langroid 0.1.133__py3-none-any.whl → 0.1.134__py3-none-any.whl

langroid/agent/base.py

@@ -143,6 +143,9 @@ class Agent(ABC):
     def get_dialog(self) -> List[Tuple[str, str]]:
         return self.dialog
 
+    def clear_dialog(self) -> None:
+        self.dialog = []
+
     def _get_tool_list(
         self, message_class: Optional[Type[ToolMessage]] = None
     ) -> List[str]:

langroid/agent/task.py

@@ -100,6 +100,7 @@ class Task:
         if isinstance(agent, ChatAgent) and len(agent.message_history) == 0 or restart:
             agent = cast(ChatAgent, agent)
             agent.clear_history(0)
+            agent.clear_dialog()
             # possibly change the system and user messages
             if system_message:
                 # we always have at least 1 task_message

langroid/parsing/parser.py

@@ -1,6 +1,6 @@
 import logging
 from enum import Enum
-from typing import List
+from typing import Dict, List
 
 import tiktoken
 from pydantic import BaseSettings
@@ -57,22 +57,34 @@ class Parser:
 
         # The original metadata.id (if any) is ignored since it will be same for all
         # chunks and is useless. We want a distinct id for each chunk.
+        orig_ids = [c.metadata.id for c in chunks]
         ids = [Document.hash_id(str(c)) for c in chunks]
 
+        # group the ids by orig_id
+        orig_id_to_ids: Dict[str, List[str]] = {}
+        for orig_id, id in zip(orig_ids, ids):
+            if orig_id not in orig_id_to_ids:
+                orig_id_to_ids[orig_id] = []  # type: ignore
+            orig_id_to_ids[orig_id].append(id)  # type: ignore
+
+        # now each orig_id maps to a sequence of ids within a single doc
+
         k = self.config.n_neighbor_ids
-        n = len(ids)
-        window_ids = [ids[max(0, i - k) : min(n, i + k + 1)] for i in range(n)]
-        for i, c in enumerate(chunks):
-            if c.content.strip() == "":
-                continue
-            c.metadata.window_ids = window_ids[i]
-            c.metadata.id = ids[i]
-            c.metadata.is_chunk = True
+        for orig, ids in orig_id_to_ids.items():
+            n = len(ids)
+            window_ids = [ids[max(0, i - k) : min(n, i + k + 1)] for i in range(n)]
+            for i, c in enumerate(chunks):
+                if c.content.strip() == "":
+                    continue
+                c.metadata.window_ids = window_ids[i]
+                c.metadata.id = ids[i]
+                c.metadata.is_chunk = True
 
     def split_simple(self, docs: List[Document]) -> List[Document]:
         if len(self.config.separators) == 0:
             raise ValueError("Must have at least one separator")
         final_docs = []
+
         for d in docs:
             if d.content.strip() == "":
                 continue
@@ -240,6 +252,11 @@ class Parser:
     def split(self, docs: List[Document]) -> List[Document]:
         if len(docs) == 0:
             return []
+        # create ids in metadata of docs if absent:
+        # we need this to distinguish docs later in add_window_ids
+        for d in docs:
+            if d.metadata.id is None:
+                d.metadata.id = d.id()
         # some docs are already splits, so don't split them further!
         chunked_docs = [d for d in docs if d.metadata.is_chunk]
         big_docs = [d for d in docs if not d.metadata.is_chunk]

{langroid-0.1.133.dist-info → langroid-0.1.134.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.133
+Version: 0.1.134
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
@@ -100,7 +100,7 @@ Description-Content-Type: text/markdown
 [![Multi-Architecture DockerHub](https://github.com/langroid/langroid/actions/workflows/docker-publish.yml/badge.svg)](https://github.com/langroid/langroid/actions/workflows/docker-publish.yml)
 
 [![Static Badge](https://img.shields.io/badge/Documentation-blue?link=https%3A%2F%2Flangroid.github.io%2Flangroid%2F&link=https%3A%2F%2Flangroid.github.io%2Flangroid%2F)](https://langroid.github.io/langroid)
-[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/langroid_quick_examples.ipynb)
+[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/Langroid_quick_start.ipynb)
 [![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?style=flat&logo=discord&logoColor=white)](https://discord.gg/ZU36McDgDs)
 [![Substack](https://img.shields.io/badge/Substack-%23006f5c.svg?style=flat&logo=substack&logoColor=FF6719)](https://langroid.substack.com/p/langroid-harness-llms-with-multi-agent-programming)
 </div>
@@ -138,7 +138,7 @@ We welcome contributions -- See the [contributions](./CONTRIBUTING.md) document
 for ideas on what to contribute.
 
