=None):
-        assert (isinstance(src, str))
-        with open(src, "r") as f:
-            for line_ind, line in enumerate(f.readlines()):
-                content = json.loads(line)
-                if row_id_key is not None:
-                    content[row_id_key] = line_ind
-                yield content
-
-    @staticmethod
-    def write_lines(target, data_it):
-        with open(target, "w") as f:
-            for item in data_it:
-                f.write(f"{json.dumps(item, ensure_ascii=False)}\n")
+            return json.load(f)

bulk_chain/core/service_llm.py

@@ -4,9 +4,6 @@ from bulk_chain.core.llm_base import BaseLM
 from bulk_chain.core.service_data import DataService
 from bulk_chain.core.utils import iter_params
 
-logger = logging.getLogger(__name__)
-logging.basicConfig(level=logging.INFO)
-
 
 def pad_str(text, pad):
     return text.rjust(len(text) + pad, ' ')
@@ -27,9 +24,12 @@ def nice_output(text, width, pad=4, remove_new_line=False):
 
 
 def chat_with_lm(lm, chain=None, model_name=None):
-    assert(isinstance(lm, BaseLM))
-    assert(isinstance(chain, list))
-    assert(isinstance(model_name, str) or model_name is None)
+    assert (isinstance(lm, BaseLM))
+    assert (isinstance(chain, list))
+    assert (isinstance(model_name, str) or model_name is None)
+
+    logger = logging.getLogger(__name__)
+    logging.basicConfig(level=logging.INFO)
 
     do_exit = False
     model_name = model_name if model_name is not None else "agent"
@@ -74,9 +74,9 @@ def chat_with_lm(lm, chain=None, model_name=None):
             logger.info(nice_output(actual_prompt, pad=pad*2, remove_new_line=True, width=80))
 
             # Response.
-            response = lm.ask(actual_prompt)
+            response_batch = lm.ask_core(batch=[actual_prompt])
             logger.info(pad_str(f"{model_name} (resp)->", pad=pad))
-            logger.info(nice_output(response, pad=pad*2, remove_new_line=False, width=80))
+            logger.info(nice_output(response_batch[0], pad=pad * 2, remove_new_line=False, width=80))
 
             # Collecting the answer for the next turn.
-            data_dict[prompt_args["out"]] = response
+            data_dict[prompt_args["out"]] = response_batch[0]

bulk_chain/core/service_schema.py

@@ -2,12 +2,11 @@ class SchemaService(object):
 
     def __init__(self, json_data):
         self.src = json_data
-        self.name = self.src["name"]
         self.r2p, self.p2r, self.cot_args, self.chain = SchemaService.__init_schema(prompts=json_data["schema"])
 
     @classmethod
     def from_prompt(cls, prompt):
-        prompt_schema = {"name": "prompt", "schema": [{"prompt": prompt, "out": "response", "in": "prompt"}]}
+        prompt_schema = {"schema": [{"prompt": prompt, "out": "response", "in": "prompt"}]}
         return cls(prompt_schema)
 
     @staticmethod

bulk_chain/infer.py

@@ -1,17 +1,18 @@
+from os.path import join, basename
+
 import argparse
 import logging
-import os
 import sys
 
+from source_iter.service_csv import CsvService
+from source_iter.service_jsonl import JsonlService
+from source_iter.service_sqlite import SQLite3Service
 from tqdm import tqdm
 
-from os.path import join, basename
-
+from bulk_chain.api import INFER_MODES, _infer_batch, CWD
 from bulk_chain.core.llm_base import BaseLM
-from bulk_chain.core.provider_sqlite import SQLiteProvider
 from bulk_chain.core.service_args import CmdArgsService
-from bulk_chain.core.service_csv import CsvService
-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_llm import chat_with_lm
 from bulk_chain.core.service_schema import SchemaService
@@ -21,7 +22,16 @@ logger = logging.getLogger(__name__)
 logging.basicConfig(level=logging.INFO)
 
 
-CWD = os.getcwd()
+WRITER_PROVIDERS = {
+    "sqlite": lambda filepath, table_name, data_it, infer_data_func, **kwargs: SQLite3Service.write(
+        data_it=data_it, target=filepath, table_name=table_name, data2col_func=infer_data_func,
+        skip_existed=True, **kwargs)
+}
+
+
+READER_PROVIDERS = {
+    "sqlite": lambda filepath, table_name: SQLite3Service.read(filepath, table=table_name)
+}
 
 
 def init_llm(**model_kwargs):
@@ -44,59 +54,44 @@ def init_llm(**model_kwargs):
     return llm, llm_model_name
 
