langroid 0.1.24__py3-none-any.whl → 0.1.26__py3-none-any.whl

langroid/cachedb/redis_cachedb.py

@@ -17,8 +17,6 @@ class RedisCacheConfig(BaseModel):
     """Configuration model for RedisCache."""
 
     fake: bool = False
-    hostname: str = "redis-11524.c251.east-us-mz.azure.cloud.redislabs.com"
-    port: int = 11524
 
 
 class RedisCache(CacheDB):
@@ -38,16 +36,18 @@ class RedisCache(CacheDB):
             self.client = fakeredis.FakeStrictRedis()  # type: ignore
         else:
             redis_password = os.getenv("REDIS_PASSWORD")
-            if redis_password is None:
+            redis_host = os.getenv("REDIS_HOST")
+            redis_port = os.getenv("REDIS_PORT")
+            if None in [redis_password, redis_host, redis_port]:
                 logger.warning(
-                    """REDIS_PASSWORD not set in .env file,
+                    """REDIS_PASSWORD, REDIS_HOST, REDIS_PORT not set in .env file,
                     using fake redis client"""
                 )
                 self.client = fakeredis.FakeStrictRedis()  # type: ignore
             else:
                 self.client = redis.Redis(  # type: ignore
-                    host=self.config.hostname,
-                    port=self.config.port,
+                    host=redis_host,
+                    port=redis_port,
                     password=redis_password,
                 )
 

langroid/vector_store/qdrantdb.py

@@ -29,7 +29,6 @@ logger = logging.getLogger(__name__)
 class QdrantDBConfig(VectorStoreConfig):
     type: str = "qdrant"
     cloud: bool = True
-    url = "https://644cabc3-4141-4734-91f2-0cc3176514d4.us-east-1-0.aws.cloud.qdrant.io:6333"
 
     collection_name: str | None = None
     storage_path: str = ".qdrant/data"
@@ -49,17 +48,20 @@ class QdrantDB(VectorStore):
         self.host = config.host
         self.port = config.port
         load_dotenv()
+        key = os.getenv("QDRANT_API_KEY")
+        url = os.getenv("QDRANT_API_URL")
+        if config.cloud and None in [key, url]:
+            logger.warning(
+                f"""QDRANT_API_KEY, QDRANT_API_URL env variable must be set to use 
+                QdrantDB in cloud mode. Please set these values 
+                in your .env file. 
+                Switching to local storage at {config.storage_path} 
+                """
+            )
+            config.cloud = False
         if config.cloud:
-            key = os.getenv("QDRANT_API_KEY")
-            if key is None or key == "":
-                raise ValueError(
-                    """QDRANT_API_KEY env variable must be set to use 
-                    QdrantDB in cloud mode. Please set the QDRANT_API_KEY value 
-                    in your .env file.
-                    """
-                )
             self.client = QdrantClient(
-                url=config.url,
+                url=url,
                 api_key=key,
                 timeout=config.timeout,
             )

{langroid-0.1.24.dist-info → langroid-0.1.26.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: langroid
-Version: 0.1.24
+Version: 0.1.26
 Summary: Harness LLMs with Multi-Agent Programming
 License: MIT
 Author: Prasad Chalasani
@@ -57,7 +57,7 @@ Requires-Dist: wget (>=3.2,<4.0)
 Description-Content-Type: text/markdown
 
 <div align="center">
-  <img src="docs/assets/langroid-card-ossem-rust-1200x630.png" alt="Logo" 
+  <img src="docs/assets/langroid-card-lambda-ossem-rust-1200-630.png" alt="Logo" 
         width="400" align="center">
 </div>
 
@@ -75,47 +75,53 @@ Description-Content-Type: text/markdown
   <a target="_blank" 
     href="https://langroid.github.io/langroid/" rel="dofollow">
       <strong>Explore the docs</strong></a>
-  ·
+  &middot;
   <a target="_blank" href="https://github.com/langroid/langroid-examples" rel="dofollow">
       <strong>Examples Repo</strong></a>
-  .
+  &middot;
   <a target="_blank" href="https://discord.gg/g3nAXCbZ" rel="dofollow">
       <strong>Discord</strong></a>
-  .
+  &middot;
   <a target="_blank" href="./CONTRIBUTING.md" rel="dofollow">
       <strong>Contributing</strong></a>
 
   <br />
 </h3>
 
-`Langroid` is an intuitive, lightweight, transparent, extensible and principled
-Python framework to super-charge development of LLM-powered applications using Multi-Agent Programming.
-Inspired by the [Actor Framework](https://en.wikipedia.org/wiki/Actor_model), 
-it is the first LLM-application framework that was explicitly
-designed with Agents as first-class citizens, and Multi-Agent Programming
-as the core design principle.
+`Langroid` is an intuitive, lightweight, extensible and principled
+Python framework to easily build LLM-powered applications. 
+You set up Agents, equip them with optional components (LLM, 
+vector-store and methods), assign them tasks, and have them 
+collaboratively solve a problem by exchanging messages. 
+This Multi-Agent paradigm is inspired by the
+[Actor Framework](https://en.wikipedia.org/wiki/Actor_model)
+(but you do not need to know anything about this!).
 