 
-Building LLM Applications? Prasad Chalasani is available for consulting
+Building LLM Applications? [Prasad Chalasani](https://www.linkedin.com/in/pchalasani/) is available for consulting
 (advisory/development): pchalasani at gmail dot com.
 
 Sponsorship is also accepted via [GitHub Sponsors](https://github.com/sponsors/langroid)
@@ -148,12 +148,12 @@ Sponsorship is also accepted via [GitHub Sponsors](https://github.com/sponsors/l
 # Quick glimpse of coding with Langroid
 This is just a teaser; there's much more, like function-calling/tools, 
 Multi-Agent Collaboration, Structured Information Extraction, DocChatAgent 
-(RAG), SQLChatAgent, etc. Scroll down or see docs for more.
-
-:fire: Just released! See this [Colab](https://colab.research.google.com/drive/190Tk7t4AdY1P9F_NlZ33-YEoGnHweQQ0) 
-for a walk-through of the new `OpenAIAssistant` class (with near-complete support for the new OpenAI Assistants API) 
-in a multi-agent setting.
+(RAG), SQLChatAgent, non-OpenAI local/remote LLMs, etc. Scroll down or see docs for more.
 
+:fire: Just released! Updated Langroid Quick-Start [Colab](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/Langroid_quick_start.ipynb)
+that builds up to a 2-agent chat example using the OpenAI ChatCompletion API. 
+See also this [version](https://colab.research.google.com/drive/190Tk7t4AdY1P9F_NlZ33-YEoGnHweQQ0) 
+that uses the OpenAI Assistants API instead.
 
 ```python
 from langroid.language_models import  OpenAIGPTConfig, OpenAIChatModel, OpenAIGPT
@@ -264,7 +264,7 @@ See [this test](tests/main/test_recipient_tool.py) for example usage.
   - **Example:** [Answer questions](examples/docqa/chat-search.py) using Google Search + vecdb-retrieval from URL contents. 
   - **0.1.39:** [`GoogleSearchTool`](langroid/agent/tools/google_search_tool.py) to enable Agents (their LLM) to do Google searches via function-calling/tools.
     See [this chat example](examples/basic/chat-search.py) for how easy it is to add this tool to an agent.
-  - **Colab notebook** to try the quick-start examples: [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/langroid_quick_examples.ipynb) 
+  - **Colab notebook** to try the quick-start examples: [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/Langroid_quick_start.ipynb) 
   - **0.1.37:** Added [`SQLChatAgent`](langroid/agent/special/sql_chat_agent.py) -- thanks to our latest contributor [Rithwik Babu](https://github.com/rithwikbabu)!
   - Multi-agent Example: [Autocorrect chat](examples/basic/autocorrect.py)
 - **July 2023:** 
@@ -515,7 +515,7 @@ for a detailed tutorial.
 
 Click to expand any of the code examples below.
 All of these can be run in a Colab notebook:
-[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/langroid_quick_examples.ipynb)
+[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langroid/langroid/blob/main/examples/Langroid_quick_start.ipynb)
 
 <details>
 <summary> <b> Direct interaction with OpenAI LLM </b> </summary>

{langroid-0.1.133.dist-info → langroid-0.1.134.dist-info}/RECORD

@@ -1,6 +1,6 @@
