bulk-chain 0.25.1__tar.gz → 0.25.2__tar.gz

{bulk_chain-0.25.1 → bulk_chain-0.25.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bulk_chain
-Version: 0.25.1
+Version: 0.25.2
 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
@@ -18,7 +18,7 @@ License-File: LICENSE
 Requires-Dist: tqdm
 Requires-Dist: source-iter==0.24.3
 
-# bulk-chain 0.25.1
+# bulk-chain 0.25.2
 ![](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)
@@ -30,6 +30,8 @@ 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>
 </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)**.
@@ -86,11 +88,32 @@ 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).
 
-## API
+## Shell
 
-Please take a look at the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+### Demo Mode
 
-## Shell
+**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
 
@@ -110,17 +133,10 @@ python3 -m bulk_chain.infer \
     --api_token "<REPLICATE-API-TOKEN>"
 ```
 
-Or, you can launch **demo mode** to interact with LLM via command line: 
-> **NOTE:** Demo supports streaming!
-```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
-```
+## API
+
+Please take a look at the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+
 
 # Embed your LLM
 

{bulk_chain-0.25.1 → bulk_chain-0.25.2}/README.md

@@ -1,4 +1,4 @@
-# bulk-chain 0.25.1
+# bulk-chain 0.25.2
 ![](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)
@@ -10,6 +10,8 @@
 
 <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>
 </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)**.
@@ -66,11 +68,32 @@ 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).
 
-## API
+## Shell
 
-Please take a look at the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+### Demo Mode
 
-## Shell
+**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
 
@@ -90,17 +113,10 @@ python3 -m bulk_chain.infer \
     --api_token "<REPLICATE-API-TOKEN>"
 ```
 
-Or, you can launch **demo mode** to interact with LLM via command line: 
-> **NOTE:** Demo supports streaming!
-```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
-```
+## API
+
+Please take a look at the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+
 
 # Embed your LLM
 

{bulk_chain-0.25.1 → bulk_chain-0.25.2}/bulk_chain/core/llm_base.py

@@ -24,7 +24,7 @@ class BaseLM(object):
             try:
                 if self.__support_batching:
                     # Launch in batch mode.
-                    content = self.ask(batch)
+                    content = batch
                 else:
                     # Launch in non-batch mode.
                     assert len(batch) == 1, "The LM does not support batching," \

{bulk_chain-0.25.1 → bulk_chain-0.25.2}/bulk_chain/core/service_llm.py

@@ -8,21 +8,12 @@ def pad_str(text, pad):
     return text.rjust(len(text) + pad, ' ')
 
 
-def text_wrap(content, width, handle_line=lambda l: l):
-    lines = []
-    for text in content.split('\n'):
-        for i in range(0, len(text), width):
-            line = handle_line(text[i:i + width])
-            lines.append(line)
-    return '\n'.join(lines)
-
-
-def nice_output(text, width, pad=4, remove_new_line=False):
+def nice_output(text, remove_new_line=False):
     short_text = text.replace("\n", "") if remove_new_line else text
-    return text_wrap(content=short_text, width=width, handle_line=lambda line: pad_str(line, pad=pad))
+    return short_text
 
 
-def chat_with_lm(lm, preset_dict=None, chain=None, model_name=None, line_width=80, pad=0):
+def chat_with_lm(lm, preset_dict=None, chain=None, model_name=None, pad=0):
     assert (isinstance(lm, BaseLM))
     assert (isinstance(chain, list))
     assert (isinstance(model_name, str) or model_name is None)
@@ -81,7 +72,7 @@ def chat_with_lm(lm, preset_dict=None, chain=None, model_name=None, line_width=8
             # Returning meta information, passed to LLM.
             streamed_logger.info(pad_str(f"{model_name} (ask [{chain_ind+1}/{len(chain)}]) ->", pad=pad))
             streamed_logger.info("\n")
-            streamed_logger.info(nice_output(actual_prompt, pad=pad, remove_new_line=True, width=line_width))
+            streamed_logger.info(nice_output(actual_prompt, remove_new_line=True))
             streamed_logger.info("\n\n")
 
             # Response.
@@ -89,7 +80,7 @@ def chat_with_lm(lm, preset_dict=None, chain=None, model_name=None, line_width=8
             streamed_logger.info(pad_str(f"{model_name} (resp [{chain_ind+1}/{len(chain)}])->", pad=pad))
             streamed_logger.info("\n")
             if isinstance(response, str):
-                streamed_logger.info(nice_output(response, pad=pad, remove_new_line=False, width=line_width))
+                streamed_logger.info(nice_output(response, remove_new_line=False))
                 buffer = [response]
             else:
                 buffer = []

{bulk_chain-0.25.1 → bulk_chain-0.25.2}/bulk_chain/demo.py

@@ -81,5 +81,4 @@ if __name__ == '__main__':
             preset_dict[key] = value
 
     # Launch Demo.
-    chat_with_lm(llm, preset_dict=preset_dict, chain=schema.chain, model_name=llm_model_name,
-                 line_width=120)
+    chat_with_lm(llm, preset_dict=preset_dict, chain=schema.chain, model_name=llm_model_name)

{bulk_chain-0.25.1 → bulk_chain-0.25.2}/bulk_chain/infer.py

@@ -68,7 +68,6 @@ 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, nargs="?", default=None)
     parser.add_argument('--schema', dest='schema', type=str, default=None,

{bulk_chain-0.25.1 → bulk_chain-0.25.2}/bulk_chain.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bulk_chain
-Version: 0.25.1
+Version: 0.25.2
 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
@@ -18,7 +18,7 @@ License-File: LICENSE
 Requires-Dist: tqdm
 Requires-Dist: source-iter==0.24.3
 
-# bulk-chain 0.25.1
+# bulk-chain 0.25.2
 ![](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)
@@ -30,6 +30,8 @@ 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>
 </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)**.
@@ -86,11 +88,32 @@ 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).
 
-## API
+## Shell
 
-Please take a look at the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+### Demo Mode
 
-## Shell
+**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
 
@@ -110,17 +133,10 @@ python3 -m bulk_chain.infer \
     --api_token "<REPLICATE-API-TOKEN>"
 ```
 
-Or, you can launch **demo mode** to interact with LLM via command line: 
-> **NOTE:** Demo supports streaming!
-```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
-```
+## API
+
+Please take a look at the [**related Wiki page**](https://github.com/nicolay-r/bulk-chain/wiki)
+
 
 # Embed your LLM
 

{bulk_chain-0.25.1 → bulk_chain-0.25.2}/setup.py

@@ -15,7 +15,7 @@ def get_requirements(filenames):
 
 setup(
     name='bulk_chain',
-    version='0.25.1',
+    version='0.25.2',
     python_requires=">=3.6",
     description='A lightweight, no-strings-attached Chain-of-Thought framework for your LLM, '
                 'ensuring reliable results for bulk input requests.',