 
-def init_schema(json_filepath):
-    return SchemaService(json_data=JsonService.read_data(json_filepath))
-
-
-def iter_content(input_dicts_iter, llm, schema, cache_target, cache_table, id_column_name):
-    """ 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`
-    """
+def iter_content_cached(input_dicts_it, llm, schema, cache_target, limit_prompt=None, **cache_kwargs):
     assert (isinstance(llm, BaseLM))
-    assert (isinstance(schema, SchemaService))
     assert (isinstance(cache_target, str))
-    assert (isinstance(cache_table, str))
 
-    infer_modes = {
-        "default": lambda prompt: llm.ask(prompt[:args.limit_prompt] if args.limit_prompt is not None else prompt)
-    }
+    # Quick initialization of the schema.
+    if isinstance(schema, str):
+        schema = JsonService.read(schema)
+    if isinstance(schema, dict):
+        schema = SchemaService(json_data=schema)
 
-    def optional_update_data_records(c, data):
-        assert (isinstance(c, str))
+    # Iterator of the queries.
+    prompts_it = map(
+        lambda data: DictionaryService.custom_update(src_dict=data, other_dict=schema.cot_args),
+        input_dicts_it
+    )
 
-        if c in schema.p2r:
-            data[c] = DataService.get_prompt_text(prompt=data[c]["prompt"], data_dict=data)
-        if c in schema.r2p:
-            p_column = schema.r2p[c]
-            # This instruction takes a lot of time in a non-batching mode.
-            data[c] = infer_modes["default"](data[p_column])
+    # Parse target.
+    cache_filepath, _, cache_table = parse_filepath(filepath=cache_target)
 
-        return data[c]
+    # Perform caching first.
+    WRITER_PROVIDERS["sqlite"](
+        filepath=cache_filepath, table_name=cache_table,
+        data_it=tqdm(prompts_it, desc="Iter content"),
+        infer_data_func=lambda c, prompt: _infer_batch(
+            batch=[prompt], cols=[c],
+            infer_func=lambda batch: INFER_MODES["default"](llm, batch, limit_prompt),
+            schema=schema)[0][c],
+        **cache_kwargs)
 
-    cache_providers = {
-        "sqlite": lambda filepath, table_name, data_it: SQLiteProvider.write_auto(
-            data_it=data_it, target=filepath,
-            data2col_func=optional_update_data_records,
-            table_name=handle_table_name(table_name if table_name is not None else "contents"),
-            id_column_name=id_column_name)
-    }
-
-    # We optionally wrap into limiter.
-    queries_it = optional_limit_iter(
-        it_data=map(lambda data: data.update(schema.cot_args) or data, input_dicts_iter),
-        limit=args.limit)
-
-    # Provide data caching.
-    cache_providers["sqlite"](cache_target, table_name=tgt_meta, data_it=tqdm(queries_it, desc="Iter content"))
-
-    return SQLiteProvider.iter_rows(cache_target, table=cache_table)
+    # 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('--attempts', dest='attempts', type=int, default=None)
     parser.add_argument('--id-col', dest='id_col', type=str, default="uid")
     parser.add_argument('--src', dest='src', type=str, default=None)
     parser.add_argument('--schema', dest='schema', type=str, default=None,
@@ -108,34 +103,52 @@ if __name__ == '__main__':
     parser.add_argument('--limit-prompt', dest="limit_prompt", type=int, default=None,
                         help="Optional trimming prompt by the specified amount of characters.")
 
-    native_args, model_args = CmdArgsService.partition_list(lst=sys.argv, sep="%%")
-
+    # Extract native arguments.
+    native_args = CmdArgsService.extract_native_args(sys.argv, end_prefix="%%")
     args = parser.parse_args(args=native_args[1:])
 
-    # Initialize Large Language Model.
-    model_args_dict = CmdArgsService.args_to_dict(model_args)
+    # 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": args.attempts}
     llm, llm_model_name = init_llm(**model_args_dict)
 
     # Setup schema.
-    schema = init_schema(args.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}")
+        logger.info(f"Using schema: {schema_name}")
 
     input_providers = {
         None: lambda _: chat_with_lm(llm, chain=schema.chain, model_name=llm_model_name),
-        "csv": lambda filepath: CsvService.read(target=filepath, row_id_key=args.id_col,
+        "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=model_args_dict.get("delimiter", "\t"),
-                                                escapechar=model_args_dict.get("escapechar", None)),
-        "jsonl": lambda filepath: JsonService.read_lines(src=filepath, row_id_key=args.id_col)
+                                                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_handled(target=filepath, data_it=data_it, header=header, data2col_func=lambda v: list(v)),
+        "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:
-        JsonService.write_lines(target=filepath,
-                                data_it=map(lambda item: {key:item[i] for i, key in enumerate(header)}, data_it))
+        JsonlService.write(target=filepath,
+                           data_it=map(lambda item: {key: item[i] for i, key in enumerate(header)}, data_it))
     }
 