 
 # :rocket: Demo
-
-A `LeaseExtractor` agent is tasked with extracting structured information
-from a commercial lease document. The Agent's LLM generates questions that are 
-answered by a `DocAgent` (its LLM) using Retrieval from a vector-database
-(into which the lease has been sharded + embedded).
-When it has all the information it needs, the `LeaseExtractor` agent's LLM
-presents the information in a structured format using a Function-call.
-You can run this script from the 
-[langroid-examples](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat_multi_extract.py) repo.
+Suppose you want to extract structured information about the key terms 
+of a commercial lease document. You can easily do this with Langroid using a two-agent system,
+as we show in the [langroid-examples](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat_multi_extract.py) repo.
+The demo showcases several features of Langroid:
+- Multi-agent collaboration: `LeaseExtractor` is in charge of the task, and its LLM (GPT4) generates questions 
+to be answered by the `DocAgent`.
+- Retrieval augmented question-answering: `DocAgent` LLM (GPT4) uses retrieval from a vector-store to 
+answer the `LeaseExtractor`'s questions.
+- Function-calling (also known as tool/plugin): When it has all the information it 
+needs, the `LeaseExtractor` LLM presents the information in a structured 
+format using a Function-call. 
+
+Here is what it looks like in action:
 
 ![Demo](docs/assets/demos/lease-extractor-demo.gif)
 
 
 # :zap: Highlights
 
-- **Agents as first-class citizens:** The `Agent` class encapsulates LLM conversation state,
+- **Agents as first-class citizens:** The [Agent](https://langroid.github.io/langroid/reference/agent/base/#langroid.agent.base.Agent) class encapsulates LLM conversation state,
   and optionally a vector-store and tools. Agents are a core abstraction in Langroid;
   Agents act as _message transformers_, and by default provide 3 _responder_ methods, one corresponding to each entity: LLM, Agent, User.
-- **Tasks:** A Task class wraps an Agent, and gives the agent instructions (or roles, or goals), 
+- **Tasks:** A [Task](https://langroid.github.io/langroid/reference/agent/task/) class wraps an Agent, and gives the agent instructions (or roles, or goals), 
   manages iteration over an Agent's responder methods, 
   and orchestrates multi-agent interactions via hierarchical, recursive
   task-delegation. The `Task.run()` method has the same 
@@ -166,34 +172,47 @@ Note that this will install `torch` and `sentence-transformers` libraries.
 
 ### Set up environment variables (API keys, etc)
 
-Copy the `.env-template` file to a new file `.env` and 
-insert these secrets:
-- **OpenAI API** key (required): If you don't have one, see [this OpenAI Page](https://help.openai.com/en/collections/3675940-getting-started-with-openai-api).
-- **Qdrant** Vector Store API Key (required for apps that need retrieval from
-  documents): Sign up for a free 1GB account at [Qdrant cloud](https://cloud.qdrant.io).
+In the root of the repo, copy the `.env-template` file to a new file `.env`: 
+```bash
+cp .env-template .env
+```
+Then insert your OpenAI API Key. If you don't have one, see [this OpenAI Page](https://help.openai.com/en/collections/3675940-getting-started-with-openai-api).
+Your `.env` file should look like this:
+
+```bash
+OPENAI_API_KEY=your-key-here-without-quotes
+````
+
+Currently only OpenAI models are supported. Others will be added later
+(Pull Requests welcome!).
+
+All of the below are optional and not strictly needed to run any of the examples.
+
+- **Qdrant** Vector Store API Key, URL. This is only required if you want to use Qdrant cloud.
+  You can sign up for a free 1GB account at [Qdrant cloud](https://cloud.qdrant.io).
+  If you skip setting up these, Langroid will use Qdrant in local-storage mode.
   Alternatively [Chroma](https://docs.trychroma.com/) is also currently supported. 
   We use the local-storage version of Chroma, so there is no need for an API key.
+- **Redis** Password, host, port: This is optional, and only needed to cache LLM API responses
+  using Redis Cloud. Redis [offers](https://redis.com/try-free/) a free 30MB Redis account
+  which is more than sufficient to try out Langroid and even beyond.
+  If you don't set up these, Langroid will use a pure-python 
+  Redis in-memory cache via the [Fakeredis](https://fakeredis.readthedocs.io/en/latest/) library.
 - **GitHub** Personal Access Token (required for apps that need to analyze git
   repos; token-based API calls are less rate-limited). See this
   [GitHub page](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens).
-- **Redis** Password (optional, only needed to cache LLM API responses):
-  Redis [offers](https://redis.com/try-free/) a free 30MB Redis account
-  which is more than sufficient to try out Langroid and even beyond.
-  
-```bash
-cp .env-template .env
-# now edit the .env file, insert your secrets as above
-``` 
-Your `.env` file should look like this:
+
+If you add all of these optional variables, your `.env` file should look like this:
 ```bash
-OPENAI_API_KEY=<your key>
-GITHUB_ACCESS_TOKEN=<your token>
-REDIS_PASSWORD=<your password>
-QDRANT_API_KEY=<your key>
+OPENAI_API_KEY=your-key-here-without-quotes
+GITHUB_ACCESS_TOKEN=your-personal-access-token-no-quotes
+REDIS_PASSWORD=your-redis-password-no-quotes
+REDIS_HOST=your-redis-hostname-no-quotes
+REDIS_PORT=your-redis-port-no-quotes
+QDRANT_API_KEY=your-key
+QDRANT_API_URL=https://your.url.here:6333 # note port number must be included
 ```
 