 langroid/__init__.py,sha256=-AWkFhhW0b0paHQ11SORyIVPnXv0nyT2X_0_xh3zLjw,408
 langroid/agent/__init__.py,sha256=ZqDw3Ktw7XGDl6mC8DN61F71V4ckf0rBoEOydH9l6C4,428
-langroid/agent/base.py,sha256=Q3xVpOuE85LjkLKvM32pBjTiViyJQSpadQ7-U08cRMo,31869
+langroid/agent/base.py,sha256=-VWT3gQWgH_uGjVILLPosa5WebzZihVY_JOi_bYYNEQ,31931
 langroid/agent/batch.py,sha256=Cg7Qv1yGi_M9rMl38_4-hjXPsoLlZrOSXDhbOFqUcKY,5593
 langroid/agent/chat_agent.py,sha256=if0wV75i8I2roNpeq-4PxSxH6bwJjhxVnm61SvNy_m0,35026
 langroid/agent/chat_document.py,sha256=dw0m_00qJgOhbzCkEsVBAiktM6BJ62mV8_piu5GruXM,7008
@@ -20,7 +20,7 @@ langroid/agent/special/sql/utils/populate_metadata.py,sha256=zRjw31a1ZXvpx9bcmbt
 langroid/agent/special/sql/utils/system_message.py,sha256=qKLHkvQWRQodTtPLPxr1GSLUYUFASZU8x-ybV67cB68,1885
 langroid/agent/special/sql/utils/tools.py,sha256=6uB2424SLtmapui9ggcEr0ZTiB6_dL1-JRGgN8RK9Js,1332
 langroid/agent/special/table_chat_agent.py,sha256=zejrvv6GaspImVJ1oXWUTVN-h-kDjadTdBDkTRqrYKo,7691
-langroid/agent/task.py,sha256=bllafGA9AbVaeL6qk1a-1Wa2sc6fsuzeNEyhKHav3K8,36260
+langroid/agent/task.py,sha256=lMn8zffp0HlA9aLfw8UrWWd8Ni5jbIuCj2COBThBk2U,36293
 langroid/agent/tool_message.py,sha256=_QS9_JnBdMBmpQw-ocu3PdJz_UzkFCytVky0UdIcMe0,6320
 langroid/agent/tools/__init__.py,sha256=6le5y_iPEHwh7Tli_0MtwCGOjy3tPQfAdfDC7WBg2e0,172
 langroid/agent/tools/extract_tool.py,sha256=u5lL9rKBzaLBOrRyLnTAZ97pQ1uxyLP39XsWMnpaZpw,3789
@@ -57,7 +57,7 @@ langroid/parsing/config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/parsing/document_parser.py,sha256=YC3IXQ9ErpBGBZh6Be9gfJWHcTwGTSMfNQMT5ARrj5g,14615
 langroid/parsing/json.py,sha256=MVqBUfInALQm1QKbcfEvLzWxBz_UztCIyGk7AK5uFPo,1650
 langroid/parsing/para_sentence_split.py,sha256=AJBzZojP3zpB-_IMiiHismhqcvkrVBQ3ZINoQyx_bE4,2000
-langroid/parsing/parser.py,sha256=kQY6pqToc_x2a96ElrcK2vA3cX9t4KN4c20WTRHPh9A,9297
+langroid/parsing/parser.py,sha256=HU8d8wzzo2rSX2tJFYVLbf_gZ3qtz6goDkctdkNHuzw,10032
 langroid/parsing/repo_loader.py,sha256=4qCyRRHCKIYd8F1ghT-D8ko1C2sXpF7UYP1L5Im1hRE,27705
 langroid/parsing/search.py,sha256=xmQdAdTIwZ0REEUeQVFlGZlqf7k8Poah7-ALuyW7Ov0,8440
 langroid/parsing/spider.py,sha256=w_mHR1B4KOmxsBLoVI8kMkMTEbwTzeK3ath9fOMJrTk,3043
@@ -97,7 +97,7 @@ langroid/vector_store/meilisearch.py,sha256=h4e1MZJ9J3EnFfcUhLshK1Duwy1dpHWH4Ajt
 langroid/vector_store/momento.py,sha256=otoUrpgwEduFOCUhbFFSZWKEzWF2di1d4-m3n5PIuHI,9964
 langroid/vector_store/qdrant_cloud.py,sha256=3im4Mip0QXLkR6wiqVsjV1QvhSElfxdFSuDKddBDQ-4,188
 langroid/vector_store/qdrantdb.py,sha256=ZEJnlNIJwWIySGhPz3jBc6spcLCPqOcUDBYBisLF90I,11379
-langroid-0.1.133.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.1.133.dist-info/METADATA,sha256=xYZstplklmIMJtwIkpDrUMT_agwXItOwPoUtgp8juoQ,42453
-langroid-0.1.133.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
-langroid-0.1.133.dist-info/RECORD,,
+langroid-0.1.134.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.1.134.dist-info/METADATA,sha256=IJPjs9SDcsyMwSqS5yWg0N4vPpxHEJzwzHTqlMaiSvI,42646
+langroid-0.1.134.dist-info/WHEEL,sha256=FMvqSimYX_P7y0a7UY-_Mc83r5zkBZsCYPm7Lr0Bsq4,88
+langroid-0.1.134.dist-info/RECORD,,