     # Setup output.
@@ -150,24 +163,29 @@ if __name__ == '__main__':
         input_providers[src_ext](None)
         exit(0)
 
+    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_target = "".join(["_".join([join(CWD, basename(src_filepath)), llm.name(), schema.name]), f".sqlite"]) \
-        if tgt_filepath is None else tgt_filepath
+    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")
 
-    data_it = iter_content(input_dicts_iter=input_providers[src_ext](src_filepath),
-                           schema=schema,
-                           llm=llm,
-                           id_column_name=args.id_col,
-                           cache_target=cache_target,
-                           cache_table=cache_table)
+    # 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,
+                                  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 = "".join(["_".join([join(CWD, basename(src_filepath)), llm.name(), schema.name]), f".{tgt_ext}"]) \
-        if tgt_filepath is None else tgt_filepath
+    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=SQLiteProvider.get_columns(target=cache_target, table=cache_table))
+                              header=SQLite3Service.read_columns(target=cache_filepath, table=cache_table))

{bulk_chain-0.24.1.dist-info → bulk_chain-0.25.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bulk_chain
-Version: 0.24.1
+Version: 0.25.0
 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
@@ -15,32 +15,42 @@ Classifier: Topic :: Text Processing :: Linguistic
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: tqdm
 
-# bulk-chain 0.24.1
+# bulk-chain 0.25.0
 ![](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)
+[![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>
 
-A lightweight, no-strings-attached **[Chain-of-Thought](https://arxiv.org/abs/2201.11903) framework** for your LLM, ensuring reliable results for bulk input requests stored in `CSV` / `JSONL` / `sqlite`.
-It allows applying series of prompts formed into `schema` (See [related section](#chain-of-thought-schema))
+A lightweight, no-strings-attached **framework**  for your LLM that allows applying [Chain-of-Thought](https://arxiv.org/abs/2201.11903) prompt `schema` (See [related section](#chain-of-thought-schema)) towards a massive textual collections.
 
-### Features
+### Main Features
 * ✅ **No-strings**: you're free to LLM dependencies and flexible `venv` customization.
-* ✅ **Provides iterator over infinite amount of input contexts** served in `CSV`/`JSONL`.
-* ✅ **Progress caching**: withstanding exception during LLM calls by using `sqlite3` engine for caching LLM answers;
 * ✅ **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;
+
 
 # Installation
 
+From PyPI: 
+
 ```bash
 pip install 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, this project exploits `JSON` format.
@@ -63,35 +73,37 @@ Below, is an example on how to declare your own schema:
 }
 ```
 
-Another templates are available [here](/ext/schema/thor_cot_schema.json).
+Another templates are available [here](/ext/schema/).
 
 # Usage
 
-Just **three** simple steps:
+Preliminary steps:
 
-1. Define your [CoT Schema](#chain-of-thought-schema), or fetch it as shown below:
-```bash
-!wget https://raw.githubusercontent.com/nicolay-r/bulk-chain/refs/heads/master/ext/schema/default.json
-```
-2. Fetch or write your own **model** or pick the one [preset here](/ext/):
-```bash
-!wget https://raw.githubusercontent.com/nicolay-r/bulk-chain/refs/heads/master/ext/flan_t5.py
-```
+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 [list of presets](/ext/).
+
+## API
+
+Please take a look at the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+
+## Shell
+
+> **NOTE:** You have to install `source-iter` package
 
-3. Launch inference in (chat mode):
 ```bash
-!python -m bulk_chain.infer \
-    --schema "default.json" \
-    --adapter "dynamic:flan_t5.py:FlanT5" \
-    %% \
-    --device "cpu" \
+python3 -m bulk_chain.infer \
+    --src "<PATH-TO-YOUR-CSV-or-JSONL>" \
+    --schema "ext/schema/default.json" \
+    --adapter "dynamic:ext/replicate.py:Replicate" \
+    %%m \
+    --api_token "<REPLICATE-API-TOKEN>" \
     --temp 0.1
 ```
 
 # Embed your LLM
 
 All you have to do is to implement `BaseLM` class, that includes:
-* `__init__` -- for initialization;
+* `__init__` -- for setting up *batching mode support* and (optional) *model name*;
 * `ask(prompt)` -- infer your model with the given `prompt`.
 
 See examples with models [here](/ext).

bulk_chain-0.25.0.dist-info/RECORD

@@ -0,0 +1,18 @@
+bulk_chain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bulk_chain/api.py,sha256=08i2tgFa_CCA0obC_Yr3rURI6MkuXYKgmuZaLcs4NLk,2807
+bulk_chain/infer.py,sha256=oWtBf2itZeM3fD-_QAzABKUMbsl4BqvHmW21TUTr880,9110
+bulk_chain/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bulk_chain/core/llm_base.py,sha256=uX_uibm5y8STfMKNYL64EeF8UowfJGwCD_t-uftHoJE,1849
+bulk_chain/core/service_args.py,sha256=x-QHaKLD1d6qaJkD4lNwx7640ku9-6Uyr3mooB_6kLc,1981
+bulk_chain/core/service_batch.py,sha256=yQr6fbQd4ifQBGMhZMrQQeZpXtDchMKMGJi8XPG7thc,1430
+bulk_chain/core/service_data.py,sha256=ZjJDtd1jrQm9hRCXMqe4CT_qF2XDbWBE1lVibP7tAWo,942
+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=1xbFW5OQY2ckKwIDZjsgNtnxKDp2wDjKKwyNS_yMU2s,2776
+bulk_chain/core/service_schema.py,sha256=KIP4n0Tz2h1i7SIMGhgAhoiCgUFXOT1rzMt38yACS2U,1154
+bulk_chain/core/utils.py,sha256=UV6Cefaw7yZiYblsCr-s9LsbcI83xe7eESBvha9A2Og,2784
+bulk_chain-0.25.0.dist-info/LICENSE,sha256=VF9SjNpwwSSFEY_eP_8A1ocDCrbwfjI1pZexXdCkOwo,1076
+bulk_chain-0.25.0.dist-info/METADATA,sha256=-Ky6ZekXHUCBByhSTgDYgMpC64ew8lGmQ7-I9dKsv6U,3874
+bulk_chain-0.25.0.dist-info/WHEEL,sha256=pL8R0wFFS65tNSRnaOVrsw9EOkOqxLrlUPenUYnJKNo,91
+bulk_chain-0.25.0.dist-info/top_level.txt,sha256=Hxq_wyH-GDXKBaA63UfBIiMJO2eCHJG5EOrXDphpeB4,11
+bulk_chain-0.25.0.dist-info/RECORD,,

bulk_chain/core/provider_sqlite.py

@@ -1,78 +0,0 @@
-import sqlite3
-
-
-class SQLiteProvider(object):
-
-    @staticmethod
-    def __create_table(table_name, columns, id_column_name,
-                       id_column_type, sqlite3_column_types, cur):
-
-        # 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 write_auto(data_it, target, data2col_func, table_name, id_column_name="id",
-                   id_column_type="INTEGER"):
-        """ NOTE: data_it is an iterator of dictionaries.
-            This implementation automatically creates the table and
-        """
-        with sqlite3.connect(target) as con:
-            cur = con.cursor()
-
-            columns = None
-            for data in data_it:
-                assert(isinstance(data, dict))
-
-                # Extracting columns from data.
-                row_columns = list(data.keys())
-                assert(id_column_name in row_columns)
-
-                # Optionally create table.
-                if columns is None:
-
-                    # Setup list of columns.
-                    columns = row_columns
-                    # Place ID column first.
-                    columns.insert(0, columns.pop(columns.index(id_column_name)))
-
-                    SQLiteProvider.__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=["TEXT"] * len(columns))
-
-                # 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]
-
-                uid = data[id_column_name]
-                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])
-                cur.execute(f"INSERT INTO {table_name}({row_columns_str}) VALUES ({params})",
-                            [data2col_func(c, data) for c in row_columns])
-                con.commit()
-
-            cur.close()
-
-    @staticmethod
-    def iter_rows(target, table="content"):
-        with sqlite3.connect(target) as conn:
-            cursor = conn.cursor()
-            cursor.execute(f"SELECT * FROM {table}")
-            for row in cursor:
-                yield row
-                
-    @staticmethod
-    def get_columns(target, table="content"):
-        with sqlite3.connect(target) as conn:
-            cursor = conn.cursor()
-            cursor.execute(f"PRAGMA table_info({table})")
-            return [row[1] for row in cursor.fetchall()]

bulk_chain/core/service_csv.py

@@ -1,57 +0,0 @@
-import csv
-import logging
-
-logger = logging.getLogger(__name__)
-logging.basicConfig(level=logging.INFO)
-
-
-class CsvService:
-
-    @staticmethod
-    def write(target, lines_it):
-        f = open(target, "w")
-        logger.info(f"Saving: {target}")
-        w = csv.writer(f, delimiter="\t", quotechar='"', quoting=csv.QUOTE_MINIMAL)
-        for content in lines_it:
-            w.writerow(content)
-
-    @staticmethod
-    def write_handled(target, data_it, data2col_func, header):
-
-        def __it():
-            yield header
-            for data in data_it:
-                content = data2col_func(data)
-                assert(len(content) == len(header))
-                yield content
-
-        CsvService.write(target, lines_it=__it())
-
-    @staticmethod
-    def read(target, skip_header=False, cols=None, as_dict=False, row_id_key=None, **csv_kwargs):
-        assert (isinstance(row_id_key, str) or row_id_key is None)
-        assert (isinstance(cols, list) or cols is None)
-
-        header = None
-        with open(target, newline='\n') as f:
-            for row_id, row in enumerate(csv.reader(f, **csv_kwargs)):
-                if skip_header and row_id == 0:
-                    header = ([row_id_key] if row_id_key is not None else []) + row
-                    continue
-
-                # Determine the content we wish to return.
-                if cols is None:
-                    content = row
-                else:
-                    row_d = {header[col_ind]: value for col_ind, value in enumerate(row)}
-                    content = [row_d[col_name] for col_name in cols]
-
-                content = ([row_id-1] if row_id_key is not None else []) + content
-
-                # Optionally attach row_id to the content.
-                if as_dict:
-                    assert (header is not None)
-                    assert (len(content) == len(header))
-                    yield {k: v for k, v in zip(header, content)}
-                else:
-                    yield content

bulk_chain-0.24.1.dist-info/RECORD

@@ -1,17 +0,0 @@
-bulk_chain/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bulk_chain/infer.py,sha256=hD9GJEp6P9PZRBSUCIxK8DaDjsX-oiq8VCe0rAD2EPs,7366
-bulk_chain/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bulk_chain/core/llm_base.py,sha256=5js2RJLpNS5t-De-xTpZCbLMgbz3F_b9tU_CtXhy02I,259
-bulk_chain/core/provider_sqlite.py,sha256=rNUvBt3aGa6Uv4a9RItyMgBZPnFbBdNjnt0Gw81lM3I,3171
-bulk_chain/core/service_args.py,sha256=Qr3rHsAB8wnajB-DbU-GjiEpRZFP4D6s1lVTpLkPPX4,1294
-bulk_chain/core/service_csv.py,sha256=-m8tNN9aIqRfJa4sPUX8ZUDP4W0fgnnOR3_0PapepDY,1984
-bulk_chain/core/service_data.py,sha256=18gQwSCTEsI7XFukq8AE5lDJX_QQRpasaH69g6EddV0,797
-bulk_chain/core/service_json.py,sha256=alYqTQbBjAcCh7anSTOZs1CLJbiWrLPpzLcoADstD0Q,743
-bulk_chain/core/service_llm.py,sha256=tYgMphJkXunhxdrThdfI4eM8qQTCZfEM1kabbReVjuQ,2726
-bulk_chain/core/service_schema.py,sha256=JVhOv2YP5VEtiwOq_zgCzhS2uF_BOATAgg6fmKRf2NQ,1209
-bulk_chain/core/utils.py,sha256=UV6Cefaw7yZiYblsCr-s9LsbcI83xe7eESBvha9A2Og,2784
-bulk_chain-0.24.1.dist-info/LICENSE,sha256=VF9SjNpwwSSFEY_eP_8A1ocDCrbwfjI1pZexXdCkOwo,1076
-bulk_chain-0.24.1.dist-info/METADATA,sha256=g5_Sr1pfa8v5lRs0sd7Ldch-uLiV_KfdDXaTHSen-R4,3649
-bulk_chain-0.24.1.dist-info/WHEEL,sha256=pL8R0wFFS65tNSRnaOVrsw9EOkOqxLrlUPenUYnJKNo,91
-bulk_chain-0.24.1.dist-info/top_level.txt,sha256=Hxq_wyH-GDXKBaA63UfBIiMJO2eCHJG5EOrXDphpeB4,11
-bulk_chain-0.24.1.dist-info/RECORD,,