-Currently only OpenAI models are supported. Others will be added later
-(Pull Requests welcome!).
 
 ---
 
@@ -207,24 +226,21 @@ and they are **not** complete runnable examples! For that we encourage you to
 consult the [`langroid-examples`](https://github.com/langroid/langroid-examples) 
 repository.
 
-:information_source: The examples below will only work with OpenAI GPT4 model,
-which is the default in Langroid. Switching to GPT3.5-Turbo is easy via a config 
-flag, but results may be inferior.
+:information_source: The various LLM prompts and instructions in Langroid
+have been tested to work well with GPT4.
+Switching to GPT3.5-Turbo is easy via a config flag
+(e.g., `cfg = OpenAIGPTConfig(chat_model=OpenAIChatModel.GPT3_5_TURBO)`),
+and may suffice for some applications, but in general you may see inferior results.
+
 
 :book: Also see the
 [`Getting Started Guide`](https://langroid.github.io/langroid/quick-start/)
-for a detailed tutorial. 
+for a detailed tutorial.
 
-- [Direct chat with LLM](#direct-llm)
-- [Simple Agent and Task](#agent-task)
-- [Three Communicating Agents](#three-agents)
-- [Agent with Tool/Function-calling](#agent-tool)
-- [Extract Structured Info with Tool/Function-calling](#agent-tool-structured)
-- [Retrieval-Augmented-Generation: Chat with Docs](#agent-rag)
-
----
+Click to expand any of the code examples below:
 
-## Direct interaction with OpenAI LLM <a name="direct-llm"></a>
+<details>
+<summary> <b> Direct interaction with OpenAI LLM </b> </summary>
 
 ```python
 from langroid.language_models.openai_gpt import ( 
@@ -243,10 +259,10 @@ messages = [
 response = mdl.chat(messages, max_tokens=200)
 print(response.message)
 ```
+</details>
 
----
-
-## Define an agent, set up a task, and run it <a name="agent-task"></a>
+<details>
+<summary> <b> Define an agent, set up a task, and run it </b> </summary>
 
 ```python
 from langroid.agent.chat_agent import ChatAgent, ChatAgentConfig
@@ -266,10 +282,12 @@ agent = ChatAgent(config)
 task = Task(agent, name="Bot") 
 task.run() # ... a loop seeking response from LLM or User at each turn
 ```
+</details>
 
----
+<details>
+<summary><b> Three communicating agents </b></summary>
 
-## Three communicating agents <a name="three-agents"></a>
+```python
 
 A toy numbers game, where when given a number `n`:
 - `repeater_agent`'s LLM simply returns `n`,
@@ -329,9 +347,11 @@ and run the `repeater_task`, kicking it off with a number as input:
 repeater_task.add_sub_task([even_task, odd_task])
 repeater_task.run("3")
 ```
----
 
-## Simple Tool/Function-calling example <a name="agent-tool"></a>
+</details>
+
+<details>
+<summary><b> Simple Tool/Function-calling example </b></summary>
 
 Langroid leverages Pydantic to support OpenAI's
 [Function-calling API](https://platform.openai.com/docs/guides/gpt/function-calling)
@@ -396,10 +416,10 @@ spy_game_agent.enable_message(ProbeTool)
 For a full working example see the
 [chat-agent-tool.py](https://github.com/langroid/langroid-examples/blob/main/examples/quick-start/chat-agent-tool.py)
 script in the `langroid-examples` repo.
+</details>
 
----
-
-## Tool/Function-calling to extract structured information from text <a name="agent-tool-structured"></a>
+<details>
+<summary> <b>Tool/Function-calling to extract structured information from text </b> </summary>
 
 Suppose you want an agent to extract 
 the key terms of a lease, from a lease document, as a nested JSON structure.
@@ -460,10 +480,10 @@ lease_extractor_agent.enable_message(LeaseMessage)
 
 See the [`chat_multi_extract.py`](https://github.com/langroid/langroid-examples/blob/main/examples/docqa/chat_multi_extract.py)
 script in the `langroid-examples` repo for a full working example.
+</details>
 
----
-
-## Chat with documents (file paths, URLs, etc) <a name="agent-docs"></a>
+<details>
+<summary><b> Chat with documents (file paths, URLs, etc) </b></summary>
 
 Langroid provides a specialized agent class `DocChatAgent` for this purpose.
 It incorporates document sharding, embedding, storage in a vector-DB, 
@@ -509,9 +529,14 @@ task.run()
 See full working scripts in the 
 [`docqa`](https://github.com/langroid/langroid-examples/tree/main/examples/docqa)
 folder of the `langroid-examples` repo.
+</details>
 
 ---
 
+# :heart: Thank you to our supporters!
+
+[![Stargazers repo roster for @langroid/langroid](https://reporoster.com/stars/langroid/langroid)](https://github.com/langroid/langroid/stargazers)
+
 # Contributors
 
 - Prasad Chalasani (IIT BTech/CS, CMU PhD/ML; Independent ML Consultant)

{langroid-0.1.24.dist-info → langroid-0.1.26.dist-info}/RECORD

@@ -14,7 +14,7 @@ langroid/agent/tool_message.py,sha256=7OdVcV7UyOZD2ihYgV1C_1fIwiWM-2pR8FFxoA1IgO
 langroid/agent_config.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/cachedb/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/cachedb/base.py,sha256=F-QSDlRXrC0tBRbxL397MX8hulfBMAnZNs1e9zH71OQ,790
-langroid/cachedb/redis_cachedb.py,sha256=TUBQJ5etrU4jN2bJ3wNHC3h3Le8ez65psNiMrVAfh4w,2335
+langroid/cachedb/redis_cachedb.py,sha256=xuQ96FAqcHTfK8PEt1tjrh1BkMWUjojFHIgjDfF3SnU,2369
 langroid/embedding_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 langroid/embedding_models/base.py,sha256=176jDrjEAAhNzdFCG8pfossd8SAhvHR8Q5Y8pOOm0LI,983
 langroid/embedding_models/clustering.py,sha256=tZWElUqXl9Etqla0FAa7og96iDKgjqWjucZR_Egtp-A,6684
@@ -60,8 +60,8 @@ langroid/vector_store/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3h
 langroid/vector_store/base.py,sha256=QZx3NUNwf2I0r3A7iuoUHIRGbqt_pFGD0hq1R-Yg8iM,3740
 langroid/vector_store/chromadb.py,sha256=GPaXNPgPGIVUwYx2eO_-kreQoJ_33IFo13oigH5BP1c,5200
 langroid/vector_store/qdrant_cloud.py,sha256=3im4Mip0QXLkR6wiqVsjV1QvhSElfxdFSuDKddBDQ-4,188
-langroid/vector_store/qdrantdb.py,sha256=y7-fMxOqMJoYbdSfIr_HKcTIWTRpnb9j3Yg5EcOyFd4,8522
-langroid-0.1.24.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
-langroid-0.1.24.dist-info/WHEEL,sha256=vVCvjcmxuUltf8cYhJ0sJMRDLr1XsPuxEId8YDzbyCY,88
-langroid-0.1.24.dist-info/METADATA,sha256=IbMs68QIj-RR1cHyZgQ-3rvEKYz5lKJQJ6gnaox5dkQ,19720
-langroid-0.1.24.dist-info/RECORD,,
+langroid/vector_store/qdrantdb.py,sha256=cnxCrp4yIdbJ7-pz7yRoepJhd29mOzwacV2C6O7G_AQ,8548
+langroid-0.1.26.dist-info/LICENSE,sha256=EgVbvA6VSYgUlvC3RvPKehSg7MFaxWDsFuzLOsPPfJg,1065
+langroid-0.1.26.dist-info/WHEEL,sha256=vVCvjcmxuUltf8cYhJ0sJMRDLr1XsPuxEId8YDzbyCY,88
+langroid-0.1.26.dist-info/METADATA,sha256=ozd74VngEPA1ZcQrREhERhw2Byb3h0wCuzAlaNJOsWo,21039
+langroid-0.1.26.dist-info/RECORD,,