Merge pull request #77 from gschmutz/main

update to remove OLLAMA_MODEL, which has been replaced by LOCAL_LLM in the code

Author: rlancemartin

.env.example

@@ -1,7 +1,3 @@
- 
-OLLAMA_BASE_URL=http://localhost:11434 # the endpoint of the Ollama service, defaults to http://localhost:11434 if not set
-OLLAMA_MODEL=llama3.2 # the name of the model to use, defaults to 'llama3.2' if not set
-
 # Which search service to use, either 'duckduckgo', 'tavily', 'perplexity', Searxng
 SEARCH_API='duckduckgo'
 # For Searxng search, defaults to http://localhost:8888
@@ -13,8 +9,9 @@ PERPLEXITY_API_KEY=pplx-xxxxx  # Get your key at https://www.perplexity.ai
 
 # LLM Configuration
 LLM_PROVIDER=lmstudio          # Options: ollama, lmstudio
-LOCAL_LLM=qwen_qwq-32b         # Model name in LMStudio
+LOCAL_LLM=qwen_qwq-32b         # Model name in LMStudio/Ollama
 LMSTUDIO_BASE_URL=http://localhost:1234/v1  # LMStudio OpenAI-compatible API URL
+OLLAMA_BASE_URL=http://localhost:11434 # the endpoint of the Ollama service, defaults to http://localhost:11434 if not set
 
 MAX_WEB_RESEARCH_LOOPS=3
 FETCH_FULL_PAGE=True

README.md

@@ -39,8 +39,9 @@ ollama pull deepseek-r1:8b
 
 * If set, these values will take precedence over the defaults set in the `Configuration` class in `configuration.py`. 
 ```shell
-OLLAMA_BASE_URL="url" # Ollama service endpoint, defaults to `http://localhost:11434` 
-OLLAMA_MODEL=model # the model to use, defaults to `llama3.2` if not set
+LLM_PROVIDER=ollama
+OLLAMA_BASE_URL="http://localhost:11434" # Ollama service endpoint, defaults to `http://localhost:11434` 
+LOCAL_LLM=model # the model to use, defaults to `llama3.2` if not set
 ```
 
 ### Selecting local model with LMStudio
@@ -185,21 +186,22 @@ https://github.com/PacoVK/ollama-deep-researcher-ts
 
 ## Running as a Docker container
 
-The included `Dockerfile` only runs LangChain Studio with ollama-deep-researcher as a service, but does not include Ollama as a dependant service. You must run Ollama separately and configure the `OLLAMA_BASE_URL` environment variable. Optionally you can also specify the Ollama model to use by providing the `OLLAMA_MODEL` environment variable.
+The included `Dockerfile` only runs LangChain Studio with local-deep-researcher as a service, but does not include Ollama as a dependant service. You must run Ollama separately and configure the `OLLAMA_BASE_URL` environment variable. Optionally you can also specify the Ollama model to use by providing the `LOCAL_LLM` environment variable.
 
 Clone the repo and build an image:
 ```
-$ docker build -t ollama-deep-researcher .
+$ docker build -t local-deep-researcher .
 ```
 
 Run the container:
 ```
 $ docker run --rm -it -p 2024:2024 \
   -e SEARCH_API="tavily" \ 
   -e TAVILY_API_KEY="tvly-***YOUR_KEY_HERE***" \
+  -e LLM_PROVIDER=ollama
   -e OLLAMA_BASE_URL="http://host.docker.internal:11434/" \
-  -e OLLAMA_MODEL="llama3.2" \  
-  ollama-deep-researcher
+  -e LOCAL_LLM="llama3.2" \  
+  local-deep-researcher
 ```
 
 NOTE: You will see log message: