Merge branch 'master' of github.com:hwchase17/langchain

docs/ecosystem/yeagerai.md

@@ -0,0 +1,43 @@
+# Yeager.ai
+
+This page covers how to use [Yeager.ai](https://yeager.ai) to generate LangChain tools and agents.
+
+## What is Yeager.ai?
+Yeager.ai is an ecosystem designed to simplify the process of creating AI agents and tools. 
+
+It features yAgents, a No-code LangChain Agent Builder, which enables users to build, test, and deploy AI solutions with ease. Leveraging the LangChain framework, yAgents allows seamless integration with various language models and resources, making it suitable for developers, researchers, and AI enthusiasts across diverse applications.
+
+## yAgents
+Low code generative agent designed to help you build, prototype, and deploy Langchain tools with ease. 
+
+### How to use?
+```
+pip install yeagerai-agent
+yeagerai-agent
+```
+Go to http://127.0.0.1:7860
+
+This will install the necessary dependencies and set up yAgents on your system. After the first run, yAgents will create a .env file where you can input your OpenAI API key. You can do the same directly from the Gradio interface under the tab "Settings".
+
+`OPENAI_API_KEY=<your_openai_api_key_here>`
+
+We recommend using GPT-4,. However, the tool can also work with GPT-3 if the problem is broken down sufficiently.
+
+### Creating and Executing Tools with yAgents
+yAgents makes it easy to create and execute AI-powered tools. Here's a brief overview of the process:
+1. Create a tool: To create a tool, provide a natural language prompt to yAgents. The prompt should clearly describe the tool's purpose and functionality. For example:
+`create a tool that returns the n-th prime number`
+
+2. Load the tool into the toolkit: To load a tool into yAgents, simply provide a command to yAgents that says so. For example:
+`load the tool that you just created it into your toolkit`
+
+3. Execute the tool: To run a tool or agent, simply provide a command to yAgents that includes the name of the tool and any required parameters. For example:
+`generate the 50th prime number`
+
+You can see a video of how it works [here](https://www.youtube.com/watch?v=KA5hCM3RaWE).
+
+As you become more familiar with yAgents, you can create more advanced tools and agents to automate your work and enhance your productivity.
+
+For more information, see [yAgents' Github](https://github.com/yeagerai/yeagerai-agent) or our [docs](https://yeagerai.gitbook.io/docs/general/welcome-to-yeager.ai) 
+
+

langchain/callbacks/comet_ml_callback.py

@@ -130,7 +130,7 @@ class CometCallbackHandler(BaseMetadataCallbackHandler, BaseCallbackHandler):
         warning = (
             "The comet_ml callback is currently in beta and is subject to change "
             "based on updates to `langchain`. Please report any issues to "
-            "https://github.com/comet-ml/issue_tracking/issues with the tag "
+            "https://github.com/comet-ml/issue-tracking/issues with the tag "
             "`langchain`."
         )
         self.comet_ml.LOGGER.warning(warning)

langchain/chains/conversational_retrieval/base.py

@@ -15,16 +15,32 @@ from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_
 from langchain.chains.llm import LLMChain
 from langchain.chains.question_answering import load_qa_chain
 from langchain.prompts.base import BasePromptTemplate
-from langchain.schema import BaseLanguageModel, BaseRetriever, Document
+from langchain.schema import BaseLanguageModel, BaseMessage, BaseRetriever, Document
 from langchain.vectorstores.base import VectorStore
 
+# Depending on the memory type and configuration, the chat history format may differ.
+# This needs to be consolidated.
+CHAT_TURN_TYPE = Union[Tuple[str, str], BaseMessage]
 
-def _get_chat_history(chat_history: List[Tuple[str, str]]) -> str:
+
+_ROLE_MAP = {"human": "Human: ", "ai": "Assistant: "}
+
+
+def _get_chat_history(chat_history: List[CHAT_TURN_TYPE]) -> str:
     buffer = ""
-    for human_s, ai_s in chat_history:
-        human = "Human: " + human_s
-        ai = "Assistant: " + ai_s
-        buffer += "\n" + "\n".join([human, ai])
+    for dialogue_turn in chat_history:
+        if isinstance(dialogue_turn, BaseMessage):
+            role_prefix = _ROLE_MAP.get(dialogue_turn.type, f"{dialogue_turn.type}: ")
+            buffer += f"\n{role_prefix}{dialogue_turn.content}"
+        elif isinstance(dialogue_turn, tuple):
+            human = "Human: " + dialogue_turn[0]
+            ai = "Assistant: " + dialogue_turn[1]
+            buffer += "\n" + "\n".join([human, ai])
+        else:
+            raise ValueError(
+                f"Unsupported chat history format: {type(dialogue_turn)}."
+                f" Full chat history: {chat_history} "
+            )
     return buffer
 
 
@@ -35,7 +51,7 @@ class BaseConversationalRetrievalChain(Chain):
     question_generator: LLMChain
     output_key: str = "answer"
     return_source_documents: bool = False
-    get_chat_history: Optional[Callable[[Tuple[str, str]], str]] = None
+    get_chat_history: Optional[Callable[[CHAT_TURN_TYPE], str]] = None
     """Return the source documents."""
 
     class Config:

langchain/chains/sql_database/prompt.py

@@ -40,6 +40,27 @@ DECIDER_PROMPT = PromptTemplate(
     output_parser=CommaSeparatedListOutputParser(),
 )
 
+_duckdb_prompt = """You are a DuckDB expert. Given an input question, first create a syntactically correct DuckDB query to run, then look at the results of the query and return the answer to the input question.
+Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per DuckDB. You can order the results to return the most informative data in the database.
+Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
+Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
+
+Use the following format:
+
+Question: "Question here"
+SQLQuery: "SQL Query to run"
+SQLResult: "Result of the SQLQuery"
+Answer: "Final answer here"
+
+Only use the following tables:
+{table_info}
+
+Question: {input}"""
+
+DUCKDB_PROMPT = PromptTemplate(
+    input_variables=["input", "table_info", "top_k"],
+    template=_duckdb_prompt,
+)
 
 _googlesql_prompt = """You are a GoogleSQL expert. Given an input question, first create a syntactically correct GoogleSQL query to run, then look at the results of the query and return the answer to the input question.
 Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per GoogleSQL. You can order the results to return the most informative data in the database.
@@ -201,6 +222,7 @@ SQLITE_PROMPT = PromptTemplate(
 
 
 SQL_PROMPTS = {
+    "duckdb": DUCKDB_PROMPT,
     "googlesql": GOOGLESQL_PROMPT,
     "mssql": MSSQL_PROMPT,
     "mysql": MYSQL_PROMPT,

langchain/document_loaders/html_bs.py

@@ -24,7 +24,8 @@ class BSHTMLLoader(BaseLoader):
             import bs4  # noqa:F401
         except ImportError:
             raise ValueError(
-                "bs4 package not found, please install it with " "`pip install bs4`"
+                "beautifulsoup4 package not found, please install it with "
+                "`pip install beautifulsoup4`"
             )
 
         self.file_path = file_path